Suspension bridge cable clamp digital twin system based on wireless intelligent washers

Abstract

The invention provides a suspension bridge cable clamp digital twin system based on wireless intelligent washers, and belongs to the crossing field of bridge engineering and intelligent monitoring technologies. According to the system, a wireless intelligent gasket is used as a core sensing unit, finite element analysis, a neural network agent model and a three-dimensional visualization technology are combined, and real-time mapping of a cable clamp physical entity and a virtual model is constructed; the system obtains data such as wireless intelligent gasket pressure, cable clamp-main cable friction force, cable clamp displacement and cable clamp structure node stress and strain through finite element analysis under different working conditions, and a parameter mapping proxy model is formed by training a mapping relation between the gasket pressure and other parameters through a neural network. And relevant models and data are developed and integrated by means of an Unreal Engine engine, and visualized real-time rendering is carried out, so that bolt fastening control in a construction stage and / or structural health monitoring in an operation and maintenance stage are / is realized. According to the system, digital management and control of the full life cycle of the cable clamp can be realized, and the monitoring precision and the engineering economy are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the interdisciplinary field of bridge engineering and intelligent monitoring technology, and relates to a digital twin system for cable clamps based on wireless intelligent washers. It is particularly suitable for the full life cycle monitoring and control of the connection nodes between cable clamps and main cables and suspenders in spatial cable-stayed suspension bridges, and can be widely used in bridge construction control, operation and maintenance management and safety early warning scenarios. Background Technology

[0002] In long-span cable-stayed bridge structures, cable clamps are the core load-bearing components that transmit force between the main cable and the suspenders, and their performance directly determines the safety and durability of the overall bridge structure. Cable clamps achieve a reliable connection with the main cable through friction generated by the pre-tightening of circumferentially distributed high-strength bolts, while simultaneously balancing the vertical and lateral loads transmitted by the suspenders through the axial force of the bolts. During bridge construction and operation, the pre-tightening force of the cable clamp bolts can decrease due to factors such as material creep, vibration relaxation, and environmental corrosion, leading to relative slippage between the cable clamp and the main cable. This can cause problems such as stress imbalance in the suspenders and localized stress concentration in the main cable, potentially resulting in structural failure in severe cases.

[0003] Currently, the monitoring of cable clamp bolt preload and cable clamp condition mainly relies on the following technical means: 1. Manual inspection and spot check: The bolt preload is checked periodically by using a torque wrench. This method is inefficient, labor-intensive, and cannot achieve real-time monitoring, making it difficult to capture the dynamic changes in preload. 2. Traditional sensor monitoring: This method uses resistance strain gauges attached to the bolt surface or piezoelectric sensors for monitoring. These methods require wiring connections, are complex to install, and are susceptible to environmental interference. They also have poor stability under harsh conditions such as humidity and vibration. 3. Finite element simulation analysis: The change of preload is simulated by establishing a cable clamp-main cable coupling model, but the model parameters are different from the actual working conditions, making it difficult to reflect the real stress state and unable to achieve real-time interaction with the physical entity; 4. Preliminary applications of digital twins: Some studies have attempted to construct digital models of cable clips, but they mostly focus on geometric modeling and lack a dynamic update mechanism based on real-time monitoring data, making it impossible to achieve accurate mapping and state prediction.

[0004] To address the aforementioned technical shortcomings, the industry urgently needs an intelligent system capable of real-time sensing of the axial force status of cable clamp bolts, accurate mapping of physical entities, and full lifecycle management. Wireless smart washers, as a novel load monitoring element, directly measure bolt axial force based on the principle of material elastic deformation. They offer advantages such as convenient installation, low cost, and adaptability to harsh environments, providing a new technological path for cable clamp status monitoring. However, current technologies lack a system solution that deeply integrates wireless smart washers with digital twin technology. There is a lack of coupled analysis of washer monitoring data and multiple cable clamp parameters (such as cable tension, tilt angle, and displacement). Furthermore, there are technological gaps in areas such as optimizing crosstalk effects during bolt tightening during construction and providing early warning of failure modes during operation and maintenance.

[0005] Therefore, developing a digital twin system for cable clamps that integrates real-time monitoring of wireless intelligent washers, finite element analysis, neural network proxy models, and 3D visualization technologies is of great significance for improving the monitoring accuracy, construction efficiency, and operation and maintenance safety of cable clamp structures in spatial cable-stayed suspension bridges. Summary of the Invention

[0006] In view of this, the purpose of this invention is to solve the problems of poor real-time performance, insufficient multi-parameter coupling analysis, low construction efficiency, and delayed operation and maintenance early warning in existing cable clamp monitoring technologies. It provides a cable clamp digital twin system based on wireless smart washers. By constructing a dynamic mapping between physical entities and virtual models, it realizes real-time monitoring and analysis of parameters such as cable clamp bolt preload, cable inclination angle, and cable clamp displacement, optimizes the fastening strategy during the construction phase, improves the early warning capability during the operation and maintenance phase, and ultimately ensures the safety of bridge structures.

[0007] To achieve the above objectives, the present invention provides the following technical solution: Optionally, a digital twin system for suspension bridge cable clamps based on wireless smart washers uses the wireless smart washer as the sole core sensing unit. Through an innovative architecture of "single-source sensing - model deduction - virtual-real linkage," it achieves precise control over the entire lifecycle of the cable clamps. This system mainly includes a data acquisition module, a finite element analysis module, a proxy model module, a 3D visualization module, a construction control module, and an operation and maintenance monitoring module. Specifically, the data acquisition module acquires bolt pressure data solely through the wireless smart washer unit, without relying on other auxiliary sensors; the finite element analysis module constructs a mechanical model to analyze parameter correlations; the proxy model module uses a neural network to map washer pressure to multiple parameters; the 3D visualization module builds a digital twin with virtual-real interaction; the construction control module optimizes bolt tightening strategies; and the operation and maintenance monitoring module provides status warnings and failure assessments. All modules work collaboratively, outputting multi-dimensional parameters of the cable clamp status through input from a single sensor, significantly simplifying hardware deployment and improving system versatility.

[0008] Optionally, the data acquisition module uses a wireless smart washer unit as the sole sensing carrier. Its design is fully adapted to the high-strength stress environment of cable clamp bolts and requires no additional sensors. The wireless smart washer unit includes a wireless smart washer, which is based on the principle of material elastic deformation. A load detection element and a micro-displacement sensor are built into the washer body: the load detection element forms a full-bridge measurement circuit through a strain gauge array, accurately capturing the elastic deformation caused by the bolt axial force and converting it into an electrical signal output; the micro-displacement sensor simultaneously monitors the axial micro-deformation of the washer after compression, complementing the strain data and improving monitoring reliability. This washer is made of heavy-duty high-strength alloy material, its volume is compatible with standard washers, and it can withstand a unidirectional long-term load exceeding 100 tons. It is directly installed between the bolt and the cable clamp without modifying the cable clamp structure. Its built-in wireless transmission unit can send data in real time, eliminating the need for wiring, and its cost is only one-fifth of traditional multi-sensor solutions. It is highly versatile and can meet the needs of large-area installation of cable clamp bolts. The module can provide a basis for subsequent analysis using only gasket pressure data, without the need for additional sensors to collect parameters such as cable tension and tilt angle, which significantly simplifies hardware deployment.

[0009] Optionally, the finite element analysis module serves as a crucial link between physical perception and the virtual model. Its core task is to construct a digital mirror of the cable clamp's mechanical behavior. In Abaqus, the module establishes a 3D model based on the actual dimensions and material properties of the cable clamp (such as the steel type and bolt mechanical properties), refining the mesh for key areas like threads and contact interfaces to ensure simulation accuracy. By setting boundary conditions (such as frictional contact between the main cable and the cable clamp, and the method of applying bolt preload), it simulates the bolt tightening process during construction, the load on the slings during operation, and the impact of environmental factors (such as temperature changes) on the cable clamp. After multi-condition simulation, it outputs rpt files containing parameters such as node coordinates, stress values, displacement, and bolt axial force. These files serve as the data source for generating the OBJ model and as the basis for subsequent parameter mapping proxy model training. Through the finite element analysis module, the intrinsic relationship between the pressure of the wireless smart washer and parameters such as sling tension, inclination angle, and cable clamp slippage is revealed, providing theoretical support for understanding the mechanical behavior of the cable clamp.

[0010] Optionally, the proxy model module aims to address the problem of excessively long finite element simulation times by constructing an efficient parameter mapping relationship through a neural network. The module first fuses the RPT file data generated from finite element analysis with real-time monitoring data from the wireless smart gasket, removing outliers and normalizing the data to form a training dataset covering parameters such as bolt preload, cable tension, tilt angle, and cable clamp slippage. Then, a neural network model is built based on a deep learning framework, using wireless smart gasket pressure and auxiliary sensor data as input, and stress and displacement of key nodes in the cable clamp as output. Through iterative training, the network structure is optimized, enabling the model to quickly output results with accuracy comparable to finite element analysis. The trained parameter mapping proxy model is integrated into the digital twin system, responding to real-time monitoring data and outputting cable clamp state parameters within milliseconds, supporting dynamic updates and rapid decision-making for the virtual model.

[0011] Optionally, the 3D visualization module constructs an interactive digital twin of the cable clamp based on an OBJ model converted from a finite element rpt file. After importing the OBJ model into the 3D engine, the module assigns it physical properties and rendering materials, ensuring the virtual cable clamp's appearance matches the physical entity. Through a dedicated interface, real-time parameters (such as bolt preload and nodal stress) output by the parameter mapping proxy model are associated with corresponding nodes in the model, enabling interactive functionality where users can "click on a node to view the data." Users can observe the virtual cable clamp from any angle using rotation, scaling, and translation. The system uses color gradients (e.g., green for normal, red for exceeding limits) to visually display the bolt preload distribution, stress concentration areas, and slippage trends, transforming abstract mechanical parameters into visualized state information. Furthermore, the module supports historical data review and operational condition simulation. Users can select real-time monitoring data at any point in time to view the cable clamp's state at that time, or input hypothetical operational condition parameters (e.g., a sudden drop in bolt preload) to observe the virtual model's response, providing an intuitive reference for decision-making.

[0012] Optionally, the construction control module focuses on optimizing bolt tightening during the cable clamp installation phase, with the core objective of resolving crosstalk effects between multiple bolts. Based on finite element analysis results, the module quantifies the mutual influence of preload under different bolt tightening sequences (e.g., the degree of preload attenuation on adjacent bolts when a bolt is tightened), constructing a crosstalk effect matrix. Combining the target preload and the crosstalk matrix, the module calculates the over-tension of each bolt to compensate for preload loss during tightening. An intelligent algorithm selects the optimal tightening sequence, prioritizing diagonal alternating tightening to minimize crosstalk impact. During construction, the module receives real-time pressure data from the wireless smart washers, compares it with the target value, and generates adjustment instructions (e.g., "increase the preload of a bolt to the specified value") to guide precise operation by construction personnel, reduce repeated tightening, and ensure that the cable clamp installation quality meets design requirements.

[0013] Optionally, the operation and maintenance monitoring module continuously tracks real-time monitoring data from the wireless smart washers to achieve dynamic assessment and risk warning of the cable clamp's operational status. The module calculates the bolt preload decay rate, cable clamp slippage, and cable inclination changes in real time, comparing these parameters with preset thresholds. When any parameter exceeds the limit (e.g., decay rate exceeds 15%), multi-level warnings are immediately triggered (local audible and visual alarms, remote information push). Simultaneously, based on correlation analysis of node data, the module identifies typical failure modes such as overall cable clamp slippage and bolt breakage risks, automatically matching emergency response plans (e.g., temporary reinforcement measures, bolt replacement procedures). Through long-term real-time monitoring data trend analysis, the module can also predict the performance degradation patterns of the cable clamps, plan maintenance schedules in advance, avoid sudden failures, extend the service life of the cable clamps, and ensure the safety of the bridge structure.

[0014] The significant advantages of this invention are reflected in the following aspects: First, the system relies solely on the wireless intelligent washer as the only sensor, eliminating the need for other auxiliary equipment, greatly simplifying the hardware installation process, reducing costs, and avoiding the technical difficulties of multi-sensor data synchronization, thus enhancing its versatility. Second, the virtual model construction based on finite element files allows each node to carry mechanical data, achieving "single-source input, multi-parameter output" by combining a parameter mapping proxy model. This breaks through the limitations of traditional monitoring's "one sensor, one parameter," allowing the acquisition of multi-dimensional information such as cable tension and inclination angle solely through washer pressure. Third, the introduction of the proxy model enables real-time calculation with finite element-level precision, reducing parameter output time from hours to milliseconds, meeting the dynamic interaction requirements of digital twins. Fourth, both construction and operation and maintenance phases are based on single sensor data and parameter mapping proxy model parameters, resulting in a simpler operation process and significantly improving the convenience of on-site applications. Fifth, through virtual-real linkage and multi-parameter early warning, the system achieves precise control of the cable clamp throughout its entire lifecycle from construction to operation and maintenance, significantly improving the safety and durability of bridge structures and possessing broad engineering application value. Attached Figure Description

[0015] To make the objectives, technical solutions, and beneficial effects of this invention clearer, the following figures are provided for illustration: Figure 1 This is a schematic diagram of a digital twin system for suspension bridge cable clamps based on wireless smart washers, as described in this invention. Figure 2 This is a schematic diagram of the cable clip structure for installing the wireless smart washer in this invention; Figure 3 This is a schematic diagram of the neural network proxy model structure in this invention; Figure 4 This is a flowchart of the bolt tightening strategy during the construction phase of this invention; Figure 5 This is a logic diagram for early warning judgment during the operation and maintenance phase of this invention.

[0016] In the picture: 1. Nut; 2. Wireless smart washer; 3. Upper cable clip; 4. Toothed joint; 5. Lower cable clip; 6. Waterproof cap; 11. Wireless intelligent washer model; 12. Finite element model of cable clamp structure; 13. System database; 14. 3D visualization model of cable clamp structure; 15. Input layer of neural network surrogate model; 16. Hidden layer of neural network surrogate model; 17. Output layer of neural network surrogate model; 101. Data Acquisition Module; 102. Finite Element Simulation Module; 103. Neural Network Agent Module; 104. 3D Visualization Module; 105. Construction Control Module; 106. Operation and Maintenance Monitoring Module. Detailed Implementation

[0017] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can also refer to the internal connection of two components; and they can refer to a wireless connection or a wired connection. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0020] This embodiment provides a linearity monitoring system for the empty cable of a spatial cable-stayed suspension bridge, such as... Figure 1 As shown, it includes: Multiple wireless smart washer data acquisition modules 101 are used to collect target data of bolt pressure during the construction and operation of suspension bridge cable clamps; The finite element simulation module 102, also known as the finite element analysis module, is used to generate files containing parameters such as nodal coordinates, stress, and displacement in multi-condition simulations, and to provide a data foundation for virtual modeling and parameter mapping proxy model training by real-time monitoring data correction. The neural network agent module 103 is used to map multiple parameters from "wireless smart washer pressure" to "sling tension, inclination angle, and cable clamp slippage", and output fast calculation results. The 3D visualization module 104 is used to integrate real-time parameters output by the parameter mapping proxy model, support node data interaction (click to view details), state rendering (color / dynamic effects), and construct a digital twin of the cable clip; Construction control module 105 is used to analyze bolt tightening crosstalk effect, calculate over-tension force and optimize tightening sequence, and output construction adjustment instructions; The operation and maintenance monitoring module 106 is used to analyze real-time pressure data, monitor preload decay and slippage, trigger multi-level early warnings and determine failure modes, and output maintenance suggestions.

[0021] For example, the following describes in detail a specific implementation of a digital twin system for suspension bridge cable clamps based on wireless smart washers according to the present invention. This system is applicable to the construction control and operation and maintenance monitoring of cable clamps for various types of suspension bridges, and is especially applicable to the full life cycle management of the connection nodes between cable clamps and main cables and suspenders in long-span spatial cable-stayed suspension bridges.

[0022] like Figure 1 As shown, the overall architecture of this system includes a data acquisition module 101, a finite element analysis module 102, a neural network proxy module 103, a 3D visualization module 104, a construction control module 105, and an operation and maintenance monitoring module 106. These modules form a closed loop through data interaction. In actual deployment, the installation scheme for the wireless smart washer must first be determined based on the specifications of the cable clamp (such as the number of bolts, diameter, and design preload). Then, a mechanical model of the cable clamp is constructed through finite element analysis. Parameter mapping is then achieved through parameter mapping proxy model training. Finally, digital management and control of construction and operation and maintenance are realized through a 3D visualization platform.

[0023] The wireless smart washer, as a core component of the data acquisition module, has the following assembly relationship with the cable clamp: Figure 2 As shown. The cable clamp body includes an upper cable clamp 3 and a lower cable clamp 5, which cooperate to form an internal space to accommodate the main cable. Engaging teeth 4 are formed at the mating point. After the main cable is loaded, bolts pass through the upper and lower clamp plates of the cable clamp. The wireless smart washer 2 is fitted between the bolt head and the upper cable clamp plate, and secured with a nut 1 on the outside. During installation, the contact surface of the cable clamp must be ground to remove rust and impurities, ensuring a tight fit between the washer 2 and the contact surface. The load detection element of the washer 2 should face the direction of bolt force to improve measurement accuracy. The working principle of the wireless smart washer 2 is based on the elastic deformation law of materials. When the bolt preload acts on the washer, its built-in strain gauge group generates a strain signal proportional to the load, which is converted into a voltage signal by a full-bridge circuit and then transmitted to the edge gateway via a wireless transmission unit. In this case, since the specific structure of the wireless smart washer 2 is not involved in the protection, the existing wireless smart washer structure can be selected in practical applications, so its structural part will not be described further.

[0024] It also includes a wireless transmission unit, integrated inside the wireless smart gasket, for data transmission; and an environmental adaptation unit, encapsulated in waterproof, corrosion-resistant, and high-temperature-resistant materials, enabling the wireless smart gasket to adapt to the harsh outdoor environment of bridges; as shown in the attached document. Figure 2 As shown, a waterproof cap 6 is fitted over the bolt to prevent water from entering the bolt connection and improve the reliability of data acquisition.

[0025] Combination Figure 3 The finite element analysis module is implemented using Abaqus software as the core platform, and parametric modeling and batch simulation are achieved through Python scripts to form a high-precision dataset covering multiple working conditions. The specific process is as follows: First, based on the cable clamp design drawings, a coupled three-dimensional geometric model of the cable clamp-bolt pair (screw, nut, washer)-main cable segment is constructed in Abaqus / CAE. The cable clamp body is modeled as a solid, the bolt contains a complete thread structure, and the main cable is simplified as an equivalent solid of multiple strands of steel wire bundles. The relevant materials are: the cable clamp material is ZG20Mn, the bolt material is 40CrNiMOA, the nut material is 15MnVB, and the smart washer needs to be input as a linear hardening elastoplastic constitutive model.

[0026] After the model is built, the preprocessing process is automated using Python scripts: defining material properties, including the elastic modulus, Poisson's ratio, and yield strength of the cable clamp; the tensile strength and thread parameters of the screw; the wire diameter and lay length of the main cable; and the breaking tensile force of the suspender. Contact relationships are set; the contact area between the main cable and the cable clamp can use a friction contact model, with the friction coefficient set to 0.2-0.3 depending on the surface treatment of the main cable. The screw and the cable clamp's screw hole can be bound together. When meshing, the mesh is refined for the screw thread and the contact area between the cable clamp and the main cable, with element sizes set to 2-5mm, and for other areas, element sizes set to 10-20mm. In the specific analysis, key parts such as bolt threads and washer contact areas use C3D8I linear hexahedral elements, while other areas use C3D10M tetrahedral elements to ensure a balance between simulation accuracy and computational efficiency. To achieve multi-parameter coupled analysis, a Python script further drives Abaqus to automate load application and work condition iteration: by modifying the force vector parameters at the sling's point of action, continuous variable inputs of sling tension (100-2000kN), lateral tilt angle (0-5°), and vertical tilt angle (0-30°) are achieved. The lateral tilt angle is simulated by applying a horizontal component force, while the vertical tilt angle is simulated by adjusting the ratio of the vertical to horizontal components. Simultaneously, a bolt preload force (50-300kN) is applied using Abaqus's "BoltLoad" function to simulate the preload effect during construction. Each set of parameters corresponds to an independent work condition. The script automatically submits calculations and extracts key results: the contact compressive stress distribution of the cable clamp washer, the slippage of the cable clamp along the main cable axis, bolt axial force, etc., and outputs an rpt result file containing node coordinates, stress values, and displacements in a unified format.

[0027] To improve the reliability of simulation data, the finite element model needs to be corrected through physical experiments: Cable clamp tests are conducted by applying known preload and cable load using a hydraulic loading system, simultaneously collecting washer pressure (via built-in strain gauges) and cable clamp displacement (via a laser tracker). The real-time monitoring data is compared with the simulation results, and the friction coefficient and material elastic modulus in the model are corrected using the least squares method, ensuring that the simulation error of key parameters is controlled within 5%. The corrected model is then run again for all operating conditions, ultimately forming a dataset containing 1200 valid samples, divided into training and testing sets in a 7:3 ratio. Each sample set includes input parameters (wasp pressure) and output parameters (cable clamp displacement, cable clamp-main cable friction, etc.), and the relationship between bolt preload and washer pressure is expressed by the linear fitting formula P=k×F (k is the corrected conversion coefficient, with a value of 0.91±0.03). On the other hand, due to the large deformation of the main cable cross section during the tightening process, the tension of the previously tensioned bolts will be reduced when the subsequent bolts are tensioned, which is the crosstalk effect of bolt tightening. The final remaining tension of the bolts after tightening is difficult to estimate.

[0028] To ensure a reliable connection between the cable clamps and the main cable, the magnitude and uniformity of the clamp bolt force need to be controlled within a reasonable range. Excessive force or insufficient force is detrimental to the safety of the cable clamp-to-main cable connection. To avoid this, construction often involves repeated tightening of the clamp bolts, regardless of manpower and time costs, resulting in significant haphazard construction organization. This paper uses a finite element model, considering the lateral stiffness characteristics of the main cable, to simulate the clamp bolt tightening process, analyze crosstalk effects, determine the main cable deformation and remaining bolt tension, compare the degree of crosstalk effects of different bolt tightening sequences, and propose bolt tightening schemes and tension control forces. Based on finite element analysis and experimental verification, a high-quality data foundation is provided for parameter mapping surrogate model training, 3D visualization model development, and subsequent construction control and operation and maintenance monitoring.

[0029] The core of the surrogate model module is to implement parameter mapping through a neural network, and its structure is as follows: Figure 3 As shown. The model takes the pressure value collected by the wireless smart washer model 11 as input and outputs the cable clamp slippage and cable clamp-main cable friction, and uses a deep learning framework to construct the network structure. Before training, the limited metadata needs to be preprocessed, including cleaning and normalizing the limited metadata and real-time monitoring data, removing outliers, and dividing the data into training set (70%), validation set (15%), and test set (15%) to improve the model's generalization ability. The system also includes a model building unit, which constructs an improved BP neural network model based on the PyTorch framework. Input layer 15 contains five parameters: wireless smart washer pressure, cable tension, vertical tilt angle, lateral tilt angle, and cable clamp displacement. There are four hidden layers with 256, 128, 64, and 32 neurons per layer, respectively. The activation function is LeakyReLU, and a Dropout layer (dropout rate = 0.2) is added to prevent overfitting. A training and optimization unit is also included, employing the AdamW optimizer with an initial learning rate of 0.001, adjusted using a cosine annealing strategy. The loss function is root mean square error (RMSE), and training is iteratively performed for 500-1000 epochs until the validation set loss converges. Hidden layer 16 uses a fully connected structure, introducing a non-linear mapping through the activation function and incorporating a regularization mechanism to suppress overfitting. During training, RMSE is used as the loss function, and the network parameters are iteratively updated by the optimizer until the validation set loss converges. The trained model can quickly output results with accuracy comparable to finite element analysis through the neural network surrogate model output layer 17, reducing computation time from hours to milliseconds and meeting the needs of real-time interaction in digital twins. The final output of the cable clamp node stress and strain is used as a rendering file for real-time rendering of the 3D visualization model.

[0030] The implementation of 3D visualization model 14 requires model conversion and scene construction. This includes: a model construction unit, which uses Python to process the mesh node data of the finite element model to generate 3D OBJ format data; a model import and rendering unit, which imports the OBJ format model into the Unity engine, configures PBR materials (with a metallicity of 0.8 and roughness of 0.3 to simulate the metallic texture of the cable clamp), and implements real-time shadow and reflection effects through the URP rendering pipeline; and a data linkage unit, which develops Python scripts to achieve real-time data interaction between the parameter mapping proxy model and the virtual model. When the pressure value of the smart washer changes, the corresponding bolt in the virtual model displays the preload state with a color gradient (green → yellow → red), and the cable clamp displacement is displayed through dynamic ghosting. The script tool parses the finite element result file, extracts node coordinates and parameter information, and converts it into a 3D model in OBJ format, ensuring that each node of the model is associated with its corresponding mechanical parameters. After importing the model into the 3D engine, materials and lighting effects are configured to simulate the metallic texture and lighting changes of the cable clamp. Develop a data interaction interface to enable real-time linkage between the output parameters of the proxy model and the virtual model. For example, use color gradients to display the bolt preload distribution (green indicates normal, red indicates exceeding limits), and use dynamic shadows to display the cable clamp slippage process. Users can interact with the model using the mouse, clicking on any node to view its corresponding pressure value, tension value, inclination angle, and other detailed information, intuitively understanding the status of the cable clamp.

[0031] The implementation process of the bolt tightening strategy in the construction control module is as follows: Figure 4 As shown. It includes a crosstalk effect analysis unit, which calculates the mutual influence coefficients of bolt preload under different tightening sequences based on a finite element model, and establishes a crosstalk matrix. The matrix element Cij represents the influence value of tightening the j-th bolt on the preload of the i-th bolt. In implementation, a crosstalk coefficient matrix is ​​constructed based on the finite element analysis results to quantify the influence of tightening a certain bolt on the preload of other bolts. Based on the target preload and crosstalk coefficient, combined with the over-tension calculation unit, the over-tension of each bolt is calculated using the following formula: Fsuper = Ftarget / (1 - ΣCij), Where Fsuper is the over-tension force, Ftarget is the design preload force, and Cij is the crosstalk coefficient.

[0032] It also includes a tightening sequence optimization unit, which uses an improved genetic algorithm to optimize the tightening sequence, with the objective function being the minimum preload deviation. The population size is set to 50, the crossover probability is 0.8, the mutation probability is 0.05, and the optimal sequence is obtained after 30 generations of iteration. The tightening sequence is optimized through an intelligent algorithm, prioritizing a diagonal alternating tightening method to reduce crosstalk effects. During construction, the system receives real-time pressure data from the wireless smart washers, compares it with the target value, and outputs adjustment instructions to guide construction personnel to gradually control the bolt preload within the allowable deviation range, reducing the number of tightening cycles.

[0033] The early warning and failure mode judgment logic of the operation and maintenance monitoring module is as follows: Figure 5 As shown, it includes: a status assessment unit, which calculates in real time the screw preload decay rate α=(Finitial-Freal-time) / Finitial×100% and the cable clamp slippage s, and judges the structural status in combination with the cable inclination angle change Δθ, where Finitial refers to the preload applied when the screw is installed, and Freal-time refers to the real-time preload of the bolt (the current value monitored by the wireless smart washer); an early warning unit, which sets multi-level early warning thresholds: Level 1 warning (α>10% or s>2mm), Level 2 warning (α>15% or s>5mm), and Level 3 warning (α>20% or s>8mm), and notifies management personnel through audible and visual alarms and remote push when an early warning is triggered; and a failure mode judgment unit, which defines three failure modes: overall cable clamp slippage (≥50% of bolts α>20% and s>10mm), bolt breakage risk (single bolt α sudden drop>30%), and cable eccentric loading (lateral inclination angle difference>3°), and automatically identifies the failure mode and outputs emergency handling plan through a logical judgment model. The system collects pressure data from the wireless smart washers in real time and calculates parameters such as bolt preload decay rate and clamp slippage using a parameter mapping proxy model. When parameters exceed preset thresholds, an early warning is triggered, and the warning information is notified to management personnel via local audible and visual alarms and remote push notifications. Simultaneously, failure modes are identified based on multi-parameter correlation analysis: when the preload of multiple bolts decays synchronously and slippage increases, it is determined to be a risk of overall clamp slippage; when the pressure of a single bolt drops sharply beyond a set proportion, it is determined to be a risk of bolt breakage. For different failure modes, the system automatically matches emergency response plans, such as temporary reinforcement measures and bolt replacement procedures, to support operational and maintenance decisions.

[0034] In practical applications, the system can be flexibly configured according to the specific parameters of the bridge (such as span, number of cable clamps, design load, etc.). For example, during the construction phase, the over-tension calculation parameters can be adjusted to adapt to construction needs under different ambient temperatures; during the operation and maintenance phase, the early warning threshold can be dynamically updated according to the bridge's service life, improving the targeting of monitoring. Through the large-scale deployment of wireless smart washers and the deep application of digital twin technology, precise control of the cable clamps throughout their entire lifecycle from installation to decommissioning is achieved, significantly improving the safety and economy of the bridge structure.

[0035] In addition, the system also includes a data storage and management module, which can optionally use an edge computing gateway for local data caching with a cache capacity of ≥1TB. At the same time, it uploads key data to a cloud database 13 via a 5G network. The cloud database adopts a hybrid architecture of MySQL + MongoDB. MySQL stores structured data (such as sensor IDs, timestamps, and pressure values), while MongoDB stores unstructured data (such as 3D model files and rendering logs), supporting a data query response time of ≤100ms.

[0036] In this implementation, the collaborative work of each module demonstrates the system's core advantages: multi-parameter monitoring and control can be achieved using only a single wireless smart washer sensor, simplifying hardware deployment; the combination of finite element analysis and neural network proxy models balances computational accuracy and real-time performance; and 3D visualization technology makes complex structural states intuitive and perceptible, reducing decision-making difficulty. These features make this system widely applicable in the field of suspension bridge cable clamp monitoring, providing strong support for the intelligent development of bridge engineering.

Claims

1. A digital twin system for cable clamps based on wireless smart washers, characterized in that, include: The data acquisition module is used to collect real-time monitoring data of the physical entity of the cable clamp; The finite element analysis module is used to build finite element models and output multi-parameter mapping relationship data; The proxy model module, based on limited metadata and real-time monitoring data, constructs a parameter mapping proxy model through neural network training. The 3D visualization module, based on the Unreal Engine, constructs a digital twin of the cable clamp, enabling real-time linkage between real-time monitoring data and the finite element model; The construction control module, which combines parameter mapping proxy model and crosstalk effect analysis, is used to optimize bolt over-tension and tightening sequence.

2. The cable clamp digital twin system based on wireless smart washers according to claim 1, characterized in that, It also includes an operation and maintenance monitoring module, which is used to monitor the screw preload decay and cable clamp slippage in real time, and to provide early warning and failure mode judgment.

3. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The data acquisition module includes: One or more wireless smart washers, each based on the principle of material elastic deformation, with built-in load detection elements and micro-displacement sensors for monitoring the axial force state of the bolt.

4. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The finite element analysis module is specifically used to establish a coupled three-dimensional finite element model of the cable clamp, screw, main cable, and suspension cable; including: defining material property parameters; setting boundary conditions; meshing; and simulating the mechanical response under different working conditions.

5. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The proxy model module includes: The data preprocessing unit cleans and normalizes the limited metadata and real-time monitoring data, and removes outliers. The model building unit is based on the PyTorch framework to build an improved BP neural network model. The optimization unit is trained using the AdamW optimizer until the validation set loss converges.

6. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The 3D visualization module includes: The model building unit generates 3D OBJ format data by processing the mesh node data of the finite element model with Python. The model import and rendering unit imports OBJ format models into the Unity engine and configures PBR materials; it also implements real-time shadow and reflection effects through the URP rendering pipeline. The data linkage unit develops Python scripts to enable real-time data interaction between the parameter mapping proxy model and the virtual model.

7. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The construction control module includes: The crosstalk effect analysis unit calculates the mutual influence coefficient of bolt preload under different tightening sequences based on the finite element model, establishes the crosstalk matrix, and the matrix element C ij This represents the effect of tightening the j-th bolt on the preload of the i-th bolt; The over-tension calculation unit, based on the crosstalk matrix and the target preload F0, uses formula F... i =F0 / (1-ΣC ij Calculate the overtension of each bolt, where F i This represents the over-tension of the i-th bolt; The fastening sequence optimization unit uses an improved genetic algorithm to optimize the fastening sequence, with the minimum preload deviation as the objective function, and iteratively obtains the optimal sequence.

8. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, The operation and maintenance monitoring module includes: The condition assessment unit calculates the screw preload attenuation rate α and cable clamp slip s in real time, and judges the structural condition by combining the cable inclination angle change Δθ. The early warning unit is equipped with multi-level early warning thresholds. When an early warning is triggered, it notifies management personnel through audible and visual alarms and remote push notifications. The failure mode determination unit automatically identifies failure modes and outputs emergency response plans through a logical judgment model.

9. A cable clamp digital twin system based on a wireless smart washer according to claim 1 or 2, characterized in that, Also includes: Data storage and management module.

10. A digital twin system for cable clamps based on wireless smart washers, characterized in that, include: The data acquisition module is used to collect real-time monitoring data of the physical entity of the cable clamp, including the wireless smart washer unit; The finite element analysis module is used to build finite element models and output multi-parameter mapping relationship data; The proxy model module, based on limited metadata and real-time monitoring data, constructs a parameter mapping proxy model through neural network training. The 3D visualization module, based on the Unreal Engine, constructs a digital twin of the cable clamp, enabling real-time linkage between real-time monitoring data and the virtual model; The operation and maintenance monitoring module is used to monitor the screw preload decay and cable clamp slippage in real time, enabling early warning and failure mode identification.

Images