A monitoring method and system of a cable-stayed buckling system based on multi-source fusion perception

Abstract

This invention discloses a monitoring method and system for a cable-stayed suspension system based on multi-source fusion sensing. The method includes: deploying multiple sensors at key nodes of the cable-stayed suspension system to acquire multi-source sampling data of the key nodes; aligning the multi-source sampling data of all key nodes in the time dimension through a phase coupling scheduling function to generate an equiphase surface sampling set for each key node; calculating the node transition density of each key node based on the equiphase surface sampling set, and performing scale normalization on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding key node; combining the node states of all key nodes into a network-wide state vector, and mapping the network-wide state vector to the overall offset prediction value of all key nodes through a weight vector, and determining the health status of the cable-stayed suspension system.

Description

Technical Field

[0001] This invention belongs to the field of monitoring technology for cable-stayed suspension systems during bridge assembly and construction, and more specifically, relates to a monitoring method and system for cable-stayed suspension systems based on multi-source fusion sensing. Background Technology

[0002] In the construction of long-span arch bridges, the cable-stayed bridge construction technique is a widely adopted temporary load-bearing system. Its key practice is to form a spatial cable system using temporary cables and anchor towers during the segmented hoisting or cantilever assembly of the arch rib. This provides vertical and horizontal stiffness compensation, thereby controlling the attitude, alignment, and stress of the arch rib segments. Currently, steel strand cables are often used in conjunction with temporary anchor towers, with phased tensioning and unloading to complete the lifting, stabilization, and closure of the arch rib segments. Since construction loads, the self-weight of the arch rib, temperature changes, and wind-induced vibrations can all cause significant fluctuations in the cable force, continuous monitoring of the stress and displacement states of the cables, anchor towers, and anchorage zones is a core requirement for ensuring construction safety.

[0003] Existing monitoring systems typically deploy fiber optic grating sensors, vibrating wire sensors, GNSS displacement monitoring devices, rangefinders, or inclinometers to measure vertical settlement, planar offset, changes in cable tension, and attitude changes at the top of the pylons in the arch rib segments. Different monitoring devices often employ independent sampling systems with inconsistent acquisition frequencies, time bases, installation locations, and data formats. Particularly during the rigging construction phase, due to the incomplete structural geometry, complex temperature gradients, and drastic nonlinear changes in cable tension with each tensioning and arch rib assembly step, the synchronization between multi-source monitoring data is poor. Engineering practices usually rely on manual data alignment or time registration via linear interpolation. However, in non-stationary phases such as wind vibration, hoisting impact, or sudden changes in local stiffness, traditional monitoring methods often fail to capture transient responses, making it difficult to reconstruct the true stress-linear evolution during arch bridge construction.

[0004] Furthermore, current monitoring of cable-stayed bridge systems primarily relies on single-modal analysis, such as adjusting tension based on cable force feedback or correcting deviations in arch rib geometry. A unified multi-physics fusion model has not been established to address the coupling relationships between these data. Since changes in cable force are transmitted to the anchorage area through temporary towers and affect the overall spatial alignment, analyzing only a single physical quantity (such as cable force) is insufficient to describe the comprehensive safety status of the entire cable-stayed system. Moreover, existing data processing largely occurs at the back end, relying on manual methods to determine cable force anomalies, alignment deviations, or tower tilt trends, and lacks online adaptive models for real-time risk prediction. With increasing arch bridge spans, more cable-stayed systems, and faster lifting speeds, traditional monitoring technologies are insufficient to meet the requirements of high-frequency acquisition, synchronous fusion, transient anomaly identification, and alignment trend prediction during the construction of large and complex arch bridge cable-stayed bridges.

[0005] Therefore, there is an urgent need for a technical solution with self-synchronous sensing and self-evolution prediction capabilities. Summary of the Invention

[0006] To address the above technical problems, this invention proposes a monitoring method for a cable-stayed suspension system based on multi-source fusion sensing, comprising:

[0007] At key nodes of the cable-stayed suspension system, multiple sensors are deployed to acquire multi-source sampling data of the key nodes. The multi-source sampling data of all key nodes are aligned in the time dimension through a phase coupling scheduling function to generate an equiphase surface sampling set for each key node.

[0008] The node transition density of each critical node is calculated based on the equiphase surface sampling set, and the scale normalization operation is performed on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding critical node.

[0009] The node states of all key nodes are combined into a global state vector, and the global state vector is mapped to the overall offset prediction value of all key nodes through a weight vector, and the health status of the cable-stayed system is determined.

[0010] Furthermore, by aligning the multi-source sampling data of all key nodes in the time dimension using a phase-coupled scheduling function, an isophase surface sampling set for each key node is generated, including:

[0011] Phase-coupled scheduling function:

[0012]

[0013] in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor;

[0014] Generating the isophase surface sample set for each key node includes:

[0015]

[0016] in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

[0017] Furthermore, the node transition density of each critical node is calculated based on the isophase surface sampling set, including:

[0018]

[0019] in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for .

[0020] Furthermore, the multi-source sampling data includes: cable force values ​​of key nodes, damage depth of key nodes, three-dimensional displacement vectors of key nodes, and temperature of key nodes.

[0021] Furthermore, the node states that are merged with the node transition density to form the corresponding critical nodes include:

[0022]

[0023] in, For time Time The node state of each key node. For the first Normalized cable force values ​​at key nodes The index of the normalized cable force value. For the first Damage depth after normalization of key nodes This is an index of the normalized damage depth. For the first Normalized three-dimensional displacement vectors of key nodes The exponent of the normalized three-dimensional displacement vector. For the first Normalized temperatures at key nodes This is an index of the normalized temperature. This is an adjustment factor for the node transition density.

[0024] Furthermore, mapping the entire network state vector to the overall offset prediction value of all key nodes through the weight vector includes:

[0025]

[0026] in, For time The overall offset prediction value of all key nodes at that time. For time The weight vector at time, It is the transpose symbol. This is the state vector of the entire network.

[0027] Furthermore, determining the health status of the cable-stayed system includes: when the overall offset prediction value exceeds the preset offset threshold, the health status of the cable-stayed system is deemed unqualified, an alarm message is issued, and construction personnel are prompted to perform maintenance operations.

[0028] This invention also proposes a monitoring system for a cable-stayed suspension system based on multi-source fusion sensing, comprising:

[0029] The time alignment module is used to deploy multiple sensors at key nodes of the cable-stayed suspension system to acquire multi-source sampling data of the key nodes. The phase coupling scheduling function aligns the multi-source sampling data of all key nodes in the time dimension to generate an equiphase surface sampling set for each key node.

[0030] The node transition module is used to calculate the node transition density of each key node based on the equiphase surface sampling set, and to perform scale normalization on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding key node.

[0031] The monitoring module is used to combine the node states of all key nodes into a network-wide state vector, and then map the network-wide state vector to the overall offset prediction value of all key nodes through a weight vector, and determine the health status of the cable-stayed system.

[0032] Furthermore, by aligning the multi-source sampling data of all key nodes in the time dimension using a phase-coupled scheduling function, an isophase surface sampling set for each key node is generated, including:

[0033] Phase-coupled scheduling function:

[0034]

[0035] in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor;

[0036] Generating the isophase surface sample set for each key node includes:

[0037]

[0038] in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

[0039] Furthermore, the node transition density of each critical node is calculated based on the isophase surface sampling set, including:

[0040]

[0041] in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for .

[0042] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:

[0043] This invention achieves real-time perception, anomaly detection, and trend prediction of structural states by constructing a multi-source fusion sensing and self-evolutionary modeling closed loop in a cable-stayed system. Through a phase-coupled scheduling function, multiple types of sensor signals can be precisely synchronized in the time domain, improving the consistency of monitoring data. By calculating nodal states, cable force, damage, displacement, and temperature characteristics are projected and fused in non-Euclidean space to form a unified energy state expression. Finally, through a coupled gain self-flow kernel, autonomous prediction and convergence correction of offsets are achieved. Attached Figure Description

[0044] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention;

[0045] Figure 2 This is a system structure diagram of Embodiment 2 of the present invention. Detailed Implementation

[0046] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0047] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0048] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0049] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0050] The display screen is used to show the user interface of each application.

[0051] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0052] Example 1

[0053] like Figure 1 As shown, this embodiment proposes a monitoring method for a cable-stayed suspension system based on multi-source fusion sensing, including:

[0054] Step 101: At the key nodes of the cable-stayed system (such as the cable, anchor cable, cable tower or anchor), deploy a variety of sensors to acquire multi-source sampling data of the key nodes. Align the multi-source sampling data of all key nodes in the time dimension through the phase coupling scheduling function to generate the equiphase surface sampling set of each key node.

[0055] Preferably, the sensors in this embodiment are fiber optic grating sensors (cable force accuracy ±0.5MPa), electromagnetic ultrasonic thickness gauges (damage identification accuracy 0.1mm), BeiDou GNSS displacement monitoring (three-dimensional attitude accuracy ±3mm), and infrared thermal imagers (temperature difference detection ±0.5℃).

[0056] Specifically, the phase-coupled scheduling function aligns the multi-source sampling data of all key nodes in the time dimension to generate an isophase surface sampling set for each key node, including:

[0057] Phase-coupled scheduling function:

[0058]

[0059] in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor;

[0060] Generating the isophase surface sample set for each key node includes:

[0061]

[0062] in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

[0063] Step 102: Calculate the node transition density of each key node based on the equiphase surface sampling set, and perform scale normalization on the equiphase surface sampling set to generate a new equiphase surface sampling set, and merge it with the node transition density to form the node state of the corresponding key node.

[0064] Specifically, the calculation of the node transition density for each critical node based on the isophase surface sampling set includes:

[0065]

[0066] in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for .

[0067] Preferably, this embodiment provides the following method for calculating time. Time The first key node Transition rate of isophase surface sampling data of a type of sensor :

[0068]

[0069]

[0070] in, The length of the sampling window. For time Time The first key node The sign change count of isophase surface sampling data of a certain sensor. This is the index number at the end of the sampling window. For symbolic functions, For the first The first key node The first type of sensor Equivalent surface sampling data, For the first The first key node The first type of sensor Equivalent surface sampling data.

[0071] Specifically, the multi-source sampling data includes: cable force values ​​of key nodes, damage depth of key nodes, three-dimensional displacement vectors of key nodes, and temperature of key nodes.

[0072] Specifically, the node states that are merged with the node transition density to form the corresponding critical nodes include:

[0073]

[0074] in, For time Time The node state of each key node. For the first Normalized cable force values ​​at key nodes The index of the normalized cable force value. For the first Damage depth after normalization of key nodes This is an index of the normalized damage depth. For the first Normalized three-dimensional displacement vectors of key nodes The exponent of the normalized three-dimensional displacement vector. For the first Normalized temperatures at key nodes This is an index of the normalized temperature. This is an adjustment factor for the node transition density. For coefficients with units, such that It is dimensionless because unit ,so The unit is s, generally speaking. ,in, For the first The average transition rate of the isophase surface sampling data of key nodes.

[0075] Preferred, regarding , , , For example, the value can be in the range of 0.5–3, but in general, the system sensitivity is set and adjusted, and this embodiment does not limit it.

[0076] Step 103: Combine the node states of all key nodes into a whole network state vector, and map the whole network state vector to the overall offset prediction value of all key nodes through the weight vector, and determine the health status of the cable-stayed system.

[0077] Preferably, the network-wide state vector is:

[0078]

[0079] in, For time Time The node state of each key node. For time The state vector of the entire network at that time.

[0080] Specifically, mapping the entire network state vector to the overall offset prediction value of all key nodes through the weight vector includes:

[0081]

[0082] in, For time The overall offset prediction value of all key nodes at that time. For time The weight vector at time, It is the transpose symbol. This is the state vector of the entire network.

[0083] Preferably, this embodiment provides the following method for calculating time. Weight vector at time :

[0084] Calculation time The state vector of the entire network at that time time derivative :

[0085]

[0086] in, For time The state vector of the entire network at that time. This represents the change over time.

[0087] Define time Coupling gain self-flowing kernel :

[0088]

[0089] in, This is a component multiplication (Hadamard multiplication).

[0090]

[0091]

[0092] in, For time The change in the weight vector at time, This is a scaling factor over time, used to control the update magnitude (in real-world applications, it is set and adjusted based on system sensitivity; for example, it could be...). ), for.

[0093] Therefore, the time derivative is calculated first. Then calculate the coupling gain self-flow kernel. Then initialize And update, finally calculate .

[0094] Specifically, determining the health status of the cable-stayed system includes: when the overall offset prediction value exceeds the preset offset threshold, the health status of the cable-stayed system is deemed unqualified, an alarm message is issued, and construction personnel are prompted to perform maintenance operations.

[0095] Example 2

[0096] like Figure 2 As shown in the figure, this embodiment proposes a monitoring system for a cable-stayed suspension system based on multi-source fusion sensing. The system specifically includes:

[0097] The time alignment module is used to deploy multiple sensors at key nodes of the cable-stayed suspension system to acquire multi-source sampling data of the key nodes. The phase coupling scheduling function aligns the multi-source sampling data of all key nodes in the time dimension to generate an equiphase surface sampling set for each key node.

[0098] Preferably, the sensors in this embodiment are fiber optic grating sensors (cable force accuracy ±0.5MPa), electromagnetic ultrasonic thickness gauges (damage identification accuracy 0.1mm), BeiDou GNSS displacement monitoring (three-dimensional attitude accuracy ±3mm), and infrared thermal imagers (temperature difference detection ±0.5℃).

[0099] Specifically, the phase-coupled scheduling function aligns the multi-source sampling data of all key nodes in the time dimension to generate an isophase surface sampling set for each key node, including:

[0100] Phase-coupled scheduling function:

[0101]

[0102] in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor;

[0103] Generating the isophase surface sample set for each key node includes:

[0104]

[0105] in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

[0106] The node transition module is used to calculate the node transition density of each key node based on the equiphase surface sampling set, and to perform scale normalization on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding key node.

[0107] Specifically, the calculation of the node transition density for each critical node based on the isophase surface sampling set includes:

[0108]

[0109] in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for .

[0110] Preferably, this embodiment provides the following method for calculating time. Time The first key node Transition rate of isophase surface sampling data of a type of sensor :

[0111]

[0112]

[0113] in, The length of the sampling window. For time Time The first key node The sign change count of isophase surface sampling data of a certain sensor. This is the index number at the end of the sampling window. For symbolic functions, For the first The first key node The first type of sensor Equivalent surface sampling data, For the first The first key node The first type of sensor Equivalent surface sampling data.

[0114] Specifically, the multi-source sampling data includes: cable force values ​​of key nodes, damage depth of key nodes, three-dimensional displacement vectors of key nodes, and temperature of key nodes.

[0115] Specifically, the node states that are merged with the node transition density to form the corresponding critical nodes include:

[0116]

[0117] in, For time Time The node state of each key node. For the first Normalized cable force values ​​at key nodes The index of the normalized cable force value. For the first Damage depth after normalization of key nodes This is an index of the normalized damage depth. For the first Normalized three-dimensional displacement vectors of key nodes The exponent of the normalized three-dimensional displacement vector. For the first Normalized temperatures at key nodes This is an index of the normalized temperature. This is an adjustment factor for the node transition density. For coefficients with units, such that It is dimensionless because unit ,so The unit is s, generally speaking. ,in, For the first The average transition rate of the isophase surface sampling data of key nodes.

[0118] Preferred, regarding , , , For example, the value can be in the range of 0.5–3, but in general, the system sensitivity is set and adjusted, and this embodiment does not limit it.

[0119] The monitoring module is used to combine the node states of all key nodes into a network-wide state vector, and then map the network-wide state vector to the overall offset prediction value of all key nodes through a weight vector, and determine the health status of the cable-stayed system.

[0120] Preferably, the network-wide state vector is:

[0121]

[0122] in, For time Time The node state of each key node. For time The state vector of the entire network at that time.

[0123] Specifically, mapping the entire network state vector to the overall offset prediction value of all key nodes through the weight vector includes:

[0124]

[0125] in, For time The overall offset prediction value of all key nodes at that time. For time The weight vector at time, It is the transpose symbol. This is the state vector of the entire network.

[0126] Preferably, this embodiment provides the following method for calculating time. Weight vector at time :

[0127] Calculation time The state vector of the entire network at that time time derivative :

[0128]

[0129] in, For time The state vector of the entire network at that time. This represents the change over time.

[0130] Define time Coupling gain self-flowing kernel :

[0131]

[0132] in, This is a component multiplication (Hadamard multiplication).

[0133]

[0134]

[0135] in, For time The change in the weight vector at time, This is a scaling factor over time, used to control the update magnitude (in real-world applications, it is set and adjusted based on system sensitivity; for example, it could be...). ), for.

[0136] Therefore, the time derivative is calculated first. Then calculate the coupling gain self-flow kernel. Then initialize And update, finally calculate .

[0137] Specifically, determining the health status of the cable-stayed system includes: when the overall offset prediction value exceeds the preset offset threshold, the health status of the cable-stayed system is deemed unqualified, an alarm message is issued, and construction personnel are prompted to perform maintenance operations.

[0138] Example 3

[0139] This invention also proposes a storage medium storing multiple instructions for implementing the monitoring method of a cable-stayed suspension system based on multi-source fusion sensing.

[0140] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0141] Optionally, in this embodiment, the storage medium is configured to store program code for performing the method steps of Embodiment 1.

[0142] Example 4

[0143] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the monitoring method for a cable-stayed hanging system based on multi-source fusion sensing.

[0144] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0145] The storage medium can be used to store software programs and modules, such as the monitoring method for a cable-stayed suspension system based on multi-source fusion sensing in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned monitoring method for a cable-stayed suspension system based on multi-source fusion sensing. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0146] The processor can execute the method steps of Embodiment 1 by calling the information and application stored in the storage medium through the transmission system.

[0147] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0148] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0151] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0152] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A monitoring method for a cable-stayed suspension system based on multi-source fusion sensing, characterized in that, include: At key nodes of the cable-stayed suspension system, multiple sensors are deployed to acquire multi-source sampling data of the key nodes. The multi-source sampling data of all key nodes are aligned in the time dimension through a phase coupling scheduling function to generate an equiphase surface sampling set for each key node. Phase-coupled scheduling function: ， in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor; The node transition density of each critical node is calculated based on the equiphase surface sampling set, and the scale normalization operation is performed on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding critical node. The node transition density of each critical node is calculated based on the isomorphic surface sampling set, including: ， in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for ; The node states that are merged with the node transition density to form the corresponding critical nodes include: ， in, For time Time The node states of each key node. For the first Normalized cable force values ​​at key nodes The index of the normalized cable force value. For the first Damage depth after normalization of key nodes This is an index of the normalized damage depth. For the first Normalized three-dimensional displacement vectors of key nodes The exponent of the normalized three-dimensional displacement vector. For the first Normalized temperatures at key nodes This is an index of the normalized temperature. This is an adjustment factor for the node transition density; The node states of all key nodes are combined into a global state vector, and the global state vector is mapped to the overall offset prediction value of all key nodes through a weight vector, and the health status of the cable-stayed system is determined.

2. The monitoring method for a cable-stayed suspension system based on multi-source fusion sensing as described in claim 1, characterized in that, By aligning the multi-source sampling data of all key nodes in the time dimension using a phase-coupled scheduling function, an isophase surface sampling set for each key node is generated, including: Generating the isophase surface sample set for each key node includes: ， in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

3. The monitoring method for a cable-stayed suspension system based on multi-source fusion sensing as described in claim 1, characterized in that, The multi-source sampling data includes: cable force values ​​of key nodes, damage depth of key nodes, three-dimensional displacement vectors of key nodes, and temperature of key nodes.

4. The monitoring method for a cable-stayed suspension system based on multi-source fusion sensing as described in claim 1, characterized in that, The entire network state vector is mapped to the overall offset prediction value of all key nodes through the weight vector, including: ， in, For time The overall offset prediction value of all key nodes at that time. For time The weight vector at time, It is the transpose symbol. This is the state vector of the entire network.

5. The monitoring method for a cable-stayed suspension system based on multi-source fusion sensing as described in claim 1, characterized in that, Determining the health status of the cable-stayed system includes: when the overall offset prediction value exceeds the preset offset threshold, the health status of the cable-stayed system is deemed unqualified, an alarm message is issued, and construction personnel are prompted to perform maintenance operations.

6. A monitoring system for a cable-stayed suspension system based on multi-source fusion sensing, characterized in that, include: The time alignment module is used to deploy multiple sensors at key nodes of the cable-stayed suspension system to acquire multi-source sampling data of the key nodes. The phase coupling scheduling function aligns the multi-source sampling data of all key nodes in the time dimension to generate an equiphase surface sampling set for each key node. Phase-coupled scheduling function: ， in, For time Sampling time correction amount For time Reference phase at time, For time Time The sampling phase of each key node, The sampling frequency of the sensor; The node transition module is used to calculate the node transition density of each key node based on the equiphase surface sampling set, and to perform scale normalization on the equiphase surface sampling set to generate a new equiphase surface sampling set, which is then merged with the node transition density to form the node state of the corresponding key node. The node transition density of each critical node is calculated based on the isomorphic surface sampling set, including: ， in, For time Time Node transition density of key nodes For the first The weight of each sensor For time Time The first key node The transition rate of the isophase surface sampling data of the sensor, where, for ; The node states that are merged with the node transition density to form the corresponding critical nodes include: ， in, For time Time The node states of each key node. For the first Normalized cable force values ​​at key nodes The index of the normalized cable force value. For the first Damage depth after normalization of key nodes This is an index of the normalized damage depth. For the first Normalized three-dimensional displacement vectors of key nodes The exponent of the normalized three-dimensional displacement vector. For the first Normalized temperatures at key nodes This is an index of the normalized temperature. This is an adjustment factor for the node transition density; The monitoring module is used to combine the node states of all key nodes into a network-wide state vector, and then map the network-wide state vector to the overall offset prediction value of all key nodes through a weight vector, and determine the health status of the cable-stayed system.

7. The monitoring system for a cable-stayed suspension system based on multi-source fusion sensing as described in claim 6, characterized in that, By aligning the multi-source sampling data of all key nodes in the time dimension using a phase-coupled scheduling function, an isophase surface sampling set for each key node is generated, including: Generating the isophase surface sample set for each key node includes: ， in, For time Time Isophase surface sampling sets of key nodes, For time Time Isophase surface sampling data of key nodes.

Images