A device transportation monitoring and early warning method and system based on digital twinning and risk index

Abstract

The application discloses a kind of equipment transport monitoring early warning methods based on digital twin and risk index, comprising: a variety of sensors are arranged to obtain real-time data;Real-time acquisition and pre-processing are carried out to the sensor data;Digital twin model of the equipment being transported is constructed in cloud;Key monitoring indicators are calculated, and the indicators are compared with preset threshold;According to the comparison result, hierarchical alarm is sent in real time in digital twin visualization interface;At the same time, based on historical data / real-time data and structural dynamics model, comprehensive risk index is calculated and output for comprehensive determination of alarm level.The application realizes the structural change of "visible" by constructing the three-dimensional digital twin model synchronized with the actual equipment, and constructs the extended risk index, which can identify the trend of rapid deterioration before the monitoring data reaches the limit value, and realize predictive warning.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation monitoring for super-large equipment, and in particular to an equipment transportation monitoring and early warning method and system based on digital twin and risk index. Background Art

[0002] With the rapid development of the large-scale equipment manufacturing industry, offshore wind power, heavy steel structure assembly projects and bridge component transportation projects, long-distance translation, transshipment and ro-ro operations of super-large equipment at construction sites are becoming increasingly common. When heavy transportation equipment represented by gantry cranes, portal cranes, SPMT multi-vehicle transport platforms, etc. performs the movement and assembly of large-size components, it is necessary to pay real-time attention to a number of key parameters such as the inclination angle, displacement, deflection, stress, force distribution, synchronization between vehicle groups and the overall transportation trajectory of the equipment. However, the existing engineering monitoring methods still mainly rely on manual experience, local monitoring and separate sensor systems, and cannot achieve comprehensive, continuous and real-time control of the equipment attitude and force state. In addition, traditional monitoring data are mostly presented as single-point values, lacking visual correlation relationships, making it difficult to accurately reflect the global state change of the equipment, and prone to misjudgment or delayed judgment of risk trends.

[0003] During the translation and hoisting process of heavy equipment, affected by factors such as uneven ground, environmental wind load, uneven load, and unsynchronized transport platforms, large structures are extremely prone to situations such as accelerated inclination, overloading of local components, abnormal increase in deflection and attitude instability. If these abnormal changes cannot be identified in time, it may cause structural damage, equipment overturning, component falling or major engineering accidents. Existing monitoring means have obvious deficiencies in accuracy, real-time performance, data fusion capability and early warning mechanism: first, they lack the capability of fusion analysis of multi-dimensional data and cannot reflect the structural state as a whole; second, they do not have the prediction capability for dangerous trends, and only give an alarm after the monitored value exceeds the threshold; third, they lack digital twin visualization means, and cannot realize intuitive presentation and linkage analysis of multi-source data; fourth, they lack a complete early warning linkage mechanism and emergency process. Contents of the Invention

[0004] The purpose of this section is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this section as well as in the abstract and title of the present application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an equipment transportation monitoring and early warning method based on digital twin and risk index, comprising: S1. Deploy multiple sensors at key locations of the monitored oversized equipment and its transport support system to obtain real-time data; S2. Real-time acquisition and preprocessing of the sensor data; S3. Construct a digital twin model of the transported equipment in the cloud, and map the preprocessed real-time data to the attitude parameters of the digital twin model; S4. Calculate the key monitoring indicators and compare the indicators with preset thresholds; S5. Based on the comparison results, issue a graded alarm in real time on the digital twin visualization interface. The graded alarms are green / yellow / orange / red, and record the alarm time, triggering sensor and current value. At the same time, issue emergency response suggestions to the site or command center. S6. Simultaneously, based on historical / real-time data and structural dynamics models, calculate and output a comprehensive risk index. Used to comprehensively determine the alarm level; when When the preset threshold is exceeded, the corresponding level of warning and handling process will be triggered.

[0006] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the data preprocessing includes suppression of stress curve amplification caused by high-frequency resonance, specifically by processing the original stress sampling sequence. Perform moving average noise reduction and downsampling on a minute-by-minute basis. The downsampling calculation method is as follows: ; in, For the original sampling points, The sensor sampling interval is defined as follows: when the sensor samples at 133.33 MHz, ; The number of sampling points within a sliding window; when using minute-by-minute averaging for noise reduction, take... , The effective stress value is obtained after noise suppression and smoothing, and is used for trend analysis and early warning determination.

[0007] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the comprehensive risk index RI can be further used to calculate the sensitivity of the rate of change of each monitored quantity, so as to quickly identify sudden dangerous trends and form an extended risk index. ;when When the preset threshold is exceeded, the corresponding level of warning and handling process will be triggered.

[0008] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the tilt angle, displacement, stress, deflection and image information are displayed side by side as multiple components on the visualization interface, and when any monitoring item enters the yellow / orange / red level, the corresponding component is highlighted and a predefined voice / text / SMS alarm channel is triggered.

[0009] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the sensors are redundantly arranged: at least two sensors of the same type are arranged in each monitoring direction to achieve mutual verification and fault tolerance, and the online / offline status is displayed in real time in the equipment status bar.

[0010] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk index described in this invention, the displacement sensor adopts an integrated wireless pull-wire displacement meter with a resolution of 0.01mm, a 4G network standard, and built-in storage and synchronization functions.

[0011] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the tilt sensor is an intelligent dual-axis tilt meter with an angle resolution of 0.001°, a measurement accuracy of 0.01°, a communication interface supporting RS485 / Modbus, and low power consumption and wide operating temperature capability.

[0012] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twins and risk indices described in this invention, the stress monitoring employs a wireless vibrating wire strain gauge with a standard range of 3000. Resolution 0.1 And the strain is directly converted into stress for display.

[0013] As a preferred embodiment of the equipment transportation monitoring and early warning method based on digital twin and risk index described in this invention, the positioning terminal supports multi-standard positioning, outputs the standard NMEA0183 string, and synchronously displays the real-time trajectory and cumulative displacement with the digital twin.

[0014] Secondly, the present invention also provides an equipment transportation monitoring and early warning system based on digital twins and risk indices, comprising: The multi-source sensor data acquisition module is responsible for real-time acquisition of various state variables generated during the transportation of ultra-large equipment; The data transmission and synchronization module transmits all collected data to the monitoring center synchronously via a wireless network; The data preprocessing and fusion module performs formatting, noise suppression, drift correction, and fusion calculations on multi-source heterogeneous data. The digital twin model driving module maps all effective data to the device's three-dimensional digital twin model in real time, enabling visualization of attitude, force, and displacement. The comprehensive risk index calculation module calculates the comprehensive risk index and the extended risk index based on real-time monitoring data. The tiered early warning and emergency response module automatically triggers different measures based on the early warning level when the comprehensive risk index and the extended risk index exceed the threshold.

[0015] The beneficial effects of this invention are: This invention integrates and collects various monitoring data, such as tilt angle, displacement, deflection, stress, train synchronization, trajectory, and video surveillance, to form a complete multi-source monitoring system. This system can comprehensively reflect the spatial attitude, structural stress, and dynamic changes of ultra-large equipment during translational transportation, which is significantly better than the traditional method that relies on only a few monitoring points.

[0016] This invention constructs a three-dimensional digital twin model synchronized with the actual equipment, which can drive the virtual model to perform posture deformation, color mapping and force display based on real-time monitoring data, realizing "visible" structural changes. This greatly improves the intuitiveness, accuracy and understandability of state judgment, enabling personnel to identify potential dangerous trends at the first time.

[0017] This invention normalizes multiple monitoring parameters and constructs an extended risk index, enabling it to identify rapidly deteriorating trends before monitoring data reaches their limit values, thus achieving predictive early warning. The system can identify dangerous precursors such as accelerated tilting, accelerated offset, and sudden stress changes several seconds to tens of seconds in advance, significantly outperforming traditional passive early warning methods that only trigger alarms when thresholds are exceeded. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart illustrating the sequence of a method for monitoring and early warning of equipment transportation based on digital twins and risk indices proposed in this invention. Figure 2 This is a flowchart illustrating the process architecture of a device transportation monitoring and early warning method based on digital twins and risk indices proposed in this invention. Figure 3 This is a system architecture diagram of an equipment transportation monitoring and early warning system based on digital twins and risk indices proposed in this invention; Figure 4 A diagram of the interface of a digital twin visualization platform; Figure 5 This is a visualization and early warning interface for multi-source monitoring data. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Example 1 Reference Figure 1-5 This invention provides a method for monitoring and early warning of equipment transportation based on digital twins and risk indices, comprising: S1. Various sensors are deployed at key locations of the monitored oversized equipment and its transportation support system to obtain real-time data. The sensors include: dual-axis tilt sensors, horizontal / vertical displacement sensors, laser displacement sensors, wireless vibrating wire strain gauges, multi-standard positioning terminals, and video cameras. The sensors are redundantly arranged: at least two sensors of the same type are deployed in each monitoring direction to achieve mutual verification and fault tolerance, and the online / offline status is displayed in real time in the device status bar; when a single sensor fails, the system can still continue monitoring through the backup sensor to avoid monitoring blind spots; at the same time, multiple sensors mutually verify each other, and by comparing the differences, problems such as drift, excessive noise, and data jaggedness can be identified in a timely manner; the data verification adopts the following method for online consistency review: ,like If a data anomaly occurs in that direction, the system will trigger an alarm and switch the data source; among which... , These are the real-time measurement values ​​from two redundant sensors. The self-calibration deviation threshold for the equipment (e.g., tilt angle deviation of 0.05°, displacement deviation of 5mm, stress deviation of 10MPa). The displacement sensor adopts an integrated wireless draw-wire displacement meter with a resolution of 0.01 mm, 4G network standard, and built-in storage and synchronization functions. The draw-wire displacement meter includes a draw-wire mechanism, a coil spring reset structure, a photoelectric encoding measurement unit, and a wireless communication module. It realizes real-time monitoring of the relative displacement of key nodes of the equipment through the linear extension and retraction of the draw-wire, and packages the measured displacement data in the form of timestamps and uploads it synchronously to the monitoring platform. With a resolution of 0.01 mm, it can identify extremely small offset changes in large equipment during translation, which is of great significance for judging whether the equipment is unbalanced and whether there is uneven stress on the structure. The tilt sensor is an intelligent dual-axis tilt meter with an angle resolution of 0.001°, a measurement accuracy of 0.01°, and a communication interface that supports RS485 / Modbus. It also features low power consumption and wide operating temperature range. The tilt meter adopts a three-dimensional installation calibration method, which achieves initial zero point, installation error compensation, and axial non-orthogonal correction through three-sided calibration, thereby improving the tilt measurement accuracy. Stress monitoring utilizes a wireless vibrating wire strain gauge with a standard range of 3000. Resolution 0.1 The strain is directly converted into stress (MPa); the strain value of the component is calculated by measuring the change of the natural frequency of the vibrating wire and the stress value (MPa) is obtained by using the elastic modulus of the material. The stress data is uploaded to the monitoring platform in real time. It is suitable for continuous monitoring of large steel structures and long-cycle transportation, and is not affected by electromagnetic noise. It is more stable under heavy load and long-distance transportation conditions. Its features include: the positioning terminal supports multi-standard positioning (GPS / BeiDou / GLONASS / Galileo), outputs standard NMEA0183 strings, and synchronously displays real-time trajectory and cumulative displacement with the digital twin; S2. Real-time acquisition and preprocessing of sensor data, including noise reduction, filtering and time synchronization; Data preprocessing includes suppressing the amplification of stress curves caused by high-frequency resonance, specifically by processing the original stress sampling sequence. Perform moving average noise reduction and downsampling on a minute-by-minute basis. The downsampling calculation method is as follows: ; in, For the original sampling points, The sensor sampling interval is defined as follows: when the sensor samples at 133.33 MHz, ; The number of sampling points within a sliding window; when using minute-by-minute averaging for noise reduction, take... , The effective stress value after noise suppression and smoothing is used for trend analysis and early warning judgment. During the transportation of gantry cranes and large steel structures, slender components will exhibit transient high-frequency vibrations under disturbances such as acceleration and deceleration during transportation and micro-vibrations of the road surface. The original stress data will show high-frequency components such as "peaks" and "burrs", causing the real-time curve to fluctuate violently. Moving average can "submerge" these high-frequency anomalies within the window, making the output closer to the true static / quasi-static stress. Downsampling can significantly reduce false alarms caused by occasional noise, and is particularly suitable for bridge noise suppression of vibrating wire wireless strain gauges. S3. Construct a digital twin model of the transported equipment in the cloud, and map the preprocessed real-time data to the attitude parameters of the digital twin model. The digital twin displays the overall transportation panorama and various monitoring quantities in a 16:9 view on a visualization interface; in this embodiment, such as Figure 4 As shown, the digital twin visualization monitoring platform includes a central digital model display area and a multi-functional monitoring component area. The central area displays a 3D digital twin model of the transported oversized equipment and its transport support system. The model is driven by real-time data acquisition, and its attitude changes, displacement changes, and stress states are synchronized with the actual equipment. The monitoring component area includes stress monitoring modules, displacement monitoring modules, tilt angle monitoring modules, deflection monitoring modules, and video monitoring modules. Each module displays its corresponding monitoring data in real-time in a graphical format and updates in conjunction with the digital twin model. The visualization interface supports multi-dimensional interactive operations, including model rotation, scaling, historical data playback, and progress synchronization control. This allows monitoring personnel to analyze equipment attitude change trends from different perspectives and perform risk tracing analysis based on historical data, thereby improving early warning accuracy and decision-making efficiency. S4. Calculate key monitoring indicators, including deflection angle. East-west relative horizontal displacement Relative horizontal displacement in the north-south direction Vertical displacement Mid-span deflection of bottom beam With several stress values The index is then compared with a preset threshold, which includes the tilt angle. The safety limit is 1°, the warning value is 1.5°, the high-risk value is 2°, and the limit value is 2.5°; the safety / warning / high-risk / limit values ​​for east-west horizontal displacement are 30 / 40 / 50 / 60 mm respectively; the safety / warning / high-risk / limit values ​​for north-south horizontal displacement are 50 / 60 / 70 / 80 mm respectively; the safety / warning / high-risk / limit values ​​for vertical displacement are 20 / 30 / 40 / 50 mm respectively; the safety / warning / high-risk / limit values ​​for bottom beam deflection are 80 / 85 / 90 / 100 mm respectively; and the safety / warning / high-risk / limit values ​​for stress are 270 / 310 / 320 / 330 MPa respectively. S5. Based on the comparison results, issue graded alarms in real time on the digital twin visualization interface. The graded alarms are green / yellow / orange / red, and record the alarm time, triggering sensor and current value. At the same time, issue emergency response suggestions to the site or command center. Tilt angle, displacement, stress, deflection, and image information are displayed side-by-side as multiple components on the visualization interface. When any monitored item enters the yellow / orange / red level, the corresponding component is highlighted and a predefined voice / text / SMS alarm channel is triggered. In large equipment, multiple physical quantities are significantly coupled: abnormal tilt angle can easily cause horizontal displacement, and increased displacement may indicate a sharp deterioration in stress or deflection. Camera footage can verify whether actual displacement or obstacle interference has occurred. Therefore, side-by-side display can reduce the difficulty of judgment for operators and achieve multi-dimensional linkage monitoring. At the same time, the multi-channel alarm mechanism allows voice broadcasts to prompt on-site personnel to react quickly, text pop-ups can be used for real-time recording in the command center, and SMS alarms can promptly notify key personnel for handling. The multi-channel alarm mechanism can reduce alarm failures caused by network or equipment failures. S6. Simultaneously, based on historical / real-time data and structural dynamics models, calculate and output a comprehensive risk index. Used to comprehensively determine the alarm level, among which The calculation formula is as follows: ; in, For each monitoring quantity (such as , ; , , ), For the limit value of the corresponding term, For normalized weights and ;when When the preset threshold is exceeded, the corresponding level of warning and handling process is triggered (the above thresholds and weights can be adjusted by users / engineers based on structural strength, initial residual stress, and safety redundancy). After the warning is triggered, the interface highlights and dynamically displays colors. When entering the yellow, orange, or red zone, the corresponding monitoring components (tilt angle, displacement, deflection, stress, etc.) immediately display a highlighted border and flashing effect. The corresponding component area in the digital twin model changes color synchronously. If it is in the red zone, the interface automatically pops up a window prompting "Stop work immediately" or "Check equipment immediately". At the same time, the system transmits alarms to the site and command center through various means, including voice reminders, APP push, large screen flashing, sound siren, and mandatory messages to key personnel. When a yellow or higher warning is triggered, the system automatically records the raw data of all sensors within ±5-10 minutes before and after the trigger and generates an event package (including time, displacement, tilt angle, stress, deflection, speed, images, etc.), and seals the key data to prevent overwriting, facilitating subsequent traceability and analysis. The comprehensive risk index RI can be further used to calculate the sensitivity of the rate of change of each monitored quantity, so as to quickly identify sudden dangerous trends and form an extended risk index. The calculation method is as follows: ; in, This represents the normalized rate of change of the monitored quantity relative to its limit value, used to characterize how fast or slow its upward or downward trend is. This is an adjustment factor for the rate of change term, used to define the degree of influence of the rate of change on the final risk index. As independent weighting factors for the rate of change term, and They are independent of each other and can be adjusted according to the importance of the project; traditional judgments based on thresholds or static amplitudes (such as those based solely on...) , , The system struggles to identify the following two types of critical hazards (whether the measured value is close to the threshold): 1) The monitored quantity is not exceeding the limit, but the rate of increase is extremely rapid, such as the tilt angle rapidly increasing from 0.5° to 1° within seconds, or the bottom beam deflection suddenly worsening from 40mm to 70mm. This scenario frequently occurs during vehicle acceleration / deceleration, uneven road surfaces, or sudden wind loads. Adding a time derivative term can identify this trend in advance, giving the early warning system "predictive" capabilities. 2) The monitored quantity has a small amplitude but exhibits abnormal abrupt changes, such as instantaneous impacts, eccentric load jumps, or small, rapid oscillations before steel component instability. The time derivative term ensures the system can issue timely warnings even when the absolute value is small but the change is rapid. Adding a rate of change term can detect risk trends several seconds to tens of seconds in advance, giving the command center more reaction time. The basic risk index... This describes whether the current state is dangerous, and includes an expanded risk index. The description concerns "whether the future might be dangerous"; when When the preset threshold is exceeded, the corresponding level of warning and handling process will be triggered.

[0022] This embodiment also provides an equipment transportation monitoring and early warning system based on digital twins and risk indices, including: The multi-source sensor data acquisition module is responsible for real-time acquisition of various state variables generated during the transportation of ultra-large equipment; The data transmission and synchronization module transmits all collected data to the monitoring center synchronously via a wireless network; The data preprocessing and fusion module performs formatting, noise suppression, drift correction, and fusion calculations on multi-source heterogeneous data. The digital twin model driving module maps all effective data to the device's three-dimensional digital twin model in real time, enabling visualization of attitude, force, and displacement. The comprehensive risk index calculation module calculates the comprehensive risk index and the extended risk index based on real-time monitoring data. The tiered early warning and emergency response module automatically triggers different measures based on the early warning level when the comprehensive risk index and the extended risk index exceed the threshold.

[0023] In summary, this invention, by constructing a three-dimensional digital twin model synchronized with the actual equipment, enables real-time monitoring data to drive the virtual model to perform posture deformation, color mapping, and force display, achieving "visible" structural changes. This greatly improves the intuitiveness, accuracy, and understandability of state judgment, allowing personnel to identify potential dangerous trends at the first moment. At the same time, by normalizing multiple monitoring quantities and constructing an extended risk index, it can identify rapidly deteriorating trends before the monitoring data reaches its limit value, achieving predictive early warning.

[0024] Example 2 This embodiment uses SPMT to perform overall horizontal transport of a large gantry crane.

[0025] The specific engineering parameters include: gantry crane span: 120m; weight: 1200t; transportation method: SPMT multi-vehicle synchronous transportation.

[0026] Step 1: Sensor Deployment: Inclinometers: Deployed at both ends of the main beam and the top of the tower to acquire real-time lateral and longitudinal tilt angles for determining overall equipment stability and identifying any off-center loading; Displacement Gauges: Deployed between the main beam and the SPMT (Special Purpose Vehicle) unit to determine if there is asynchronous movement or offset; Strain Gauges: Deployed at the mid-span of the main beam and support connection nodes to calculate real-time stress and deflection trends, identifying structural stress anomalies or local overloads; GNSS (GNSS Modules): Deployed on both sides of the gantry crane and the SPMT unit for real-time trajectory tracking, unit synchronization analysis, and translation path deviation detection; Cameras: Deployed along the transport path for visual assistance in judgment and confirmation of abnormal conditions.

[0027] Step 2: Digital Twin Modeling: Establish a 3D model of the gantry crane; use tilt angle to synchronize attitude changes, use displacement to drive node translation in real time, and use color to map stress changes; achieve real-time visualization of the structural state.

[0028] Step 3: Risk Index Calculation: Real-time Calculation and Used to identify abnormal trends; Step Four: According to and The calculation results will be subject to the following control strategy: Yellow Alert (Minor Abnormality): Instructs operators to pay attention, check SPMT synchronization status, and reduce operating speed; Orange Alert (Significant Abnormality): Force deceleration, suspend transportation, and check tower stress and ground conditions; Red Alert (Dangerous State): Immediately stop SPMT operation, activate the emergency braking system, lock equipment attitude, and notify the on-site supervisor for emergency handling.

[0029] This embodiment can identify tilt, offset and stress anomalies in advance, and achieve safety control throughout the entire process.

[0030] This invention achieves intelligent monitoring and safety early warning of the translation and transportation process of ultra-large equipment through multi-source monitoring, digital twin modeling, and risk index analysis, and has significant engineering application value.

[0031] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for monitoring and early warning of equipment transportation based on digital twins and risk indices, characterized in that: include: S1. Deploy multiple sensors at key locations of the monitored oversized equipment and its transport support system to obtain real-time data; S2. Real-time acquisition and preprocessing of the sensor data; S3. Construct a digital twin model of the transported equipment in the cloud, and map the preprocessed real-time data to the attitude parameters of the digital twin model; S4. Calculate key monitoring indicators; and compare the indicators with preset thresholds; S5. Based on the comparison results, issue a graded alarm in real time on the digital twin visualization interface. The graded alarms are green / yellow / orange / red, and record the alarm time, triggering sensor and current value. At the same time, issue emergency response suggestions to the site or command center. S6. Simultaneously, based on historical / real-time data and structural dynamics models, calculate and output a comprehensive risk index. Used to comprehensively determine the alarm level; when When the preset threshold is exceeded, the corresponding level of warning and handling process will be triggered.

2. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 1, characterized in that: The data preprocessing includes suppressing the amplification of the stress curve caused by high-frequency resonance, specifically by processing the original stress sampling sequence. Perform moving average noise reduction and downsampling on a minute-by-minute basis. The downsampling calculation method is as follows: ； in, For the original sampling points, The sensor sampling interval is defined as follows: when the sensor samples at 133.33 MHz, ; The number of sampling points within a sliding window; when using minute-by-minute averaging for noise reduction, take... , The effective stress value is obtained after noise suppression and smoothing, and is used for trend analysis and early warning determination.

3. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 2, characterized in that: The comprehensive risk index RI can be further used to calculate the sensitivity of the rate of change of each monitored quantity, so as to quickly identify sudden dangerous trends and form an extended risk index. ;when When the preset threshold is exceeded, the corresponding level of warning and handling process will be triggered.

4. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 3, characterized in that: The tilt angle, displacement, stress, deflection, and image information are displayed side by side as multiple components on the visualization interface. When any monitoring item enters the yellow / orange / red level, the corresponding component is highlighted and a predefined voice / text / SMS alarm channel is triggered.

5. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 1, characterized in that: The sensors are redundantly arranged: at least two sensors of the same type are arranged in each monitoring direction to achieve mutual verification and fault tolerance, and the online / offline status is displayed in real time in the device status bar.

6. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 5, characterized in that: The displacement sensor is an integrated wireless drawstring displacement meter with a resolution of 0.01mm, a 4G network standard, and built-in storage and synchronization functions.

7. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 6, characterized in that: The tilt sensor is an intelligent dual-axis tilt meter with an angle resolution of 0.001°, a measurement accuracy of 0.01°, a communication interface supporting RS485 / Modbus, and low power consumption and wide operating temperature range.

8. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 7, characterized in that: The stress monitoring employs a wireless vibrating wire strain gauge with a standard range of 3000. Resolution 0.1 And the strain is directly converted into stress for display.

9. The equipment transportation monitoring and early warning method based on digital twins and risk indices according to claim 8, characterized in that: The positioning terminal supports multi-standard positioning, outputs the standard NMEA0183 string, and synchronously displays the real-time trajectory and cumulative displacement with the digital twin.

10. A monitoring and early warning system for equipment transportation based on digital twins and risk indices, based on the monitoring and early warning method for equipment transportation based on digital twins and risk indices as described in any one of claims 1-9, characterized in that: include: The multi-source sensor data acquisition module is responsible for real-time acquisition of various state variables generated during the transportation of ultra-large equipment; The data transmission and synchronization module transmits all collected data to the monitoring center synchronously via a wireless network; The data preprocessing and fusion module performs formatting, noise suppression, drift correction, and fusion calculations on multi-source heterogeneous data. The digital twin model driving module maps all effective data to the device's three-dimensional digital twin model in real time, enabling visualization of attitude, force, and displacement. The comprehensive risk index calculation module calculates the comprehensive risk index and the extended risk index based on real-time monitoring data. The tiered early warning and emergency response module automatically triggers different measures based on the early warning level when the comprehensive risk index and the extended risk index exceed the threshold.

Images