A digital twin digital intelligence construction method and system for a track laying machine

Abstract

The present invention relates to the technical field of bridge construction and construction monitoring, and provides a digital twin digital intelligence construction method and system for a track laying machine. Under the construction working condition of the rear superposition of PK-section steel beams and prefabricated concrete bridge panels, the construction monitoring sensor information of each track laying machine is obtained during the main bridge construction process, and OPC data is integrated to form the logic, physical information and construction environment data information of the track laying machine. Through PLC programming data processing, modular associated simulation drive is used to simulate the three-dimensional simulation of the main beam construction and associate the construction monitoring data information, complete the matching of the working posture of each simulation model with the physical information state and the dynamic construction simulation of the construction environment, realize the digital twin digital intelligence construction of actual physical data, promote the digital intelligence development of bridge construction, and solve the problem of immature intelligent safety monitoring technology of construction equipment and steel beam structure under the asynchronous construction conditions of the rear superposition of PK-section steel beams and prefabricated bridge panels in the existing technology.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge construction monitoring technology, and in particular to a digital twin digital intelligence construction method and system for an integrated bridge laying machine. Background Art

[0002] As the construction of modern cross-river and cross-sea bridges continues to expand, large-span cable-stayed bridges increasingly utilize steel-concrete composite beams with excellent span capacity, constructed using a cantilevered hoisting method using a bridge crane. The deadweight of the steel-concrete composite beam directly determines the crane's lifting capacity, impacting the steel reinforcement required for key beam sections and the length of the main bridge segments, restricting the overall progress of main beam construction. Reducing the deadweight of the bridge crane and main beam segments allows for the use of a post-lapping construction method involving steel beams and precast concrete bridge decks. By hoisting the main beam and deck in stages, the deadweight requirements for both machinery and the main beam structure can be reduced, thereby strengthening overall control over material investment and construction schedules.

[0003] Conventional bridge cranes, slewing cranes, and other equipment can be used to construct the post-assembly of beams and slabs for main bridges of cross-river and cross-sea cable-stayed bridges. Based on their inherent design capabilities or with the assistance of truck cranes, these cranes can complete the installation of N sections of bridge decks after hoisting N beams. However, these cranes are heavy, resulting in low overall efficiency and a long construction cycle. As large-scale lifting equipment, bridge cranes bear the immense loads of hoisting beams. Collecting and analyzing the stress state of the crane structure is a crucial measure to ensure its safe operation. Structural monitoring of conventional bridge crane processes is widely implemented, but existing technology lacks a comprehensive construction and monitoring process for the asynchronous construction of beam hoisting and bridge deck installation, which occurs in different sections.

[0004] In existing technologies, the post-assembly and cantilevered construction of the main bridge of a cross-river and cross-sea cable-stayed bridge often uses channel steel box girders as the main beam structure. The control of post-assembly construction technology for PK-type steel beams is poor both domestically and internationally, and the maturity of construction monitoring and early warning systems and simulation and early warning systems is low. Furthermore, existing construction monitoring technologies require manual extraction and judgment of key basic information data, and model analysis requires manual updating of real-world modeling. This carries significant system operation and maintenance costs and time investment, hindering the rapid development of intelligent digital bridge construction. Furthermore, existing construction monitoring technologies cannot reliably implement monitoring and early warning systems and simulation and early warning systems. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide a digital twin digital intelligent construction method and system for a track laying machine that overcomes the above problems.

[0006] One aspect of the present invention provides a digital twin construction method for a track-laying machine. The method is used for a construction operation in which a PK-section steel beam is superimposed on a precast concrete bridge deck. The PK-section steel beam hoisting construction and the precast concrete bridge deck paving construction are performed simultaneously, and the construction areas are located in different sections. The method includes:

[0007] Pre-build construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model;

[0008] Under the construction conditions of post-lapping of PK-section steel beams and precast concrete decks, IoT devices installed at key points on each bridge-laying machine acquire construction monitoring sensor information from each machine during the main bridge construction process. This information includes beam segment position information, stress monitoring information, internal force information of the steel beam structure, construction site environment information, equipment tilt information, equipment posture information, and equipment positioning information.

[0009] Transmitting the construction monitoring sensor information to the OPC server for OPC data integration to form the track laying machine logic, physical information and construction environment data information, and transmitting the OPC data integration to the PLC programmable logic controller;

[0010] The information extraction and processing of OPC data integration is completed through the PLC programmable logic controller, and the obtained logical, physical information and construction environment data information are fed back to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, completing the matching of the working posture of each simulation model with the physical information status and the dynamic construction simulation of the construction environment, realizing the digital twin digital intelligent construction of actual physical data.

[0011] Furthermore, the method further comprises:

[0012] The construction monitoring sensor information under the current stage of construction operation conditions is processed and analyzed to form a construction simulation of the construction operation of the PK-section steel beam and the concrete precast bridge deck. Combined with the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction operation conditions, the deduction and prediction of the safety warning of the next stage of construction operation are carried out.

[0013] Furthermore, in the process of executing the deduction and prediction of the safety warning of construction work in the next stage, the comparison threshold range of different alarm levels of various safety warnings is adjusted according to the deviation inertia ratio of the data to eliminate the monitoring error caused by the cumulative loss of components.

[0014] Furthermore, the deduction and prediction of the execution of the safety warning of the construction work in the next stage includes:

[0015] The deep learning model of a neural network uses the current physical state of the bridge deck slab and the bridge deck slab to be installed as the analysis object. Based on the lifting position of each bridge deck slab and the positioning and cylinder stroke data of the bridge deck slab, it is determined whether the equipment's positioning and cylinder stroke meet the beam-slab connection requirements during the installation process when lifting the next bridge deck slab at the current position and state.

[0016] According to the current posture of the track laying machine and the form of the beam and slab to be installed in the next step, the inclination and deformation state of the track laying machine will be predicted according to the stress and structural strain calculation, so as to predict the stability of the equipment operation.

[0017] Furthermore, the method further comprises:

[0018] Obtain monitoring image information of the main bridge construction;

[0019] Remotely transmit construction monitoring image information to the PLC programmable logic controller through the server streaming application;

[0020] Through the preset intelligent hazard identification algorithm, construction monitoring image information is used to actively identify high-altitude falls, fires, and unsafe behaviors of workers.

[0021] Furthermore, the information extraction of OPC data integration is completed by the PLC programmable logic controller, including:

[0022] Clean and filter the construction monitoring sensor information in OPC data integration, remove excessive deviations and non-standard data to eliminate data differences;

[0023] Through the sensor data interaction strategy, multi-source data are synchronously integrated to realize data classification labeling and ensure the consistency of data standards. Through the Kalman filter algorithm, each type of data is smoothed separately to obtain the optimal estimated value of the corresponding data and extract it.

[0024] Furthermore, the information processing to complete OPC data integration through the PLC programmable logic controller includes:

[0025] The actual operating status of the track laying machine is analyzed based on the beam section position information, equipment inclination information, equipment posture information and equipment positioning information. By comparing and analyzing the actual operating status of the track laying machine with the preset design operating status, safe management and real-time early warning of the equipment operating status are achieved.

[0026] Furthermore, the obtained logical, physical information and construction environment data information are fed back to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, completing the matching of the working posture of each simulation model with the physical information state and the dynamic construction simulation of the construction environment, including:

[0027] Create model attribute parameters that match the data collected on the construction site for the construction structure model, GIS real-scene site model, construction equipment simulation model, and construction dynamic information model. By integrating the data and model attribute parameters, the digital twin application of actual physical data is realized.

[0028] Linking the construction dynamic information model with production management data, and linking construction progress information, prefabricated beam and slab process acceptance data, and bridge structure block installation team information with the model to achieve a multi-dimensional digital twin of the construction dynamic information model;

[0029] The actual working scene of bridge construction is created by updating satellite 3D map image data and construction environment data information, and the GIS real-scene site model is automatically driven and adjusted as the satellite image changes.

[0030] Another aspect of the present invention provides a digital twin digital intelligent construction system for a track laying machine. The system is used for a construction operation in which a PK-section steel beam is superimposed on a precast concrete bridge deck. The PK-section steel beam hoisting construction and the precast concrete bridge deck paving construction are carried out simultaneously, and the construction areas are located in different sections. The system includes a functional module for implementing the digital twin digital intelligent construction method for a track laying machine as described in any of the above items, specifically including:

[0031] Simulation model building module, used to pre-build construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model;

[0032] The structural monitoring module is used to obtain construction monitoring sensor information from each track-laying machine during the main bridge construction process through IoT devices installed at key points of each track-laying machine under the construction conditions of the PK-section steel beam and the precast concrete bridge deck. The construction monitoring sensor information includes beam segment position information, stress monitoring information, steel beam structure internal force information, construction site environment information, equipment inclination information, equipment posture information, and equipment positioning information;

[0033] A data transmission module is used to transmit the construction monitoring sensor information to the OPC server for OPC data integration, to form the track laying machine logic, physical information and construction environment data information, and to transmit the OPC data integration to the PLC programmable logic controller;

[0034] The construction linkage digital twin module is used to complete the information extraction and processing of OPC data integration through the PLC programmable logic controller, and feed back the obtained logical, physical information and construction environment data information to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, to complete the matching of the working posture of each simulation model with the physical information status and the dynamic construction simulation of the construction environment, and realize the digital twin digital intelligent construction of actual physical data.

[0035] Furthermore, the system further comprises:

[0036] The construction simulation analysis module is used to process and analyze the construction monitoring sensor information under the current construction working conditions to form a construction simulation of the construction operation of the PK-type cross-section steel beam and the concrete prefabricated bridge deck. Combined with the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction working conditions, it performs the deduction and prediction of the safety warning of the next stage of construction work.

[0037] The embodiment of the present invention provides a digital twin digital intelligent construction method and system for a track laying machine. Under the construction working condition of the rear overlap of PK-section steel beams and precast concrete bridge decks, the construction monitoring sensor information of each track laying machine is obtained during the construction of the main bridge, and OPC data is integrated to form the logic, physical information and construction environment data information of the track laying machine. Through PLC programming data processing, modular associated simulation drive is used to simulate the three-dimensional simulation of the main beam construction and associate the construction monitoring data information, complete the matching of the working posture of each simulation model with the physical information state and the dynamic construction simulation of the construction environment, realize the digital twin digital intelligent construction of actual physical data, and promote the digital and intelligent development of bridge construction.

[0038] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Various other advantages and benefits will become apparent to those skilled in the art by reading the detailed description of the preferred embodiment below. The accompanying drawings are only for the purpose of illustrating the preferred embodiment and are not to be considered as limiting the present invention. In the accompanying drawings:

[0040] Figure 1 This is a structural diagram of a bridge site working condition system in a digital twin digital intelligent construction method for a track laying machine according to an embodiment of the present invention;

[0041] Figure 2 This is a flow chart of a digital twin digital intelligence construction method for a track laying machine according to an embodiment of the present invention;

[0042] Figure 3 This is a flow chart of a digital twin digital intelligence construction method for a track laying machine according to another embodiment of the present invention;

[0043] Figure 4 Schematic diagram of the electronic information transmission structure of the digital twin digital intelligent construction system of the integrated track laying machine in an embodiment of the present invention;

[0044] Figure 5 This is a structural schematic diagram of a digital twin digital intelligent construction system for a track laying machine in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art in the art to which this invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless specifically defined, should not be interpreted in an idealized or overly formal sense.

[0047] The embodiment of the present invention provides a digital twin digital intelligent construction method for a track-laying integrated machine, which is used for the construction operation condition of the PK-section steel beam and the concrete precast bridge deck being superimposed. The PK-section steel beam hoisting construction and the concrete precast bridge deck paving construction are carried out simultaneously and the construction areas are located in different segment areas, such as Figure 1 As shown, the bridge site working condition system in this embodiment covers key technical process control components such as the laying machine, N-segment steel beam hoisting, N-2 segment prefabricated bridge deck paving, and predicted hoisting of N-segment steel beams. Figure 2 As shown, the digital twin digital intelligence construction method of the track laying machine proposed in the present invention includes the following steps:

[0048] S11. Pre-build the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model.

[0049] The simulation model in this embodiment includes a construction structure model, a GIS real-scene site model, a construction equipment simulation model, and a construction dynamic information model. The construction structure model, based on various modeling software, creates a BIM model of the bridge's complex curved main tower structure, various forms of PK steel beams, various forms of precast bridge deck panels, bridge deck wet joint structures and reinforcement, and bridge protective structures during the construction process. A conversion and recognition module for multiple model formats is created to integrate the overall building model. The GIS real-scene site model uses drone oblique photography technology to generate an on-site surrounding site environment model. For drone oblique photography modeling of wide-area water flow surfaces, accurate and efficient modeling of wide-area water flow surfaces is achieved through front-end data processing for image format, exposure rate, and noise reduction balance, as well as back-end data processing parameter modules for regional multi-point adjustment and multi-point image matching based on the width of the water area. Furthermore, satellite 3D map image data updates and open-source reservoir water level monitoring data are integrated to automatically identify and obtain the bridge's environment, water level, water velocity, flow rate, and 10-nautical-mile main beam transportation positioning information, forming a dynamic simulation of the surrounding environment model during the bridge construction process. The construction equipment simulation model includes the structure of the new bridge deck girder and slab laying machine, as well as the complete equipment structure model of the track, winch, jack, and pump station. Dynamically measured physical property parameters are assigned to the structural model to simulate the machine's operating status through data-model interaction. The dynamic construction information model associates construction progress attributes and construction quantity attributes with the building structure model, overlaying production data and process quality control information on prefabricated components to achieve multi-dimensional information integration within the BIM model.

[0050] S12. Under the construction working condition of the PK-section steel beam and the precast concrete bridge deck being overlapped, the construction monitoring sensor information of each track laying machine during the main bridge construction process is obtained through the Internet of Things devices installed at the key points of each track laying machine. The construction monitoring sensor information includes the beam section position information, stress monitoring information, steel beam structure internal force information, construction site environment information, equipment tilt information, equipment posture information and equipment positioning information.

[0051] Specifically, after receiving the confirmation information from the digital twin intelligent safety monitoring system of the track laying machine fed back by the track laying machine, the construction monitoring sensor information of each track laying machine in the main bridge construction is obtained.

[0052] S13, transmitting the construction monitoring sensor information to the OPC server for OPC data integration, forming the track laying machine logic, physical information and construction environment data information, and transmitting the OPC data integration to the PLC programmable logic controller.

[0053] Specifically, the IoT devices collect actual data on site, use the OPC server for data integration, and package the data into a standard communication data language to form the logic, physical information and construction environment data information of the track laying machine. Through the data processing function of the PLC programmable logic, while filtering and noise reduction are performed on the packaged data transmitted by the OPC server to improve data quality, the collected data is calculated and analyzed through the logic operation module, the results are output, and the output physical information is fed back to the bridge construction simulation.

[0054] S14. Complete the information extraction and processing of OPC data integration through the PLC programmable logic controller, and feed back the obtained logical, physical information and construction environment data information to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, complete the matching of the working posture of each simulation model with the physical information status and the dynamic construction simulation of the construction environment, and realize the digital twin digital intelligent construction of actual physical data.

[0055] In this embodiment, data collection by IoT devices is used to obtain beam section position information, stress monitoring information, internal force information of steel beam structure, construction site environment information, equipment tilt information, equipment posture information, and equipment positioning information. The logic and physical information of the track laying machine are integrated with OPC data, and the information extraction, processing, and output of the data integration are automatically completed through PLC programming data processing, thereby realizing the monitoring of the track laying machine structure and beam and slab status during the construction process.

[0056] In this embodiment, step S14 completes the information extraction of OPC data integration through the PLC programmable logic controller, including: cleaning and filtering the construction monitoring sensor information in the OPC data integration, removing deviation exceeding the limit and non-standard data to eliminate data differences; synchronously integrating multi-source data through sensor data interaction strategy to realize data classification labeling, ensuring that the data has standard consistency, and smoothing each type of data separately through the Kalman filtering algorithm to obtain the optimal estimated value of the corresponding data and extract it.

[0057] In this embodiment, the information processing of OPC data integration is completed by the PLC programmable logic controller in step S14, including: analyzing the actual operating status of the track laying machine based on the beam section position information, equipment inclination information, equipment posture information and equipment positioning information of the track laying machine, and realizing safe control and real-time early warning of the equipment operating status by comparing and analyzing the actual operating status of the track laying machine with the preset design operating status.

[0058] Specifically, the bridge and beam segment position information is monitored through the collaboration of a 3D high-frequency, low-wave rangefinder and a linear detector. The distance between the track-laying machine and the single-span construction center of the bridge and its plane position status are transmitted to the OPC data integration, converted into a standard format, and packaged for transmission. Furthermore, the beam segment position data is processed to safely calculate the distance between the track-laying machine and the bridge center and beam end under the hoisting operation conditions of different types of PK-section steel beams during the operation of the track-laying machine, determine the safety threshold, and filter and reduce the noise of the beam segment position data measured at the construction site received from the OPC data integration transmission through the PLC programmable logic controller. The processed data is compared with the calculated safety threshold. If the safety threshold is exceeded, an early warning is issued, and the track-laying machine operation position is adjusted immediately until the warning is eliminated.

[0059] Specifically, stress monitoring information is arranged according to structural design calculations; the stress data of the monitoring points is monitored by a compound variable chord sensor, transmitted to the OPC data integration, converted into a standard format, and packaged for transmission. Furthermore, stress monitoring data is processed, and finite element analysis is performed on the structural stress state of the PK-section steel beam under hoisting, prefabricated plate installation, and cable tensioning conditions. The stress thresholds of the diaphragm, web, and anchor box are determined considering the specified safety factor. The stress data received from the OPC data integration during the beam and slab installation process is filtered and noise-reduced by the PLC programmable logic controller. The processed data is compared with the calculated safety threshold. If the safety threshold is exceeded, an early warning is issued, and the posture of the laying machine and transport barge is adjusted until the beam and slab stress information is within a reasonable range to avoid excessive deformation of the beam and slab or the laying machine during installation. Furthermore, stress monitoring data processing is also used to monitor the force on the inclined cables through the PLC programmable logic controller. The force data on the inclined cables during the tensioning process in two stages, namely, the installation of the beams and slabs is completed and the pouring of the wet joints of the bridge deck beams and slabs is completed, are collected and compared with the tensioning design values ​​to form guidance and verification for the tensioning operations at the construction site. At the same time, the force on the cables during the construction process is monitored to avoid stress concentration.

[0060] Specifically, the internal force information of the steel beam structure is arranged according to the structural design concept and the supporting position of the laying machine. The load state of the components is monitored by surface stress gauges and transmitted to the OPC server for integration of the internal force data of the laying machine structure. The data format is converted and packaged for transmission through the OPC server. Specifically, the internal force data of the steel beam structure is processed by performing finite element stress analysis on the chord, vertical rod, and lower horizontal parallel span position under the lifting condition of the laying machine to verify the stability of the laying machine structure under the most unfavorable working condition. At the same time, the calculated stress of the laying machine under the most unfavorable working condition is imported into the PLC programmable logic controller as a safety control threshold. The PLC programmable logic controller filters and reduces the noise of the key structural stress data of the laying machine received from the OPC data integration transmission. The processed data is compared with the safety control threshold. When the measured data exceeds the limit, it proves that the construction process has exceeded the most unfavorable working condition of the theoretical analysis. At this time, the non-compliance of the construction organization must be dealt with in a timely manner. In this embodiment, the PLC programming data processing can automatically determine whether the monitoring information data meets the structural construction bearing capacity, form a four-level warning, and take appropriate response measures based on the warning information.

[0061] Specifically, the on-site environmental information is monitored by environmental information collection equipment, including the temperature, wind speed, rainfall, air pressure, and air humidity of the construction site. The OPC server integrates the construction site environmental data 405, converts the data into a standard format, and packages it for transmission. Furthermore, the construction site environmental data is processed, and the temperature, wind speed, rainfall, air pressure, and air humidity of the construction site are controlled according to the construction work conditions. The PLC programmable logic controller filters and de-noises the construction site environmental data received from the OPC data integration transmission, and compares and analyzes the measured data. When the measured on-site ambient temperature is higher than 35°C or higher than 32°C and the relative humidity is ≥80%RH, a high temperature warning is triggered, and the construction site takes measures such as adjusting working hours or rotating shifts. When the wind speed reaches 10m / s, a beam and slab hoisting operation warning is triggered. When the wind speed reaches 13m / s, a bridge deck operation warning is triggered. Similarly, a welding operation warning is triggered based on rainfall conditions.

[0062] Specifically, equipment tilt information is collected by installing inclination sensors on the main beams and pillars of the track laying machine to collect tilt status data of the equipment's key structures in the X and Y directions. At the same time, the operating data of the hydraulic sensors and stroke sensors of the track laying machine's hydraulic cylinders are collected. The tilt data of the main beams and pillars of the track laying machine are integrated through the OPC server, converted into a standard format, and packaged for transmission. Furthermore, the equipment tilt data is processed by determining the tilt status threshold of the main beams and pillars of the track laying machine according to the equipment design specifications. The tilt data of the main beams and pillars of the track laying machine at the construction site received from the OPC data integration transmission is filtered and noise-reduced through the PLC programmable logic controller. The processed data is compared with the threshold, and an alarm is issued when deviation exceeds the limit.

[0063] Specifically, the equipment posture information is integrated through the OPC server through the hydraulic sensor of the laying machine's lifting cylinder, the longitudinal and transverse cylinder stroke sensors, the hydraulic pump station pressure sensor, and the winch lifting weight data. The data is converted into a standard format and packaged for transmission. Furthermore, the equipment posture data is processed by pre-setting the equipment working index parameter thresholds such as cylinder stroke deviation, cylinder working pressure deviation, and winch lifting weight according to the working posture requirements of the laying machine. The PLC programmable logic controller filters and reduces noise on the construction site laying machine's operating posture data received from the OPC data integration transmission. The cylinder stroke deviation can reflect the tilt of the laying machine and the synchronous movement of the main beam and frame. The cylinder working pressure can reflect the sealing status of the equipment hydraulic system. When the deviation between the measured data and the equipment working parameter threshold exceeds the limit, the system will trigger an alarm.

[0064] Specifically, the equipment positioning information is collected through Beidou positioning tags to collect the location information of steel beam transport ships and the location information of on-site workers is collected through positioning safety helmets. Combined with the map data embedded in the Wiscada desktop system, visual control of equipment and personnel positioning data in dangerous workplaces is achieved.

[0065] In this embodiment, step S14 feeds the obtained logical, physical information, and construction environment data information into the construction structure model, the GIS real-scene site model, the construction equipment simulation model, and the construction dynamic information model, respectively, to complete the matching of the working posture of each simulation model with the physical information state and the dynamic construction simulation of the construction environment, including:

[0066] Create model attribute parameters that match the data collected on the construction site for the construction structure model, GIS real-scene site model, construction equipment simulation model, and construction dynamic information model. By integrating the data and model attribute parameters, the digital twin application of actual physical data is realized.

[0067] Linking the construction dynamic information model with production management data, and linking construction progress information, prefabricated beam and slab process acceptance data, and bridge structure block installation team information with the model to achieve a multi-dimensional digital twin of the construction dynamic information model;

[0068] The actual working scene of bridge construction is created by updating satellite 3D map image data and construction environment data information, and the GIS real-scene site model is automatically driven and adjusted as the satellite image changes.

[0069] In this embodiment, in order to realize the interactive application of BIM model and physical data collected by IoT multivariate data, modular correlation simulation drive (MKQ) can be used as the basis, and logic programming can be used as the information processing operation to realize the correlation between BIM model parameters and physical data to complete the matching of the working posture of the simulation model and the physical information state, thereby simulating the bridge construction.

[0070] Specifically, the data processing of modular correlation simulation drive (MKQ) is to clean and filter the field data collected by IoT devices, remove excessive deviations and non-standard data to eliminate data differences, and synchronously integrate multi-source data through sensor data interaction strategies to achieve data classification labels, ensure that the data has standard consistency, and smooth and measure the data through the Kalman filter algorithm to obtain the optimal estimate of the data and extract it.

[0071] Specifically, the data and model fusion of modular correlative simulation drive (MKQ) creates model attribute parameters for the BIM model that match the data collected at the construction site, such as the jacking cylinder stroke, cylinder pressure, winch lifting weight, upper beam horizontality, etc. of the track laying machine. Through the fusion and correspondence of data and model parameters, the digital twin application of actual physical data is realized.

[0072] Specifically, the BIM model is associated with production management data, and the construction progress information, prefabricated beam and slab process acceptance data, and bridge structure block installation team information are associated with the model to realize a multi-dimensional digital twin based on the BIM model.

[0073] Specifically, the BIM model is based on BIM software modeling, and creates the actual working scene of bridge construction through satellite three-dimensional map images + oblique photography real-scene modeling technology, which satisfies the automatic driving adjustment of the real-scene environment model as the satellite image changes. Based on the BIM information model, the bridge construction simulation in the form of PK-type cross-section steel beam + concrete precast bridge deck composite beam is carried out.

[0074] Specifically, the working scenario automatically identifies and obtains the water level, water flow velocity, flow rate and 10-nautical-mile main beam transportation positioning information at the bridge location based on the satellite three-dimensional map image data update and the reservoir water level monitoring open source data, integrates the relevant network open source data information with OPC data, automatically completes the information data processing through PLC programming, and inputs it into the bridge construction simulation.

[0075] Specifically, the modular correlation simulation drive (MKQ) is used to match the water level status of the bridge site during the flood season and dry season with the simulation posture of the information model, and to display the relevant coordinated information locally.

[0076] In the embodiment of the present invention, oblique photography real-scene modeling is designed to address the problem of inaccurate modeling caused by the influence of water flow fluctuations and water surface reflection on the oblique photography modeling of wide-area water flow surfaces. By debugging the technical parameters of front-end data processing for image format, exposure rate, and noise reduction balance, and back-end data processing for regional multi-point adjustment and multi-point image matching based on the width of the water area, a real-scene modeling data processing parameter set is formed to achieve accurate and efficient modeling of wide-area water flow surfaces and the integration of modular correlation simulation drive (MKQ) data with the real-scene model.

[0077] In an embodiment of the present invention, in a bridge construction simulation, a target area is set according to the designed main beam segment division, and the target area connects the construction monitoring sensor information and the construction monitoring image information.

[0078] In the embodiment of the present invention, the bridge construction simulation satisfies the requirement that the main process contents such as the lifting of the N-segment steel beams of the PK section, the installation of the N-2 segment prefabricated bridge deck, the initial tensioning of the inclined cables, and the casting of wet joints are not carried out in the same segment area, but meet the process characteristics of the simultaneous execution of multiple processes such as beam erection and decking.

[0079] In another embodiment of the present invention, Figure 3 As shown, the method further includes step S15:

[0080] S15. Data processing and analysis of the construction monitoring sensor information under the current stage of construction working conditions is performed to form a construction simulation of the construction work of the PK-section steel beam and the concrete precast bridge deck after superposition. Combined with the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction working conditions, the deduction and prediction of the safety warning of the next stage of construction work is performed.

[0081] In this embodiment of the present invention, an Ecological Logic Information Processing Model (ELPML) is developed to simulate the construction of a track-laying machine and analyze the subsequent construction process. This model enables the prediction and alerting of safety warnings for the next phase of construction. Specifically, the ELPML automatically predicts and alerts safety warnings for the next phase of construction by processing and analyzing current construction monitoring data and combining it with simulated construction status and actual measured construction monitoring information for the next phase.

[0082] In this embodiment, a clear visual display interface can be built through the Wiscada desktop system to integrate sensor positioning, PLC programming data processing, modular correlation simulation drive (MKQ), and state logic information processing model (ELPML) data to achieve good visual communication of system information.

[0083] Furthermore, in the process of executing the deduction and prediction of the safety warning of construction work in the next stage, the comparison threshold range of different alarm levels of various safety warnings is adjusted according to the deviation inertia ratio of the data to eliminate the monitoring error caused by the cumulative loss of components.

[0084] Furthermore, the deduction and prediction of the execution of the safety warning of the construction work in the next stage includes: using the deep learning model of the neural network to take the current physical state of the laying machine and the bridge deck beam to be installed in the next step as the analysis object, according to the lifting position of each bridge deck beam and the position of the laying machine and the active cylinder stroke data, it is obtained whether the position of the equipment and the cylinder stroke when lifting the next section of the bridge deck beam in the current position and state meet the beam-slab docking requirements during the installation process; according to the current posture of the laying machine and the form of the beam to be installed in the next step, the inclination and deformation state of the laying machine is predicted according to the stress and structural strain calculation, so as to realize the prediction of the stability of the equipment operation.

[0085] Specifically, the Ecological Logical Information Processing Model (ELPML) can also automatically identify the physical information of subsequently installed steel beams or bridge decks by analyzing the FRID tag data of beam-slab segments and the recorded data of installed steel beams and bridge decks, thereby realizing dynamic deduction of the asynchronous construction of bridge deck steel beam and bridge deck installation.

[0086] In another embodiment of the present invention, the method further comprises:

[0087] Acquire construction monitoring video information for the main bridge. Specifically, this information can be obtained through high-definition digital cameras while simultaneously acquiring information from the construction monitoring sensors of each bridge-laying machine. This information is then remotely transmitted to the PLC programmable logic controller (PLC) via a server streaming application. The PLC's pre-set intelligent hazard identification algorithm proactively identifies falls from height, fires, and unsafe worker behavior, enabling the system to provide safety supervision and emergency command capabilities in hazardous construction sites.

[0088] In this embodiment, the construction site construction image data is collected by a high-definition digital camera, and the intelligent hazard identification algorithm is used to analyze the data to achieve active identification of falls from heights, fires, and unsafe behaviors of workers. Specifically, the intelligent hazard identification algorithm is used to analyze the on-site construction images, and the collected images are pre-processed by noise reduction, image contrast enhancement, and color boundary space recognition conversion. Specifically, the PLC programmable logic controller uses the convolutional neural network (CNN) image recognition algorithm to identify the flame shape, smoke effect, and reflective characteristics of clothing in the image, and feedback is given on the dangerous state information of fire and explosion and the non-compliant behavior information of workers not wearing reflective clothing or helmets; at the same time, human body recognition is performed on the image and the FRID tags of the edge protection components and dangerous equipment on the construction site are dynamically tracked, and feedback is given on the positional relationship between the personnel and the dangerous operating equipment and the dangerous edges; thus, early warning of the dangerous state of the construction site and the dangerous behavior of the workers is achieved.

[0089] In an embodiment of the present invention, a digital twin digital intelligent construction method for a track laying machine provided by the present invention further includes a data tracing implementation step, specifically including:

[0090] The data server and application server are independently deployed to formulate a data storage and backup strategy. Based on the data server's 1000GB capacity, system data is backed up monthly. The equipment's operating data under various working conditions is mined and analyzed to form standard values ​​for the equipment's operating status parameters under various working conditions, such as the position data and cylinder movement data of the track laying machine during the installation of each type of bridge deck slab. A database of construction process monitoring data and equipment parameters is established, and a standardized format template for data output is created to export data reports. Data reports are used as information carriers for information exchange and penetration between various disciplines and departments. A professional project production management process control system is established around the working data of the new track laying machine, promoting the continuous optimization of the cable-stayed bridge precast girder and slab installation construction process. Specifically, the data report is based on the production and operation data of the track laying machine, forming a standard format for cable-stayed bridge slab installation construction process data. It mainly reflects the staged construction process records, the installed bridge deck slab segments, the number and classification of warnings issued during the stage, and the maximum structural internal force of the track laying machine, the maximum main beam inclination, the maximum lifting weight, and other production data that occurred during this stage.

[0091] In the embodiment of the present invention, see Figure 4 Communication and data transmission adopts a combination of wired and wireless data acquisition and transmission, sets an independent power supply, and integrates wired transmission + 5G wireless data communication to achieve a data reception and transmission range of up to 19 kilometers and a millisecond-level feedback speed, accurately and quickly inputting information into OPC data integration.

[0092] In the embodiment of the present invention, data can be visualized and deployed through the Wiscada desktop system software, and the data of the PLC programmable logic controller or some Internet of Things devices can be processed to develop and implement personalized HMI screens for each system functional module.

[0093] The present invention innovatively develops a digital twin digital intelligent construction method and system for an integrated laying machine. For the construction process of post-overlapping of PK-section steel beams and precast concrete bridge panels, which is weak in the existing technology, the main process contents such as steel beam hoisting, precast bridge panel paving, phased tensioning of inclined cables, and wet joint casting are not carried out in the same segment area, but meet the process characteristics of simultaneous execution of multiple processes. Digital twin digital intelligent construction is carried out, and the safety inspection of equipment and steel beam structure, video monitoring information and digital twin simulation model during the construction process are associated and displayed, so as to realize the use of monitoring data to drive model simulation, and the model simulation feedback monitoring parameters. The manually collected monitoring data is converted into automatic acquisition, processing and three-dimensional simulation display, which enhances the timeliness and accuracy of monitoring data and improves the digital intelligent construction capability of bridge engineering.

[0094] The present invention integrates logic and physical information with OPC data, automatically completes the information extraction, processing, and output of the data integration through PLC programming, adopts modular correlation simulation drive (MKQ) to complete the matching of the working posture and physical information of the simulation model, and innovatively develops the ecological logic information processing model (ELPML). Combined with the construction simulation posture and the actual construction monitoring information of the next stage, it automatically carries out the deduction and prediction of the construction safety warning in the next stage. While ensuring construction monitoring, it develops the process monitoring deduction of ecological logic processing to achieve advanced monitoring of construction safety and improve the safety protection level and digital intelligence level of engineering construction.

[0095] The present invention collects environmental information using satellite maps and network messages, while superimposing a physical information model based on modular correlation simulation drive (MKQ) to achieve more comprehensive feedback on on-site work status information.

[0096] This invention organically combines monitoring data with digital twins, enabling advanced simulation of working conditions, predictive data feedback, and predictive alarms. It transforms the approach to bridge construction safety management, shifting from a problem-finding and problem-solving approach to one that predicts potential safety hazards and proactively investigates and controls them. This fully ensures the safety and reliability of digitally intelligent bridge construction.

[0097] The digital twin digital construction method of the track-laying machine provided by the present invention takes a specialized bridge construction equipment that meets the needs of asynchronous installation of prefabricated beams and slabs of large-span bridges as the research object. Correspondingly, in terms of design and operation information monitoring, it is not limited to the monitoring of the track-laying machine itself, but also covers the monitoring of the position relationship between the track-laying machine and the prefabricated beam and slab segments, the positioning of construction and transportation equipment (pilot application of Beidou positioning in the engineering construction process), and changes in the surrounding environment of the construction. It emphasizes the integrity of construction process control around the operation of the track-laying machine.

[0098] In the technical solution of the present invention, the operation monitoring of the laying machine is specialized, and the Internet of Things monitoring equipment targeted at the production needs of professional equipment is used to obtain information data that truly reflects the production status, avoid data redundancy and cumbersome operation of the system, and improve the practicality of the system.

[0099] In the technical solution of the present invention, by building an image recognition algorithm suitable for determining dangerous elements at construction sites, the ability to automatically identify dangerous behaviors of personnel and dangerous states of objects at large-span bridge construction sites through images is enhanced, highlighting the application value of the system in construction safety management.

[0100] In the technical solution of the present invention, by building a driver that associates physical data with models, a one-to-one correspondence between the virtual model and the physical data is achieved, thereby realizing a vivid display of the ready-made collected data and realizing a more realistic digital twin of the construction site.

[0101] In the technical solution of the present invention, by building an ecological logic information processing model and strengthening the understanding of the construction process by digital technology, the system can automatically identify the next construction content and the model of the prefabricated bridge deck beams and slabs to be hoisted in the next step, and combine the current status of the equipment to determine whether the equipment meets the requirements of the next construction and issue an early warning, thereby achieving the effect of advanced control.

[0102] The technical solution of the present invention provides a more accurate and complete real-scene modeling function, which forms a real-scene model that better reflects the actual on-site environment by processing image data and superimposing on-site environmental data (water flow, water surface width, etc.).

[0103] The technical solution of the present invention provides a more practical system data post-processing function module to store and back up process data, form professional equipment operation and construction production reports, extract key data, and collaboratively share all information of the laying machine during the construction and production process among all project management participants, management departments, and professionals, so as to achieve optimization and improvement of production equipment and production processes.

[0104] For simplicity of description, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because certain steps can be performed in other orders or simultaneously according to the embodiments of the present invention. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0105] Another embodiment of the present invention further provides a digital twin digital intelligent construction system for a track laying machine, which includes a functional module for implementing the digital twin digital intelligent construction method for a track laying machine as described in any of the above items. Figure 5 The present invention schematically shows a structural diagram of a digital twin digital intelligent construction system for a track laying machine, with reference to Figure 5 , a digital twin digital intelligent construction system of a track laying machine according to an embodiment of the present invention specifically includes:

[0106] The simulation model building module 501 is used to pre-build a construction structure model, a GIS real-scene site model, a construction equipment simulation model, and a construction dynamic information model;

[0107] Structural monitoring module 502 is used to obtain construction monitoring sensor information from each track-laying machine during the main bridge construction process, using IoT devices installed at key points on each track-laying machine during the construction operation of the PK-section steel beam and the precast concrete bridge deck. The construction monitoring sensor information includes beam segment position information, stress monitoring information, steel beam structure internal force information, construction site environment information, equipment tilt information, equipment posture information, and equipment positioning information.

[0108] The data transmission module 503 is used to transmit the construction monitoring sensor information to the OPC server for OPC data integration, to form the track laying machine logic, physical information and construction environment data information, and to transmit the OPC data integration to the PLC programmable logic controller;

[0109] The construction linkage digital twin module 504 is used to complete the information extraction and processing of OPC data integration through the PLC programmable logic controller, and feed back the obtained logical, physical information and construction environment data information to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, to complete the matching of the working posture of each simulation model with the physical information status and the dynamic construction simulation of the construction environment, and realize the digital twin digital intelligent construction of actual physical data.

[0110] In another embodiment of the present invention, the system also includes a construction simulation analysis module not shown in the accompanying drawings. The construction simulation analysis module is used to perform data processing and analysis on the construction monitoring sensor information under the current stage of construction operation conditions to form a construction simulation simulation of the construction operation of the PK-type cross-section steel beam and the concrete prefabricated bridge deck after superposition, and combine the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction operation conditions to perform deduction and prediction of the safety warning of the next stage of construction operation.

[0111] In another embodiment of the present invention, the system also includes a construction simulation analysis module not shown in the accompanying drawings. The construction simulation analysis module is used to perform data processing and analysis on the construction monitoring sensor information under the current stage of construction operation conditions to form a construction simulation simulation of the construction operation of the PK-type cross-section steel beam and the concrete prefabricated bridge deck after superposition, and combine the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction operation conditions to perform deduction and prediction of the safety warning of the next stage of construction operation.

[0112] In another embodiment of the present invention, the system further includes a video monitoring module not shown in the accompanying drawings, and the video monitoring module is used to obtain monitoring image information of the main bridge construction.

[0113] Furthermore, the data transmission module 503 remotely transmits the construction monitoring image information to the PLC programmable logic controller via the server streaming application;

[0114] Furthermore, the system also includes an intelligent recognition module not shown in the accompanying drawings, which is used to actively identify high-altitude falls, fires, and unsafe behaviors of operators in construction monitoring image information through a preset hazard source intelligent recognition algorithm.

[0115] In the specific implementation process of this system embodiment, you can refer to the above method embodiment, which has the corresponding technical effects

[0116] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, any of the claimed embodiments may be used in any combination.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A digital twin construction method for a track laying machine, characterized in that: The method is used for the construction operation condition of post-overlapping of PK-section steel beams and precast concrete bridge decks, in which the hoisting construction of the PK-section steel beams and the paving construction of the precast concrete bridge decks are carried out simultaneously and the construction areas are located in different sections, including: Pre-build construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model; Under the construction conditions of post-lapping of PK-section steel beams and precast concrete decks, IoT devices installed at key points on each bridge-laying machine acquire construction monitoring sensor information from each machine during the main bridge construction process. This information includes beam segment position information, stress monitoring information, internal force information of the steel beam structure, construction site environment information, equipment tilt information, equipment posture information, and equipment positioning information. Transmitting the construction monitoring sensor information to the OPC server for OPC data integration to form the track laying machine logic, physical information and construction environment data information, and transmitting the OPC data integration to the PLC programmable logic controller; The PLC programmable logic controller is used to extract and process OPC data integration information, and the obtained logical, physical information and construction environment data are fed back to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively. This matches the working posture of each simulation model with the physical information status and performs dynamic construction simulation of the construction environment, realizing digital twin digital intelligent construction of actual physical data. Data processing and analysis are performed on the construction monitoring sensor information under the current stage of construction working conditions to form a construction simulation of the superposition of PK-section steel beams and concrete prefabricated bridge panels. Combined with the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction working conditions, the deduction and prediction of the safety warning of construction work in the next stage are performed. The deduction and prediction of the safety warning of construction work in the next stage include: using the current physical state of the laying machine and the bridge deck beams to be installed in the next step as analysis objects through the deep learning model of the neural network, according to the position of each bridge deck beam hoisting and the position of the laying machine and the active cylinder stroke data, it is determined whether the position of the equipment and the cylinder stroke when hoisting the next section of the bridge deck beam in the current position and state meet the beam-slab docking requirements during the installation process; according to the current posture of the laying machine and the form of the beam to be installed in the next step, the inclination and deformation state of the laying machine are predicted according to the stress and structural strain calculation, so as to predict the stability of the equipment operation.

2. The method according to claim 1, characterized in that During the deduction and prediction process of the next stage of construction work safety warning, the comparison threshold range of different alarm levels of various safety warnings is adjusted according to the deviation inertia ratio of the data to eliminate the monitoring error caused by the cumulative loss of components.

3. The method according to claim 1, characterized in that The method further comprises: Obtaining monitoring image information of the main bridge construction; Remotely transmit construction monitoring image information to the PLC programmable logic controller through the server streaming application; Through the preset intelligent hazard identification algorithm, construction monitoring image information is used to actively identify high-altitude falls, fires, and unsafe behaviors of workers.

4. The method according to any one of claims 1 to 3, characterized in that The information extraction of OPC data integration is completed by using a PLC programmable logic controller, including: Clean and filter the construction monitoring sensor information in OPC data integration, remove excessive deviations and non-standard data to eliminate data differences; Through the sensor data interaction strategy, multi-source data are synchronously integrated to realize data classification labeling and ensure the consistency of data standards. Through the Kalman filter algorithm, each type of data is smoothed separately to obtain the optimal estimated value of the corresponding data and extract it.

5. The method according to any one of claims 1 to 3, characterized in that The information processing to complete OPC data integration through PLC programmable logic controller includes: The actual operating status of the track laying machine is analyzed based on the beam section position information, equipment inclination information, equipment posture information and equipment positioning information. By comparing and analyzing the actual operating status of the track laying machine with the preset design operating status, safe management and real-time early warning of the equipment operating status are achieved.

6. The method according to any one of claims 1 to 3, characterized in that The obtained logical, physical information and construction environment data information are fed back to the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively, completing the matching of the working posture of each simulation model with the physical information state and the dynamic construction simulation of the construction environment, including: Create model attribute parameters that match the data collected on the construction site for the construction structure model, GIS real-scene site model, construction equipment simulation model, and construction dynamic information model. By integrating the data and model attribute parameters, the digital twin application of actual physical data is realized. Linking the construction dynamic information model with production management data, and linking construction progress information, prefabricated beam and slab process acceptance data, and bridge structure block installation team information with the model to achieve a multi-dimensional digital twin of the construction dynamic information model; The actual working scene of bridge construction is created by updating satellite 3D map image data and construction environment data information, and the GIS real-scene site model is automatically driven and adjusted as the satellite image changes.

7. A digital twin digital intelligent construction system for a track laying machine, characterized by: The system is used for the construction operation of post-superposition of PK-section steel beams and precast concrete bridge decks. The PK-section steel beam hoisting construction and the precast concrete bridge deck paving construction are carried out simultaneously and the construction areas are located in different sections, including: Simulation model building module, used to pre-build construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model; The structural monitoring module is used to obtain construction monitoring sensor information from each track-laying machine during the main bridge construction process through IoT devices installed at key points of each track-laying machine under the construction conditions of the PK-section steel beam and the precast concrete bridge deck. The construction monitoring sensor information includes beam segment position information, stress monitoring information, steel beam structure internal force information, construction site environment information, equipment tilt information, equipment posture information, and equipment positioning information; A data transmission module is used to transmit the construction monitoring sensor information to the OPC server for OPC data integration, to form the track laying machine logic, physical information and construction environment data information, and to transmit the OPC data integration to the PLC programmable logic controller; The construction linkage digital twin module is used to complete the information extraction and processing of OPC data integration through the PLC programmable logic controller, and feed the obtained logical, physical information and construction environment data information into the construction structure model, GIS real-scene site model, construction equipment simulation model and construction dynamic information model respectively. It completes the matching of the working posture of each simulation model with the physical information status and the dynamic construction simulation of the construction environment, realizing digital twin digital intelligent construction of actual physical data; The system further comprises: The construction simulation analysis module is used to process and analyze the construction monitoring sensor information under the current construction working conditions to form a construction simulation simulation of the construction work of the PK-section steel beam and the concrete prefabricated bridge deck after superposition. Combined with the construction simulation posture and the measured construction monitoring sensor information under the next stage of construction working conditions, the deduction and prediction of the safety warning of the construction work in the next stage are performed. The deduction and prediction of the safety warning of the construction work in the next stage include: using the deep learning model of the neural network to take the current physical state of the laying machine and the bridge deck beam to be installed in the next step as the analysis object, according to the position of each bridge deck beam hoisting and the position of the laying machine and the active cylinder stroke data, whether the position of the equipment and the cylinder stroke when hoisting the next section of the bridge deck beam in the current position and state meet the beam-slab docking requirements during the installation process; according to the current posture of the laying machine and the form of the beam to be installed in the next step, the inclination and deformation state of the laying machine are predicted according to the stress and structural strain calculation, so as to predict the stability of the equipment operation.

Images