An intelligent collaborative control system for physical simulation of disasters in ultra-large-scale deep engineering projects

Abstract

This invention provides an intelligent collaborative control system for physical simulation of ultra-large-scale deep engineering disasters, belonging to the field of deep engineering disaster physical simulation technology. The system includes a cross-protocol transparent and efficient communication architecture responsible for communication and data transmission between the various components of the physical simulation facility; a test big data storage and fusion analysis module for multi-source heterogeneous test big data storage and fusion analysis; a multi-task joint planning module for formulating and planning physical simulation test task plans; an intelligent dynamic collaborative control module for constructing a collaborative control model and performing real-time dynamic collaborative control of the physical simulation test process; a collaborative control model autonomous optimization module for continuously optimizing the collaborative control model; and a multi-task intelligent execution fault-tolerant module and a multi-task integrated display module providing intelligent fault tolerance and integrated display functions. This system can achieve intelligent dynamic collaborative control of multiple strongly coupled systems in an ultra-large-scale deep engineering disaster physical simulation facility.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deep engineering disaster physical simulation, and particularly relates to an intelligent collaborative general control system for super-large deep engineering disaster physical simulation. BACKGROUND

[0002] The physical simulation test of the existing size can only simulate simple geological structure and simple excavation, and can only apply stress environment. The super-large deep engineering disaster physical simulation test aims to simulate deep engineering rock mass characteristics, geological structure, environmental conditions and engineering activities. In order to achieve this goal, the super-large deep engineering disaster physical simulation test is composed of deep complex geological body 3D printing, deep engineering environment application, robot excavation, multi-element information monitoring and other systems, and highly coupled and cooperatively works. If each system adopts independent control mode and only relies on internal information of the system to carry out local work, the coupled environment loading and engineering activity tasks of the physical simulation test cannot be correctly or efficiently completed.

[0003] Therefore, it is necessary to design a collaborative general control system, which aims to ensure that the overall facility correctly carries out the test task with the global optimal execution efficiency according to the overall test target and plan of the physical simulation test, and realizes efficient interconnection and intercommunication between systems through intelligent optimization decision method.

[0004] In order to achieve the above-mentioned goal, the primary task of the deep engineering disaster physical simulation collaborative general control system is to collect test big data from each system in real time, and to ensure efficient interconnection and intercommunication between systems. In addition, during the super-large deep engineering disaster physical simulation test, the core task of the collaborative general control system is to realize the following collaborative control tasks:

[0005] (1) Environmental application collaborative control: temperature field, pressure field and flow field are important geological parameters of deep engineering geological body, and the three are coupled and influence each other's application process. The pressure parameters of the hydraulic loading system, the temperature parameters of the temperature control system and the fluid parameters of the injection system need to be cooperatively controlled to ensure that the physical simulation test is carried out in the expected geological environment.

[0006] (2) Deep buried tunnel and underground chamber excavation collaborative control: on the basis of environmental application collaborative control, the excavation robot construction and multi-element information monitoring system are cooperatively controlled to ensure that the excavation process is correctly, efficiently and safely carried out according to the expected test scheme.

[0007] (3) Collaborative control of deep metal mining: Based on the collaborative control of the environment, it is necessary to carry out collaborative interaction between the robot excavation, cutting, and mining operations and the monitoring information of the multi-dimensional information monitoring system; collaboratively regulate the filling preparation and conveying device in the filling system, and adjust the filling preparation process and filling process in a timely manner based on the data such as the deformation of the surrounding rock and the stress field changes monitored by the multi-dimensional monitoring system to ensure good filling matching and filling rate; collaboratively regulate the air supply parameters of the ventilation system and the behavior posture and construction parameters of the robot in the robot excavation system to ensure that the temperature, pollutants, and harmful gases in the construction environment meet the requirements of the physical simulation test scheme.

[0008] (4) Collaborative control of deep oil and gas extraction: Based on the collaborative control of the environment, the collaborative robot excavation system and the multi-dimensional information monitoring system ensure that the excavation of vertical and horizontal wells meets the requirements of the physical simulation test task; the collaborative injection system and the multi-dimensional information monitoring system adjust key parameters such as the flow rate and pressure of the injected multiphase fluid in a timely manner to ensure that the injection system completes stable injection according to the physical simulation test plan.

[0009] (5) Collaborative control of deep geothermal development: Based on the collaborative control of the environment, the collaborative robot excavation system and the multi-dimensional information monitoring system ensure that the excavation of injection wells and production wells meets the requirements of physical simulation test tasks; the collaborative injection system and the multi-dimensional monitoring system continuously monitor the development of fracture network and adjust the injection parameters in a timely manner to ensure that the injection and production processes proceed stably.

[0010] However, no control system for physical simulation experiments has yet been found that can achieve the collaborative control task of the aforementioned physical simulation experiment for disasters in ultra-large deep engineering projects.

[0011] Furthermore, with the continuous improvement of the requirements and technical indicators for physical simulation of disasters in deep engineering, the complexity of control requirements has increased significantly, posing enormous challenges to efficient communication and collaborative control among various systems. These challenges are mainly manifested in the following three aspects:

[0012] (1) Low efficiency of cross-protocol communication: The system composition of the ultra-large deep engineering disaster physical simulation facility is extremely complex. The control accuracy, response time, number of controlled units of the local control devices equipped in each system are different. There are also differences in control methods, communication protocols, interface design, bus layout design and deployment, which leads to problems such as limited communication, low communication efficiency and time asynchrony between the central control system and each system.

[0013] (2) Low efficiency of collaborative task execution: As can be seen from the task of the overall control system, the collaborative overall control requirements of the physical simulation test of deep engineering disaster are extremely complex. It involves the application and control of multiple coupled environments such as stress, pressure, and temperature, as well as the multi-process behavior control of various complex engineering activities such as injection and extraction, excavation, ventilation, and filling. Since the operating states of each system have strong coupling characteristics, if only the independent control systems of each system are considered for task planning and control, it will lead to a low success rate of physical simulation test tasks, poor fault tolerance in the test execution process, longer test cycle and increased cost.

[0014] (3) The collaborative control model is difficult to optimize: the collaborative control task of each physical simulation experiment is difficult to draw on the collaborative control experience in the big data of historical experiments, and it is impossible to guarantee that the collaborative control model of physical simulation experiment is used to execute the collaborative task of physical simulation experiment. Summary of the Invention

[0015] The technical problem to be solved by the present invention is to provide an intelligent collaborative control system for physical simulation of disasters in ultra-large deep engineering projects, which addresses the shortcomings of the prior art and realizes multi-task intelligent collaborative control of various engineering activities.

[0016] To address the aforementioned technical problems, the technical solution adopted by this invention is: an intelligent collaborative control system for physical simulation of ultra-large-scale deep engineering disasters, comprising a cross-protocol transparent and efficient communication architecture, an experimental big data storage and fusion analysis module, a multi-task joint planning module, an intelligent dynamic collaborative control module, and a collaborative control model autonomous optimization module; the cross-protocol transparent and efficient communication architecture is responsible for communication and data transmission between the various component systems of the ultra-large-scale deep engineering disaster physical simulation facility; the experimental big data storage and fusion analysis module is used to store and fusion analyze multi-source heterogeneous experimental big data collected from various systems of the ultra-large-scale deep engineering disaster physical simulation experimental facility based on the cross-protocol transparent and efficient communication architecture; the multi-task joint planning module is used to formulate task plans that can be efficiently executed in the ultra-large-scale deep engineering disaster physical simulation experiment; the intelligent dynamic collaborative control module is used to generate a collaborative control model to coordinate and control the real-time field process of the ultra-large-scale deep engineering disaster physical simulation experimental facility; the collaborative control model autonomous optimization module is used to autonomously learn control experience from multiple historical experimental big data to achieve continuous optimization of the collaborative control model.

[0017] Preferably, the intelligent collaborative control system for the physical simulation of ultra-large-scale deep engineering disasters further includes a multi-task intelligent execution fault-tolerant module and a multi-task integrated display module; the multi-task intelligent execution fault-tolerant module is used to ensure the availability of the ultra-large-scale deep engineering disaster physical simulation test facility in the event of a communication failure, and to provide intelligent fault tolerance for abnormal and incorrect test task execution; the multi-task integrated display module displays the detailed values ​​and overall development trend of the deep engineering disaster physical simulation test data of each system, or provides a visual overview of multiple systems on the same page.

[0018] Preferably, the cross-protocol transparent and efficient communication architecture collects and transmits test process and result data of each component system of the ultra-large deep engineering disaster physical simulation facility in real time, and obtains the test task execution status and results of each system; it provides a multi-protocol adaptive communication gateway, which shields different communication protocols through external bus and internal bus design, and realizes unified access for different control methods, communication protocols and interface designs.

[0019] Preferably, the experimental big data storage and fusion analysis module stores multi-source heterogeneous experimental big data collected from various systems of the ultra-large deep engineering disaster physical simulation test facility based on a cross-protocol transparent and efficient communication architecture in a cloud platform distributed file system; preprocesses the experimental big data and uses a dynamically expandable semantic template library to perform semantic mapping between data sources of various systems in the ultra-large deep engineering disaster physical simulation test facility, realizing semantic fusion of multi-source heterogeneous experimental big data; provides a unified calculation model for batch and stream fusion processing, integrating batch calculation of historical experimental big data of ultra-large deep engineering disaster physical simulation with streaming calculation of real-time experimental big data collected from various systems, and realizes efficient calculation and analysis of physical simulation experimental big data through unified batch and stream expression and intelligent planning of calculation tasks.

[0020] Preferably, the multi-task joint planning module defines the task based on the overall objectives and content of the ultra-large deep engineering disaster physical simulation test task; intelligently decomposes the overall physical simulation test task into sub-tasks on each system; performs sub-task planning based on joint design optimization through a data and knowledge-driven intelligent optimization decision-making method, and determines the dependencies between sub-tasks; and generates the control logic and control timing of the sub-tasks based on the sub-task planning and dependencies, thereby completing the sub-task allocation of each system.

[0021] Preferably, the intelligent dynamic collaborative control module transforms the control logic and control timing in the task plan generated by the multi-task joint design and optimization module into control instructions for the underlying controllers of each system in the ultra-large deep engineering disaster physical simulation test. The control instructions are issued to each system and executed. A collaborative control model is generated through intelligent collaborative control optimization technology to perform adaptive error control on each sub-task, ensuring the achievement of collaborative goals. The sub-tasks are dynamically allocated based on the execution status and results returned by each system.

[0022] Preferably, the collaborative control model autonomous optimization module, based on the massive historical experimental big data provided by the experimental big data storage and fusion analysis module, uses a data-driven deep learning model to analyze the experimental process and results, analyze the limiting factors of the execution efficiency of the ultra-large deep engineering disaster physical simulation test task, and autonomously optimize the operating parameters and collaborative control model parameters of similar tasks.

[0023] Preferably, the multi-task intelligent execution fault-tolerant module adopts a communication redundancy design based on flexible switching between primary and secondary channels, providing an availability protection mechanism in case of communication failure to avoid the physical simulation test operation being affected by communication failure; when anomalies or errors occur during the execution of the test sub-tasks allocated by each system, anomaly capture is performed, and the cause of the anomaly or error is determined through intelligent analysis of log information, thereby automatically correcting the overall task and sub-tasks, avoiding irreparable systemic and catastrophic errors in the ultra-large deep engineering disaster physical simulation test facility.

[0024] Preferably, the multi-task integrated display module supports multi-task integrated information including equipment operation information and health status of each system in the deep engineering disaster physical simulation test, test execution process analysis results, test process monitoring information, and test big data intelligent analysis and calculation results; the display mode supports multi-modal integrated display of multi-dimensional data charts, multimedia data, and three-dimensional rendering models.

[0025] The beneficial effects of adopting the above technical solution are as follows: The intelligent collaborative control system for physical simulation of disasters in ultra-large-scale deep engineering provided by this invention can achieve:

[0026] (1) Transparent and efficient communication across multiple systems and protocols: It enables transparent and efficient communication and data exchange across protocols, which can ensure the interconnection of experimental big data among various systems of the ultra-large deep engineering disaster physical simulation facility.

[0027] (2) Multi-task intelligent collaborative control: realize intelligent dynamic collaborative control of multiple strongly coupled systems of ultra-large deep engineering disaster physical simulation facility, and ensure the successful completion of test tasks with optimal execution efficiency.

[0028] (3) Autonomous optimization of collaborative control model: It realizes intelligent analysis of system bottlenecks of ultra-large deep engineering disaster physical simulation facility, autonomously optimizes collaborative control model, and can continuously improve test execution efficiency. Attached Figure Description

[0029] Figure 1 This is a structural block diagram of an intelligent collaborative control system for physical simulation of disasters in ultra-large deep engineering projects, provided in an embodiment of the present invention.

[0030] Figure 2 A flowchart for batch-stream fusion calculation of experimental big data provided in an embodiment of the present invention;

[0031] Figure 3 The flowchart of the autonomous optimization of the collaborative control model provided in this embodiment of the invention. Detailed Implementation

[0032] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0033] In this embodiment, an intelligent collaborative control system for physical simulation of disasters in ultra-large-scale deep engineering projects is described, such as... Figure 1 As shown, it includes a cross-protocol transparent and efficient communication architecture, an experimental big data storage and fusion analysis module, a multi-task joint planning module, an intelligent dynamic collaborative control module, a collaborative control model autonomous optimization module, a multi-task intelligent execution fault-tolerant module, and a multi-task integrated display module;

[0034] The cross-protocol transparent and efficient communication architecture is responsible for communication and data transmission between the various components of the ultra-large deep engineering disaster physical simulation facility. This architecture collects and transmits real-time test process and result data from each component system, and obtains the test task execution status and results of each system. It also provides a cross-protocol adaptive communication gateway, including a protocol adaptation layer and a format conversion layer. Through external and internal bus design, it shields the communication differences between systems, achieving unified access for different control methods, communication protocols, and interface designs, as well as unified data transmission. When receiving data from various systems, the cross-protocol adaptive communication... The communication gateway extracts the data portion from the data packet via the external bus, encapsulates it into a custom general message through the format conversion layer, and transmits it to the experimental big data storage and fusion analysis module via the internal bus. When sending data to various systems, the cross-protocol adaptive communication gateway receives the general message transmitted by the internal bus. The protocol adaptation layer embeds the general message into the data packet that conforms to the communication protocol format of the target system according to the target system's communication protocol, and transmits it to the target system via the external bus. By adopting the above bus-based communication method, the communication architecture is simplified, the scalability of the communication architecture is enhanced, the communication and data exchange efficiency between various systems is improved, and transparent interconnection of the ultra-large deep engineering disaster physical simulation facility is realized.

[0035] The experimental big data storage and fusion analysis module is used to store and fuse multi-source heterogeneous experimental big data collected from various systems of the ultra-large deep engineering disaster physical simulation experimental facility based on a cross-protocol transparent and efficient communication architecture. In this embodiment, the collaborative control system collects experimental data from various systems based on the cross-protocol transparent and efficient communication architecture, such as geological body data such as similar material states, nozzle behavior parameters, and geological body scanning images collected from the 3D printing system; pressurization data such as pressure and displacement parameters obtained from the three-dimensional loading system; and environmental data such as temperature, injection flow rate, and pressure collected from the high-temperature injection system. Environmental parameters; engineering activity data such as rock reaction force, laser point cloud, and real-time video obtained from the robotic excavation system; rock mass failure monitoring data such as stress, strain, acoustic emission, and ultrasound obtained from the multi-element monitoring system; injection and production temperature and pressure, and fracture acoustic emission monitoring results data obtained from the geothermal development system; flow field data such as fluid velocity and rheology obtained from the filling system, as well as mechanical behavior data of the filling body such as pore water pressure, total soil pressure, strain, temperature, electrical conductivity, and three-dimensional fractures; surrounding rock temperature, airflow temperature and humidity, dust pollutant concentration, and operating status data of main fan, local fan, and damper obtained from the ventilation system. To fully utilize heterogeneous data from various systems, the experimental big data storage and fusion analysis module stores multi-source heterogeneous experimental big data collected from various systems of the ultra-large deep engineering disaster physical simulation experimental facility into a cloud platform distributed file system, improving the read and write performance of experimental big data. It preprocesses the experimental big data, employing a dynamically expandable semantic template library to perform semantic mapping between data sources from various systems of the ultra-large deep engineering disaster physical simulation experimental facility, achieving semantic fusion of multi-source heterogeneous experimental big data. It also provides a unified computational model for batch and stream fusion processing, such as... Figure 2 As shown, this method enables batch computation and real-time streaming computation of big data from physical simulation experiments of ultra-large-scale deep engineering disasters. It achieves efficient computation of big data from physical simulation experiments by unifying the expression modeling and integrating batch and streaming data models, transformation models, and action models. The unified computation process of batch and streaming fusion mainly includes the following steps:

[0036] S1: The multi-source heterogeneous experimental data collected by various systems of the differential deep engineering disaster physical simulation facility are modeled into a data stream, and a finite set is extracted as its special cases to complete the data model unification;

[0037] S2: It adopts a unified programming interface to call the calculation process from the input dataset to the output dataset, provides unified underlying execution logic, and completes the unification of transformation models;

[0038] S3: Abstracts the computational operations in the experiment and analysis process into pipelines that encapsulate logic such as filtering, cleaning, and merging, enabling batch and stream-indiscriminate computation of big data in experiments and achieving unified action models;

[0039] S4: Import the dataset required for computation using a predefined data source format to complete the initialization of the computation node;

[0040] S5: Notify the computing system to distribute data, process the acquired streaming data in real time, execute batch data calculation instructions, and finally complete the final calculation after batch-stream fusion.

[0041] The multi-task joint planning module is used to formulate efficient task plans for ultra-large-scale deep engineering disaster physical simulation experiments. To broaden the application scope of the ultra-large-scale deep engineering disaster physical simulation facility, the module designs different task plans for different engineering activities, applicable to projects such as deep-buried tunnel and underground cavern excavation, deep metal mining and oil and gas extraction, and deep geothermal development. First, based on the overall objectives and content of the ultra-large-scale deep engineering disaster physical simulation experiment, the task definition is completed. Then, the overall physical simulation experiment task is intelligently decomposed into sub-tasks on each system. Next, through a data- and knowledge-driven intelligent optimization decision-making method, sub-task planning based on joint design optimization is performed, and the dependencies between sub-tasks are determined. Finally, based on the sub-task planning and dependencies, the control logic and control sequence of the sub-tasks are generated, completing the sub-task allocation for each system.

[0042] The intelligent dynamic collaborative control module generates a collaborative control model to coordinate and control the real-time field processes of the ultra-large deep engineering disaster physical simulation test facility. It transforms the control logic and timing from the task plan generated by the multi-task joint design optimization module into control commands for the underlying controllers of each system in the ultra-large deep engineering disaster physical simulation test. These control commands are then issued to and executed by each system. During control command execution, it acquires real-time system data and sub-task execution status from multiple systems and performs intelligent collaborative control optimization analysis on the real-time data and task execution status. It compares and analyzes the real-time performance indicators of each task after control command execution with the target performance indicators, and then optimizes the efficiency of sub-task execution based on the dependencies between different sub-tasks. It iteratively optimizes the control logic and control commands to continuously improve control accuracy during the physical simulation test and achieve globally optimal joint execution efficiency for multiple tasks. The module generates a collaborative control model through intelligent collaborative control optimization technology, performs adaptive error control on each sub-task, and ensures the achievement of collaborative goals. It also dynamically allocates sub-tasks based on the execution status and results returned by each system.

[0043] The autonomous optimization module of the collaborative control model, such as Figure 3As shown, this method is used to autonomously learn control experience from multiple historical experimental big data sets, achieving continuous optimization of the collaborative control model. Based on the massive historical experimental big data provided by the experimental big data storage and fusion analysis module, as well as the operation logs and other record files of the ultra-large deep engineering disaster physical simulation test facility, resource consumption, running time, and other characteristics are determined as operational status evaluation indicators. The correlation between all operating parameters and control parameters and evaluation indicators is calculated, and the main limiting factors of the execution efficiency of ultra-large deep engineering disaster physical simulation test tasks are analyzed. A data-driven deep learning model is used to analyze the experimental process and results caused by different parameters, to mine the potential patterns in prior knowledge and experimental big data, and to use intelligent decision-making algorithms to determine the optimal operating parameters and control parameters under different experimental task settings, autonomously optimizing the operating parameters and collaborative control model parameters of similar tasks.

[0044] The multi-task intelligent execution fault-tolerant module ensures the availability of the ultra-large deep engineering disaster physical simulation test facility in the event of communication failures and provides intelligent fault tolerance for test task execution anomalies and errors. The module employs a communication redundancy design based on flexible switching between primary and secondary channels. When the primary communication channel of any system fails, a backup communication channel is activated to ensure uninterrupted operation of the physical simulation test. During the execution of the test sub-tasks assigned to each system, their status is monitored in real time. When an anomaly or error occurs in a sub-task, anomaly capture is performed. Through intelligent analysis of log information, the cause of the anomaly or error is determined, thereby automatically correcting the overall task and sub-tasks to prevent irreparable systemic and catastrophic errors in the ultra-large deep engineering disaster physical simulation test facility.

[0045] The multi-task integrated display module showcases detailed numerical values ​​and overall development trends of deep engineering disaster physical simulation test data from various systems, or provides a visual overview of multiple systems on the same page. It supports multi-task integrated information display of equipment operation information and health status, test execution progress analysis results, test process monitoring information, and intelligent analysis and calculation results of test big data for each system in deep engineering disaster physical simulation tests. It can display detailed numerical values ​​and overall development trends of deep engineering disaster physical simulation test data from various systems, or provide a visual overview of multiple systems on the same page, facilitating researchers' overall situation control and detailed in-depth research of physical simulation tests. Furthermore, this module can achieve integrated statistical display of specific indicators such as temperature, humidity, and stress. Display methods support two-dimensional multi-dimensional data charts such as line graphs, curves, bar charts, pie charts, or tables, multimedia data, three-dimensional rendered models, multimedia information such as images and videos, and multi-modal integrated display of two-dimensional model renderings.

[0046] In summary, this invention constructs an intelligent collaborative control system for multi-engineering activities in the physical simulation of disasters in ultra-large-scale deep engineering projects. Facing various technological processes and disaster physical simulation experiments in deep engineering, it achieves intelligent dynamic collaborative control for multi-task joint planning and execution. Through the collection, fusion, batch-stream calculation and analysis, integrated visualization, and autonomous optimization of operating parameters and collaborative control model parameters for similar tasks, intelligent collaborative control of various systems in the ultra-large-scale deep engineering disaster physical simulation facility is achieved. This ensures that experimental tasks can be executed efficiently according to plan and achieve the expected experimental results.

[0047] Finally, 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 them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. An intelligent collaborative control system for physical simulation of disasters in ultra-large-scale deep engineering projects, characterized in that: The system comprises a cross-protocol transparent high-efficiency communication architecture, a test big data storage and fusion analysis module, a multi-task joint planning module, an intelligent dynamic cooperative control module, and a cooperative control model autonomous optimization module.

2. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 1, characterized in that: The system further comprises a multi-task intelligent execution fault-tolerant module and a multi-task integrated display module.

3. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 2, characterized in that: The cross-protocol transparent high-efficiency communication architecture collects and sends test process and result data of each component system of the super-large deep engineering disaster physical simulation facility in real time, and obtains test task execution state and result of each system.

4. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 3, characterized in that: The test big data storage and fusion analysis module stores multi-source and heterogeneous test big data collected from each system of the super-large deep engineering disaster physical simulation test facility into a cloud platform distributed file system. The test big data storage and fusion analysis module stores multi-source and heterogeneous test big data collected from each system of the super-large deep engineering disaster physical simulation test facility into a cloud platform distributed file system. The test big data storage and fusion analysis module stores multi-source and heterogeneous test big data collected from each system of the super-large deep engineering disaster physical simulation test facility into a cloud platform distributed file system.

5. The intelligent collaborative general control system for ultra-large physical simulation of deep engineering disasters according to claim 4, characterized in that: The multi-task joint planning module completes task definition according to the overall goal and content of the super-large deep engineering disaster physical simulation test task, intelligently decomposes the physical simulation test overall task into sub-tasks on each system, and determines the dependency relationship between the sub-tasks through the intelligent optimization decision method driven by data and knowledge, and plans the sub-tasks based on joint design optimization. According to the sub-task planning and dependency relationship, the control logic and control timing of the sub-tasks are generated, and the sub-tasks of each system are allocated.

6. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 5, characterized in that: The intelligent dynamic collaborative control module converts the control logic and control timing in the task plan generated by the multi-task joint design optimization module into control instructions of the bottom controllers of each system of the super-large deep engineering disaster physical simulation test, and the control instructions are sent to each system and executed; a collaborative control model is generated through intelligent collaborative control optimization technology to perform adaptive error control on each sub-task and ensure the realization of the collaborative goal; and the execution state and results returned by each system are used to dynamically allocate the sub-tasks.

7. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 6, characterized in that: The collaborative control model autonomous optimization module analyzes the test process and results based on the massive historical test big data provided by the test big data storage and fusion analysis module, analyzes the limiting factors of the execution efficiency of the super-large deep engineering disaster physical simulation test task, and autonomously optimizes the operation parameters and collaborative control model parameters of the same type of task.

8. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 7, characterized in that: The multi-task intelligent execution fault tolerance module adopts a communication redundancy design based on flexible switching of primary and secondary channels to provide an availability protection mechanism when communication fails, avoiding the impact of communication failure on the operation of the physical simulation test; when an abnormality or error occurs in the execution of the test sub-tasks allocated by each system, the abnormality is captured, the cause of the abnormality or error is judged through intelligent analysis of log information, and the overall task and sub-tasks are automatically corrected to avoid irreversible systematic and catastrophic errors in the super-large deep engineering disaster physical simulation test facility.

9. The intelligent collaborative general control system for super-large deep engineering disaster physical simulation according to claim 8, characterized in that: The multi-task integrated display module supports the multi-task integrated information of the equipment operation information and health status of each system of the deep engineering disaster physical simulation test, the test execution process analysis results, the test process monitoring information, and the intelligent analysis and calculation results of the test big data. The display mode supports multi-modal integrated display of multi-dimensional data charts, multimedia data, and three-dimensional rendering models.

Images