Intelligent control system for shield construction

Abstract

The invention discloses an intelligent control system for shield construction, which is characterized in that an MATLAB program is installed in an industrial personal computer, a compiled deep learning intelligent control model PSO-GA-D-FNN combined neural network model is imported into the MATLAB program, and the MATLAB program is connected with a PLC (Programmable Logic Controller) of a shield machine control room. The system can read the control parameters of the shield tunneling machine at the current moment in real time, input the control parameters to an MATLAB program in the industrial personal computer for calculation, and output the predicted value of the pressure of the shield soil bin at the next moment and the propelling speed, the total thrust and the rotating speed of the spiral conveyor required for achieving the pressure of the target soil bin, so that intelligent control over the pressure of the shield soil bin is achieved. The method has the advantages that the intelligent level of shield construction is improved, manual intervention is reduced, unmanned control of the shield tunneling machine and real-time intelligent prediction of parameters are achieved, and meanwhile the refinement level of construction is improved.

Description

Technical Field

[0001] The invention relates to the technical field of shield construction, and in particular to an intelligent control system for shield construction. Background Art

[0002] As a key underground engineering technology, shield construction is widely used in urban subway, tunnel and other construction projects. Effectively controlling the movement and construction parameters of the shield machine is the core issue to ensure construction efficiency and safety. Traditional control methods mostly rely on manual experience and simple algorithms, and often face challenges such as slow response speed and poor adaptability. This makes the research on intelligent control and direction adjustment methods of shield machines increasingly important.

[0003] Patent CN117685001A is based on PID control, which is a classic control strategy. It is widely used in various types of engineering equipment because of its simple structure and easy implementation. In the intelligent direction adjustment system of the shield machine based on PID control, the system can dynamically adjust the propulsion direction and speed of the shield machine through the feedback of real-time sensor data, significantly improving the accuracy and safety of construction. However, PID control is often not flexible enough when dealing with complex geological conditions; PID control relies on set gain parameters and is difficult to adjust adaptively, resulting in unsatisfactory performance in dynamic environments and difficulty in meeting the requirements of real-time regulation. In addition, PID control is usually applicable to linear systems. For nonlinear and complex systems, the effect of PID control may be limited and cannot effectively handle various emergencies; although PID control can be adjusted automatically, it still relies on manual setting of parameters, which increases the complexity of human-computer interaction and reduces the automation level of the system.

[0004] Patent CN117846629A model predictive control is a more advanced control method that can predict future system behavior by establishing a dynamic model and optimize the control strategy accordingly. In the shield intelligent adjustment system based on model predictive control, the shield machine's posture data, excavation parameters, geological parameters and geometric parameters are collected in real time, and the pressure signals of each partition propulsion cylinder are dynamically adjusted through the optimization algorithm to effectively respond to sudden geological changes. Its advantage is that it can combine real-time data for intelligent prediction, which improves the control accuracy and response speed of the shield machine. However, model predictive control (MPC) relies on an accurate system model. If there is a deviation between the model and the actual dynamic behavior of the shield machine, it may lead to poor control effect; MPC usually needs to perform optimization calculations in each control cycle, which will increase the computational burden, especially in real-time control. It may cause delays; and MPC has poor adaptability. When facing a changing environment and working conditions, the update and adjustment of the model may lag behind, thus affecting the real-time performance and safety of the shield machine. Summary of the invention

[0005] The present invention aims to overcome the deficiencies of the prior art and provide an intelligent control system for shield construction, which can predict the key parameters in the shield construction process in real time to achieve intelligent control, significantly improve construction efficiency and safety, and ensure efficient, safe and stable operation of the construction process.

[0006] The problems solved by the present invention include:

[0007] (1) Reduce manual dependence and improve the level of intelligence: Parameter adjustment in traditional shield construction relies on manual experience, which has problems of subjectivity and lack of real-time performance.

[0008] (2) Real-time prediction enables intelligent control and enhanced construction safety: The pressure change in the soil bin is closely related to geological conditions, and traditional methods are difficult to respond to sudden geological conditions in a timely manner.

[0009] (3) Optimize construction efficiency and reduce construction risks: After the introduction of the intelligent control model, the system can automatically optimize key parameters and improve excavation efficiency.

[0010] (4) Coping with complex geological conditions and improving construction capabilities: The deep learning model enhances the system's ability to adapt to complex geology and achieves refined management.

[0011] (5) Intelligent transformation of old shield machines: The intelligent control module is connected to the PLC in the shield machine control room and is suitable for the transformation of old shield machines.

[0012] An intelligent control system for shield construction is developed. By installing the MATLAB program inside the industrial computer, the PSO-GA-D-FNN combined neural network model of deep learning intelligent control model is imported into the MATLAB program and connected with the PLC in the shield machine control room:

[0013] The system can read the current shield machine control parameters in real time and input them into the MATLAB program in the industrial computer for calculation:

[0014] Through the calculation results, the predicted value of the shield soil bin pressure at the next moment is output, as well as the propulsion speed, total thrust and screw conveyor speed required to achieve the target soil bin pressure, thereby realizing the advanced prediction and intelligent control of the shield soil bin pressure:

[0015] The system comprises:

[0016] (1) PLC control unit: used for data collection and transmission during the advancement of the shield machine;

[0017] (2) MATLAB program processing unit: calculates the collected shield construction parameters, predicts the parameters at the next moment based on the calculation results and existing construction data, and then outputs the control parameters at the next moment;

[0018] (3) Wireless communication module: It uses industrial-grade wireless transmission protocols to ensure the stability and real-time performance of data transmission. It is used to realize data transmission between the MATLAB program processing unit, the PLC control unit, and the shield actuator, ensuring real-time data sharing and collaborative work.

[0019] (4) Industrial computer: connected to the control system, as the core control device of the system, coordinates the work between modules to ensure the efficient operation of the system:

[0020] (5) Shield machine actuator: including propulsion system, screw conveyor, cutter head and other components, responsible for executing the control instructions received from the PLC, adjusting the propulsion speed, total thrust and screw conveyor speed, etc.

[0021] Furthermore, the PLC control unit includes: PLC collects various sensor data on the shield machine, such as cutter head torque, propulsion speed, support pressure, etc., and transmits the data to the industrial computer; PLC receives the control instructions output by the MATLAB program processing unit and passes it to the shield machine actuator.

[0022] Furthermore, the MATLAB program processing unit includes:

[0023] Step 1) Install the MATLAB program in the industrial computer to execute the deep learning model PSO-GA-D-FNN combined neural network model;

[0024] Step 2) Calculate and predict the shield construction parameters collected and transmitted by the PLC control unit, and output the predicted parameter values ​​as the control parameters at the next moment.

[0025] Furthermore, data transmission between various units of the system is based on standardized data interface protocols to ensure compatibility between modules and accuracy of data.

[0026] Furthermore, the communication between the MATLAB program processing unit and the PLC adopts the OPC (OLE for Process Control) protocol to achieve seamless connection and sharing of data.

[0027] Furthermore, the system adopts a modular design based on a distributed architecture, so that the intelligent prediction module and control module can be distributed in various key parts of the shield machine. This design enhances the flexibility and reliability of the system and effectively reduces the risk of single point failure, ensuring the stability and continuity of the construction process. For example, when a local module fails, other modules can still operate normally to ensure that the construction is not affected.

[0028] Furthermore, the terminal device of this system is an industrial tablet computer, which has the characteristics of earthquake resistance and waterproofness, ensuring stable operation in complex construction environments and improving the reliability of data collection and monitoring.

[0029] Furthermore, the system provides a variety of data analysis tools, including statistical analysis and trend forecasting, to help managers make scientific construction decisions.

[0030] Furthermore, the system is designed with a fault diagnosis function to monitor the operating status of each module in real time and issue an alarm in case of abnormalities to ensure construction safety.

[0031] As an improvement, by connecting with the shield construction monitoring platform, the system can upload real-time data to the cloud server and support remote monitoring functions. Managers can view the construction status at any time through mobile devices for viewing and analysis, realizing visual management of the construction process and data-driven decision support. The cloud server can realize real-time synchronization of multi-terminal data, ensure data consistency and sharing between different workstations, and improve overall construction management efficiency.

[0032] In the specific implementation process, the system first collects various sensor data of the shield machine through the PLC control unit. The data is transmitted to the MATLAB program processing unit in the industrial computer in real time through the wireless communication module, which uses the deep learning model to analyze and output the corresponding control parameters. At the same time, these processing results are transmitted to the PLC control unit through the wireless communication module, and the PLC control unit guides the shield machine actuator to achieve intelligent control, so as to quickly adjust the working status of each actuator to ensure the flexibility and efficiency of construction.

[0033] The present invention uses real-time prediction and analysis to intelligently adjust shield construction parameters and achieve unmanned control. The system monitors various parameters in real time during the construction process, effectively reducing manual intervention, and significantly improving construction safety and efficiency, especially under complex geological conditions. Unmanned control not only reduces the risk of human error, but also can quickly respond to emergencies and ensure the smooth progress of construction.

[0034] The present invention has efficient data transmission and sharing capabilities. Through the data sharing characteristics of the MATLAB dynamic link library, each module can achieve high-speed data transmission. The wireless communication module ensures that each module shares data in real time, thereby enhancing the collaborative efficiency of the system. This design not only reduces transmission delays, but also improves the accuracy and consistency of data, providing a guarantee for real-time monitoring.

[0035] The technical advantages of the present invention are embodied in many aspects:

[0036] (1) Combination of real-time and intelligence: The system uses MATLAB's powerful data processing capabilities and the PSO-GA-D-FNN combined neural network model to achieve real-time data collection, analysis, and prediction.

[0037] (2) System flexibility and stability: The distributed architecture design improves system flexibility and can flexibly adjust the operating status of each module according to specific construction needs.

[0038] (3) Reduce construction risks and improve safety: Unmanned intelligent control significantly reduces manual intervention in the construction process, especially under complex or dangerous geological conditions.

[0039] (4) The module is easy to integrate and expand: The module design based on MATLAB dynamic link library facilitates integration with the existing shield control system and reduces the difficulty of technical implementation.

[0040] (5) Improve construction efficiency: The intelligent system can automatically optimize key parameters, improve excavation efficiency, and reduce the risk of human misjudgment.

[0041] (6) Ability to cope with complex geological conditions: The present invention enhances the system's ability to adapt to complex geological conditions and achieves refined management of the construction process.

[0042] (7) Intelligent transformation of old shield machines: The intelligent control module of the present invention can be connected to the PLC of the shield machine control room and is suitable for the intelligent transformation of old shield machines.

[0043] Beneficial effects of an intelligent control system for shield construction: After adopting the above technical solution, the present invention has the following effects compared with the prior art:

[0044] (1) Through the intelligent control module, real-time prediction and control of key parameters of shield construction can be achieved, which significantly improves the level of intelligent construction, reduces manual dependence, and ensures efficiency and safety.

[0045] (2) The deep learning model quickly responds to geological changes during the construction process, adjusts the advancement speed and soil bin pressure in real time, enhances safety, and effectively responds to emergencies under complex geological conditions.

[0046] (3) Modular design enhances system flexibility and reliability. Modules can be distributed in different parts of the shield machine to reduce the risk of single point failure and ensure construction continuity and stability.

[0047] (IV) The system has efficient data transmission capabilities, and can achieve rapid data sharing between modules through wireless communication, reduce transmission delays, improve data accuracy and consistency, and provide guarantees for real-time monitoring.

[0048] (V) The unmanned control mode reduces the risk of human operation, ensures smooth construction in complex or dangerous environments, and improves overall efficiency.

[0049] (VI) Self-learning ability optimizes control strategies based on historical data, improves parameter prediction accuracy and construction efficiency, and provides scientific decision-making support for management personnel.

[0050] (VII) The system supports remote monitoring, and managers can check the construction status at any time through mobile devices, make timely adjustments and responses, and enhance management flexibility and real-time invention content. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is the intelligent control flow chart of shield soil bin pressure. DETAILED DESCRIPTION

[0052] The following is combined with Figure 1 The present invention is further described in detail with the following embodiments:

[0053] Example 1

[0054] like Figure 1 , which is a flowchart of intelligent control of shield soil bin pressure. This flowchart shows the multi-parameter dynamic control process of shield construction soil bin pressure based on the DWT-PAO-GA-D-FNN hybrid deep learning model. First, after the model is built, it is integrated with the industrial computer and connected to the shield machine control system PLC to achieve three-level continuous control of soil bin pressure. During the process, the screw conveyor speed parameter n(t), total thrust parameter F(t), and propulsion speed parameter v(t) are dynamically adjusted to achieve the target soil bin pressure P 0 For reference, the system determines the deviation between the actual pressure and the target value step by step. If a deviation exists, the relevant parameters are adjusted in turn. When all parameters meet the target pressure conditions, the corresponding control parameters at the next moment are output to the shield control program, ultimately achieving accurate, multi-dimensional real-time regulation of the soil bin pressure to ensure construction safety and efficiency.

[0055] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. An intelligent control system for shield construction, characterized in that: By installing the MATLAB program inside the industrial computer, the prepared deep learning intelligent control model PSO-GA-D-FNN combined neural network model is imported into the MATLAB program and connected with the PLC in the shield machine control room: The system reads the current shield machine control parameters in real time and inputs them into the MATLAB program in the industrial computer for calculation: Based on the calculation results, the predicted value of the shield soil bin pressure at the next moment is output, as well as the propulsion speed, total thrust and screw conveyor speed required to achieve the target soil bin pressure. The PLC control unit is used to guide the shield machine actuator to achieve intelligent control. The system comprises: (1) PLC control unit: used for data collection and transmission during the advancement of the shield machine; (2) MATLAB program processing unit: calculates the collected shield construction parameters, predicts the parameters at the next moment based on the calculation results and existing construction data, and then outputs the control parameters at the next moment; (3) Wireless communication module: It uses industrial-grade wireless transmission protocols to ensure the stability and real-time performance of data transmission. It is used to realize data transmission between the MATLAB program processing unit, the PLC control unit, and the shield actuator, ensuring real-time data sharing and collaborative work. (4) Industrial computer: connected to the control system, as the core control device of the system, coordinates the work between modules to ensure the efficient operation of the system: (5) Shield machine actuator: including propulsion system, screw conveyor, cutter head and other components, responsible for executing the control instructions received from the PLC and adjusting the propulsion speed, total thrust and screw conveyor speed.

2. The intelligent control system for shield construction according to claim 1 is characterized in that: The PLC control unit comprises: The PLC collects data from various sensors on the shield machine, including cutter head torque, propulsion speed, and support pressure, and transmits the data to the industrial computer; The PLC receives the control instructions output by the MATLAB program processing unit and transmits them to the shield machine actuator.

3. The intelligent control system for shield construction according to claim 1 is characterized in that: Described MATLAB program processing unit comprises: Step 1) Install the MATLAB program in the industrial computer to execute the deep learning model PSO-GA-D-FNN combined neural network model; Step 2) Calculate and predict the shield construction parameters collected and transmitted by the PLC control unit, and output the predicted parameter values ​​as the control parameters at the next moment.

4. The intelligent control system for shield construction according to claims 1-3 is characterized in that: Data transmission between system units is based on standardized data interface protocols.

5. The intelligent control system for shield construction according to claims 1-4 is characterized in that: The communication between MATLAB program processing unit and PLC adopts OPC protocol.

6. The intelligent control system for shield construction according to claim 1 is characterized in that: This system adopts a modular design based on a distributed architecture, which enables the intelligent prediction module and control module to be distributed in various key parts of the shield machine.

7. The intelligent control system for shield construction according to claim 1 is characterized in that: The working process of the intelligent control system is as follows: the system is based on the DWT-PAO-GA-D-FNN hybrid deep learning model. After the model is built, it is integrated through the industrial computer and connected to the shield machine control system PLC to realize three-level continuous control of the soil bin pressure, and dynamically adjust the screw conveyor speed parameter n(t), the total thrust parameter F(t), and the propulsion speed parameter v(t). With the target soil bin pressure P0 as a reference, the system judges the deviation between the actual pressure and the target value step by step. If a deviation exists, the relevant parameters are adjusted in turn; when all parameters meet the target pressure conditions, the control parameters corresponding to the next moment are output to the shield control program.

8. The intelligent control system for shield construction according to claim 1 is characterized in that: The terminal device of this system is an industrial tablet computer.

9. The intelligent control system for shield construction according to claim 1, characterized in that: The system is designed with a fault diagnosis function to monitor the operating status of each module in real time and issue an alarm when an abnormality occurs.

10. The intelligent control system for shield construction according to claim 1, characterized in that: By connecting with the shield construction monitoring platform, the system can upload real-time data to the cloud server and support remote monitoring functions.

Images