A pipe network engineering construction period intelligent remote monitoring method and system

Abstract

The application provides a kind of pipe network engineering construction period intelligent remote monitoring method and system, related to underground space engineering safety technical field.The application obtains the transient dynamics parameters such as pipe network interface shear displacement, displacement rate and soil pore water pressure around pipe, and constructs system state vector and control vector by combining with construction machinery and grouting system operation boundary parameter, accurately reflects real-time dynamics state of pipe network;With pipe-soil coupling dynamics state evolution equation as constraint, with the minimum pipe network state deviation and control energy consumption as target to construct Hamilton function, and based on the pontryagin principle to solve the optimal control solution, realize the rapid deduction and global optimal control decision of pipe network deformation trend;Finally, the synchronous control instruction of mechanical frequency reduction and grouting pressurization is generated, which can complete active collaborative intervention in a very short time when high-frequency shear impact occurs, inhibit the transient shear deformation of pipe network interface, avoid interface shear separation damage, and reduce control energy consumption.

Description

Technical Field

[0001] This invention relates to the field of underground space engineering safety technology, and in particular to an intelligent remote monitoring method and system for pipeline engineering construction. Background Technology

[0002] During the construction of urban underground pipeline networks, the operation of surface construction machinery generates high-frequency vibrations and impacts. These vibrations are transmitted through the soil to the underground pipeline network, easily causing instantaneous and severe shearing forces at the pipeline interfaces. Existing pipeline monitoring systems mostly adopt static displacement threshold alarm methods, which only trigger alarms and intervention actions after the pipeline displacement reaches a preset threshold, constituting a passive and delayed response mechanism.

[0003] When faced with high-frequency shear impact conditions, the deformation of pipeline interfaces has transient and rapid evolution characteristics. Traditional static threshold monitoring methods have defects such as data processing lag, slow alarm issuance, and untimely control response. They cannot achieve rapid prediction and active intervention within the short time window of impact occurrence, which can easily lead to irreversible shear separation damage of pipeline interfaces, affecting the safety of pipeline structure and normal construction. Summary of the Invention

[0004] This invention provides an intelligent remote monitoring method and system for pipeline engineering construction, which solves the technical problem of underground pipelines being susceptible to shear damage during construction.

[0005] In a first aspect, the present invention provides an intelligent remote monitoring method for pipeline engineering construction. The method includes: acquiring transient dynamic parameters of the underground pipeline network during construction, as well as operational boundary parameters of the surface construction machinery and the underground targeted grouting system; the transient dynamic parameters include shear displacement, displacement rate, and pore water pressure of the surrounding soil at the pipeline network interface; constructing a system state vector and a control vector based on the transient dynamic parameters and operational boundary parameters; constructing a Hamiltonian function with the pipeline-soil coupling dynamic state evolution equation followed by the system state vector and control vector as constraints, and minimizing pipeline state deviation and control energy consumption as objectives; solving for the optimal control solution based on the Hamiltonian function and the Pontryagin principle; and generating synchronous control commands based on the optimal control solution, the synchronous control commands including mechanical frequency reduction commands for the surface construction machinery and coordinated grouting and pressurization commands for the underground targeted grouting system.

[0006] In a first aspect, the present invention provides an intelligent remote monitoring device for pipeline engineering construction. The device includes a communication unit and a processing unit. The communication unit is used to acquire transient dynamic parameters of the underground pipeline network during construction, as well as the operational boundary parameters of the surface construction machinery and the underground targeted grouting system. The transient dynamic parameters include shear displacement, displacement rate, and pore water pressure of the surrounding soil at the pipeline network interface. The processing unit is used to construct a system state vector and a control vector based on the transient dynamic parameters and operational boundary parameters. Using the pipeline-soil coupling dynamic state evolution equation followed by the system state vector and control vector as constraints, and aiming to minimize pipeline state deviation and control energy consumption, a Hamiltonian function is constructed. Based on the Hamiltonian function and combined with Pontryagin's principle, the optimal control solution is solved. Based on the optimal control solution, synchronous control commands are generated, including mechanical frequency reduction commands for the surface construction machinery and coordinated grouting and pressurization commands for the underground targeted grouting system.

[0007] Thirdly, embodiments of the present invention provide an intelligent remote monitoring system for pipeline engineering construction. The remote monitoring system includes an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method as described in the first aspect and any possible implementation thereof.

[0008] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method as described in the first aspect and any possible implementation thereof.

[0009] This invention provides an intelligent remote monitoring method and system for pipeline network construction. The invention acquires transient dynamic parameters such as shear displacement, displacement rate, and pore water pressure in the surrounding soil at real time, and constructs system state and control vectors by combining these parameters with the boundary parameters of the construction machinery and grouting system. This accurately reflects the real-time dynamic state of the pipeline network. A Hamiltonian function is constructed using the pipe-soil coupled dynamic state evolution equation as a constraint and minimizing pipeline state deviation and control energy consumption as the objective. The optimal control solution is then solved based on the Pontryagin principle, enabling rapid deduction of pipeline deformation trends and globally optimal control decisions. Finally, synchronous control commands for mechanical frequency reduction and grouting pressurization are generated, allowing for proactive and coordinated intervention within a very short time after high-frequency shear impact. This suppresses transient shear deformation at the pipeline interface, prevents interface shear separation and damage, reduces control energy consumption, and improves the monitoring response speed and safety protection capabilities during pipeline network construction. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of the structure of an intelligent remote monitoring system for pipeline engineering construction provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating an intelligent remote monitoring method for pipeline engineering construction provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0013] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0014] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0015] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0016] As described in the background section, in the construction scenarios of pipeline engineering in complex urban geological environments, there is often a situation where heavy-duty surface machinery and underground concealed pipelines operate in parallel. In this case, the transient high-frequency excitation force generated by the surface machinery can penetrate the heterogeneous soil layer and cause severe transient dynamic impact on the flexible socket interfaces of adjacent pipe sections of the underground pipeline. The prominent technical problem in this typical application scenario is that most existing monitoring systems rely on passive hysteresis alarm mechanisms based on static displacement thresholds. Faced with instantaneous high-frequency shear impacts, they cannot accurately capture the dynamic evolution trend of pipe-soil coupling within a very short time window. Furthermore, due to the lack of rigorous functional variational mathematical derivation at the underlying level, the system cannot solve for the globally optimal control quantity that can both curb pipeline deformation and reduce energy consumption costs in real time. This results in the frequency reduction action of surface construction machinery and the active pressurization action of underground targeted grouting system being in a state of mutual disconnection and blind response. It is difficult to achieve precise coordinated intervention of multiple devices across space. It is very easy for irreversible shear separation damage to occur at the pipeline interface due to action lag or lack of theoretical optimal guidance, or unnecessary project stagnation due to excessive intervention.

[0017] To solve the above problems, such as Figure 1 As shown, the present invention provides an intelligent remote monitoring system for pipeline engineering construction. The system includes a transient feature multi-dimensional perception module, a control variable mapping definition module, a dynamic evolution space modeling module, an objective functional and Hamiltonian construction module, a Pontryagin extreme value solution module, and a multi-field collaborative intervention driving module.

[0018] The transient feature multidimensional sensing module is used to acquire the shear displacement, displacement rate and pore water pressure of the pipeline interface and construct the system state vector. As the underlying data acquisition hub, it directly acquires the deformation of the pipeline interface and the stress parameters around the pipe and tensors them to generate the system state vector, thereby establishing the initial physical boundary for dynamic deduction.

[0019] The control variable mapping definition module is used to define control vectors that include mechanical frequency reduction components and grouting pressure components; it clarifies the execution domain of surface machinery and underground grouting intervention actions in the mathematical dimension and outputs standardized control vectors.

[0020] The dynamic evolution space modeling module is connected to the transient feature multidimensional perception module and the control variable mapping definition module, respectively. It is used to receive the system state vector and control vector, introduce excitation force disturbance, and construct the pipe-soil coupled dynamic state evolution equation. It receives the above two sets of vector parameters in series, adds the excitation force disturbance data measured in the field, and establishes the pipe-soil coupled dynamic state evolution equation that characterizes the mutual constraint relationship between the pipe network and the surrounding soil.

[0021] The objective functional and Hamiltonian construction module is connected to the dynamic evolution space modeling module. It is used to construct the objective functional and Hamiltonian function by combining the costate vector and the weight matrix. Taking the state evolution equation as the core constraint, and combining the weight matrix and costate vector corresponding to various engineering deviation indicators to set the comprehensive cost evaluation benchmark, the Hamiltonian function is derived.

[0022] The Pontryagin extreme value solution module, connected to the objective functional and Hamiltonian construction module, is used to solve costate differential equations. It calculates the optimal control solution by setting the partial derivative of the Hamiltonian function with respect to the control vector to zero. Based on the stationary point equation optimization logic, it performs partial derivative calculations on the Hamiltonian function to solve the costate differential equations and derives the optimal control solution within a limited algebraic space.

[0023] The multi-field collaborative intervention driving module, connected to the Pontryagin extreme value calculation module, is used to convert the optimal control solution into commands to drive field equipment and feed back the physical state to the transient feature multi-dimensional sensing module. It is responsible for inversely converting the mathematical optimal control solution into underlying hardware communication commands, triggering synchronized physical actions between surface construction machinery and the underground targeted grouting system. The new round of physical states generated by the intervention is then captured by the front-end sensing elements and enters the next iteration cycle.

[0024] This invention establishes a functional extremum solution mechanism by deeply integrating the Pontryagin maximum principle into the bottom layer of the monitoring system. It uses the pipe-soil coupling dynamic state evolution equation to guide the joint intervention of multiple devices, which improves the traditional technical defects of the traditional remote monitoring platform when facing transient high-frequency excitation force. It relies heavily on passive threshold alarms and cannot coordinate heterogeneous intervention devices in a very short time. This avoids the specific problem of irreversible shearing and detachment damage of the flexible interface of underground pipeline caused by a single surface heavy mechanical vibration.

[0025] based on Figure 1 The remote monitoring system shown is as follows: Figure 2 As shown, this invention provides an intelligent remote monitoring method for pipeline engineering construction. The method includes steps S101-S105.

[0026] S101. Obtain the transient dynamic parameters of the underground pipeline network during the construction of the pipeline project, as well as the operating boundary parameters of the surface construction machinery and the underground targeted grouting system.

[0027] In this embodiment, the transient dynamic parameters include the shear displacement, displacement rate, and pore water pressure of the surrounding soil at the pipe network interface.

[0028] For example, a transient feature multidimensional sensing module is used to acquire the shear displacement, displacement rate and pore water pressure of the pipeline interface and construct the system state vector; Furthermore, the transient feature multidimensional perception module is specifically used to: synchronously acquire axial shear displacement signals, shear displacement rate signals, and pore water pressure signals of the surrounding soil at the pipeline interface under a unified timestamp; perform analog-to-digital conversion and filtering denoising on the axial shear displacement signals, shear displacement rate signals, and pore water pressure signals; extract effective values ​​of physical features; and perform tensor splicing of the extracted effective values ​​of physical features according to a preset dimensional order to generate a system state vector representing the current physical and dynamic equilibrium state.

[0029] S102. Based on transient dynamic parameters and operational boundary parameters, construct the system state vector and control vector.

[0030] As one possible implementation, step S102 can be specifically implemented as steps S1021-S1024.

[0031] S1021. Based on transient dynamic parameters, under a unified timestamp, analog-to-digital conversion and filtering denoising are performed to extract the effective values ​​of the physical characteristics of each parameter.

[0032] For example, at a pipeline construction site, there is a spatial physical isolation between the surface heavy-duty mechanical vibration source and the underground concealed pipeline network. The system synchronously collects signals from all sources under a unified timestamp, with the fundamental purpose of eliminating the time delay differences in the data communication paths of heterogeneous sensors. The time alignment mechanism ensures that all physical variables involved in the subsequent pipe-soil coupled dynamic state evolution equations are at the same absolute time section, preventing the divergence of the Hamiltonian optimal control solution due to multi-channel time sequence misalignment.

[0033] The acquired raw analog signals often contain high-frequency random oscillation noise from construction machinery. The module internally performs analog-to-digital conversion and filtering noise reduction logic to remove the random noise amplitude that exceeds the normal mechanical response frequency band, and extract the effective values ​​of physical characteristics that only reflect the true trend of pipeline interface deformation and soil stress.

[0034] S1022. Based on the effective values ​​of the physical characteristics of each parameter, tensors are spliced ​​according to a preset dimensional order to generate a system state vector representing the real-time dynamic equilibrium state of the pipeline network.

[0035] For example, this invention performs tensor concatenation on the effective values ​​of the physical characteristics after clutter removal, according to the variable placeholder requirements of the higher-order dynamic equations, to generate a system state vector. After tensor concatenation, the underlying discrete scalar sensing data is reconstructed into a standard vector data structure, which is directly used as the mathematical initial boundary for solving the Pontryagin extremum condition. The mathematical model for generating the system state vector is expressed as follows: ; in, Represents at discrete time nodes The output system state vector Representing time nodes The effective value of the extracted axial shear displacement physical characteristics Representing time nodes The extracted effective value of the physical characteristic of shear displacement rate. Representing time nodes The effective values ​​of the physical characteristics of pore water pressure in the soil surrounding the pipe were extracted. The transpose operator represents a vector matrix.

[0036] For example, the complete data input / output interaction process of the module is manifested as a one-way up-dimensional mapping: the on-site physical sensing element inputs discrete multi-channel continuous analog electrical signals to the module; after receiving the analog electrical signals, the main control chip inside the module performs time marking, analog-to-digital conversion, and frequency domain filtering extraction to complete numerical cleaning; finally, the main control chip assembles the cleaned physical scalar values ​​into a column vector format according to the dimension, and outputs a system state vector digital message containing the current physical dynamic equilibrium state to the backend dynamic evolution space modeling module.

[0037] S1023. Analyze the operating boundary parameters of surface construction machinery and underground targeted grouting system, and generate the mechanical frequency reduction component and grouting pressure component respectively.

[0038] S1024. Normalize and map the mechanical frequency reduction component and the grouting pressure component, and combine them in a preset dimension order to obtain the control vector representing the multi-equipment collaborative operation command.

[0039] For example, the control variable mapping definition module is used to define a control vector that includes a mechanical frequency reduction component and a grouting pressure component; Furthermore, the control variable mapping definition module is specifically used to: obtain the mechanical frequency reduction operation boundary parameters of the surface construction machinery and generate the mechanical frequency reduction component; obtain the grouting pressure operation boundary parameters of the underground targeted grouting system and generate the grouting pressure component; perform a normalization mapping operation on the mechanical frequency reduction component and the grouting pressure component, and combine the normalized mechanical frequency reduction component and the grouting pressure component by dimension to generate a control vector that uniformly represents the multi-equipment collaborative operation command.

[0040] Specifically, the vibration frequency of surface construction machinery and the pumping pressure of underground grouting systems belong to completely different physical dimensions. Directly introducing physical parameters with their original dimensions into subsequent dynamic differential equations would result in excessively large differences in the order of magnitude of elements in the calculation matrix, leading to matrix singularities or divergences during the Pontryagin extreme value solution process. This module receives operational boundary parameters from heterogeneous surface and underground equipment as initial input data. After extracting the specific extreme value boundaries, physical unit attributes are removed, and the movement amplitudes of equipment in different dimensions are forcibly compressed into a unified closed interval through mapping calculations.

[0041] The specific normalization mapping operation and control vector generation logic are implemented through the following mathematical model: Let the initial mechanical frequency reduction component of the surface construction machinery be... The obtained mechanical frequency reduction operating boundary parameters include the lower limit of frequency reduction. With frequency reduction limit Let the initial grouting pressure component of the underground targeted grouting system be... The obtained grouting pressure operating boundary parameters include the lower pressure limit. With pressure upper limit .

[0042] The formula for performing the normalization mapping operation on the two components mentioned above is: ; ; in, This represents the normalized mechanical down-frequency component. This represents the normalized grouting pressure component. The above mapping restricts the action commands to be solved to a standard numerical range of zero to one.

[0043] After scalar-level normalization, the program performs algebraic-dimensional tensor combination on the normalized mechanical frequency reduction component and the grouting pressure component to generate a unified control vector representing the multi-equipment collaborative operation command: ; in, This represents the control vector of the final output. This vector serves as an independent variable in the optimization algorithm during subsequent calculations.

[0044] In the data input / output flow chain, this module's front end interfaces with the hardware programmable logic controllers of various underlying devices, collecting the absolute physical operational limits allowed by the devices. Internally, the module utilizes computing power to perform extreme value substitution and tensor concatenation. At the rear end, it sends the generated dimensionless control vector digital matrix to the dynamic evolution space modeling module. Here, the underlying data structure completes the separation and integration of physical boundaries into a pure mathematical search space, ensuring the consistency of the mathematical dimensions in the subsequent control solution process.

[0045] S103. Using the pipe-soil coupling dynamic state evolution equations followed by the system state vector and control vector as constraints, and aiming to minimize the pipe network state deviation and control energy consumption, a Hamiltonian function is constructed.

[0046] As one possible implementation, step S103 can be specifically implemented as steps S1031-S1034.

[0047] S1031. Introducing the excitation force disturbance term generated by surface construction machinery, and combining the tangential stiffness of the pipe-soil interface and the soil permeability coefficient, the system state matrix and control input matrix are calibrated, and a pipe-soil coupled dynamic state evolution equation describing the dynamic change of the system state vector with the control vector and the excitation force disturbance term is constructed.

[0048] For example, the dynamic evolution space modeling module is connected to the transient feature multidimensional perception module and the control variable mapping definition module respectively, and is used to receive the system state vector and control vector, introduce excitation force disturbance, and construct the pipe-soil coupled dynamic state evolution equation. Furthermore, the dynamic evolution space modeling module is specifically used for: analyzing the physical environment in which the system state vector is located, extracting the tangential stiffness parameters and soil permeability coefficient of the pipe-soil interface; mapping the tangential stiffness parameters and soil permeability coefficient to the diagonal and off-diagonal elements of the system state transition matrix, respectively, to complete the construction of the system state transition matrix; and constructing the control input matrix based on the physical influence weights of the mechanical frequency reduction component and the grouting pressure component in the control vector on the system state vector.

[0049] The dynamic evolution space modeling module is also used to collect time-series excitation waveforms generated by surface construction machinery, extract the initial high-frequency excitation force function based on the time-series excitation waveforms, and construct an external disturbance matrix that reflects the waveform transmission attenuation characteristics. The module calculates the product of the system state transition matrix and the system state vector, the product of the control input matrix and the control vector, and the product of the external disturbance matrix and the initial high-frequency excitation force function. The module performs linear algebraic superposition of the product of the system state transition matrix and the system state vector, the product of the control input matrix and the control vector, and the product of the external disturbance matrix and the initial high-frequency excitation force function, and defines the superposition result as the first derivative of the system state vector with respect to time, generating the pipe-soil coupled dynamic state evolution equation.

[0050] Specifically, the dynamic evolution space modeling module in the system mainly undertakes the core computational task of converting discrete physical sensing data into a continuous temporal dynamic model. It maps the underground hidden physical space where the pipeline network is located into a computable linear differential equation, and establishes the future temporal evolution boundary of the pipe-soil interaction under complex excitation conditions.

[0051] After receiving the system state vector and control vector transmitted from the underlying layer, the program initiates the analysis of the physical environment parameters surrounding the pipeline network. The algorithm directly extracts the tangential stiffness parameter and soil permeability coefficient at the pipe-soil interface. The tangential stiffness parameter reflects the frictional slip resistance between the pipe wall and the surrounding soil. The soil permeability coefficient reflects the dissipation rate of pore water pressure. The main control program assigns the tangential stiffness parameter to the main diagonal position of the system state transition matrix and the soil permeability coefficient to the off-diagonal position of the system state transition matrix, thereby assembling and generating the system state transition matrix.

[0052] For the surface mechanical frequency reduction component and the underground grouting pressure component, the algorithm scales the weight values ​​according to the physical influence of the two on the pipeline shear displacement and pore water pressure, and constructs the control input matrix accordingly.

[0053] The dynamic load of heavy-duty construction machinery on the ground is a source of high-frequency, drastic fluctuations. The system's front-end hardware acquires the timing excitation waveform and inputs it into this module. The signal processing unit within the module extracts the initial high-frequency excitation force function characterizing the excitation source based on this waveform. Based on the damping attenuation characteristics of the soil medium, the module constructs an external disturbance matrix reflecting the stress wave propagation attenuation characteristics.

[0054] After constructing all tensors and functions, the processor performs matrix algebraic multiplication and linear superposition operations. The system multiplies the system state transition matrix by the system state vector to obtain the first product. It multiplies the control input matrix by the control vector to obtain the second product. It multiplies the external disturbance matrix by the initial high-frequency excitation force function to obtain the third product. The three products are then algebraically summed. This sum physically represents the rate of change of the system state vector with respect to time, which the algorithm defines as the first derivative of the system state vector with respect to time.

[0055] The final mathematical model of the pipe-soil coupled dynamic state evolution equation is as follows: ; in, This represents the first derivative of the system state vector with respect to time. Represents the system state vector. Represents the control vector. Represents the system state transition matrix. Represents the control input matrix. Represents the external perturbation matrix. This represents the initial high-frequency excitation force function.

[0056] In the data flow chain, the module's input receives state vector messages from the transient feature multidimensional sensing module, dimensionless control vectors from the control variable mapping definition module, and time-series waveforms reported by the field vibration measurement elements. Within the module's computing unit, the data undergoes parameter mapping, matrix instantiation, and linear algebra superposition calculations. The module's output sends the generated ordinary differential equation data packet to the backend Hamiltonian construction module. This equation directly constitutes the absolute physical boundary constraints upon which the subsequent objective functional extremum solution depends.

[0057] S1032. Determine the weight matrix, which includes a process state penalty weight matrix for constraining the deformation deviation of the entire pipeline network, a terminal state penalty weight matrix for constraining the pipeline network safety threshold at the end of the control cycle, and a control energy consumption weight matrix for constraining the energy consumption of equipment actions.

[0058] S1033. Based on the system state vector, control vector, and weight matrix, perform quadratic integral operations within a finite control time window, superimpose terminal state penalty terms, and generate an objective functional with the core objective of minimizing network state deviation and control energy consumption.

[0059] S1034. Introduce a costate vector with the same dimension as the system state vector, and algebraically superimpose the instantaneous integral kernel term of the objective functional, the inner product term of the costate vector transpose and the pipe-soil coupled dynamic state evolution equation to generate a Hamiltonian function for unconstrained extreme value solution.

[0060] For example, the objective functional and Hamiltonian building module is connected to the dynamic evolution space modeling module to construct the objective functional and Hamiltonian function by combining the costate vector and the weight matrix; Furthermore, the objective functional and Hamiltonian construction module is specifically used to: set a finite time window to define the scope of dynamic deduction; initialize the terminal state penalty weight matrix reflecting the objective deviation penalty, the process state penalty weight matrix reflecting the process trajectory deviation penalty, and the control energy consumption weight matrix reflecting the equipment energy consumption penalty; combine the system state vector, control vector, terminal state penalty weight matrix, process state penalty weight matrix, and control energy consumption weight matrix, and perform quadratic combination and continuous integration operations within the finite time window to generate the objective functional characterizing the comprehensive evolution cost of the system.

[0061] The objective functional and Hamiltonian construction module is also used to: set the costate vector as a continuously differentiable vector with the same dimension as the system state vector; calculate the inner product of the transpose of the costate vector and the pipe-soil coupling dynamic state evolution equation; extract the quadratic integral kernel part in the objective functional, and directly algebraically add the quadratic integral kernel part to the calculated inner product to generate the Hamiltonian function.

[0062] Specifically, on-site intervention and control need to meet two mutually constraining engineering indicators. On the one hand, the shear displacement amplitude of pipeline interfaces must be strictly limited to ensure structural safety. On the other hand, the high-intensity operation of surface machinery and underground grouting equipment must be limited to save energy and prevent equipment overload. This module uses mathematical methods to find the optimal balance between these two. The processor establishes a mathematical benchmark for evaluating the comprehensive cost of system evolution by constructing an objective functional. Subsequently, a costate vector is introduced to construct a Hamiltonian function, providing a basic mathematical foundation for subsequent calls to the Pontryagin maximum principle to perform extremum differentiation.

[0063] The mathematical model for constructing the objective functional within the module is as follows: ; in, The objective functional represents the cost of the overall evolution of the system. This represents the start time of the set finite time window. This represents the end time of the set finite time window. This represents the terminal state vector of the system at the termination time. This represents the initial terminal state penalty weight matrix that reflects the penalty for target deviation. This represents the process state vector of the system at the time node of the integral variable. The initialization reflects the process state penalty weight matrix, which reflects the penalty for process trajectory deviation. This represents the control vector at the time node of the integral variable. This represents the initial control energy consumption weight matrix reflecting the energy consumption penalty of the device. (Superscript) The transpose operator represents a matrix. This represents a time integral infinitesimal.

[0064] After establishing the objective functional, the system's computing unit extracts the quadratic integral kernel from it. Internally, the program declares a continuously differentiable vector strictly aligned with the system state vector dimension and defines it as a costate vector. The processor calculates the inner product of the transpose of this costate vector and the soil-pipe coupling dynamics state evolution equation. The quadratic integral kernel is then directly algebraically added to this inner product to generate the Hamiltonian function. The corresponding mathematical model is as follows: ; in, This represents the Hamiltonian function generated during construction. The whole represents the quadratic integral kernel extracted from the objective functional. This represents the introduced continuously differentiable costate vector. The transpose of the costate vector. This represents the pipe-soil coupled dynamic state evolution equation generated by the dynamic evolution space modeling module.

[0065] At the data input / output interaction level, the data input end of this module connects to the output end of the dynamic evolution space modeling module. The processor receives system state vector messages, control vector messages, and soil-pipe coupling dynamic state evolution equation data packets transmitted on the bus. After entering the module, the computing unit performs quadratic combination, continuous integration, and vector inner product calculations according to the preset penalty weight matrix parameters. After completing all matrix algebraic transformations, the data output end of this module connects to the downstream Pontryagin extremum solution module. The generated Hamiltonian function structure and objective functional equations are packaged and sent directionally as input parameters required for subsequent costate differential equation derivation.

[0066] S104. Solve for the optimal control solution based on the Hamiltonian function and the Pontryagin principle.

[0067] As one possible implementation, step S104 can be specifically implemented as steps S1041-S1046.

[0068] S1041. Using a finite control time window as the time domain boundary and the pipe-soil coupling dynamic state evolution equation as the system state differential equation, the initial boundary conditions of the system state vector are set as the initial state values ​​of the pipe network at the parameter acquisition time, thus completing the time domain and initial value boundary settings before solving.

[0069] S1042. Using the system state vector as the derivative variable, perform partial derivative operations on the Hamiltonian function. Based on the necessary condition of the costate equation according to the Pontryagin maximum principle, define the negative value of the partial derivative result as the time rate of change of the costate vector, and generate the costate differential equation.

[0070] S1043. Based on the co-state differential equation and combined with the terminal state penalty weight matrix, determine the terminal cross-sectional boundary conditions of the co-state differential equation.

[0071] S1044. Using the control vector as the derivative variable, perform partial derivative operations on the Hamiltonian function. Based on the necessary condition for the extremum of the Pontryagin maximum principle, set the partial derivative result corresponding to the control vector to the zero vector to obtain the stationary point equation used to solve the optimal control quantity.

[0072] In some embodiments, the stationary point equations are used to solve for the optimal control solution.

[0073] S1045. Perform positive definite verification and matrix inversion operations on the control energy consumption weight matrix, and perform algebraic transformation on the stationary point equation by combining the transpose vector of the control input matrix. Separate the control vector to the left side of the equation to complete the standardized transformation of the solution equation and obtain the standardized stationary point equation.

[0074] S1046. By simultaneously solving the system state differential equations, co-state differential equations, and standardized stationary point equations, and combining the initial boundary conditions with the terminal cross-sectional boundary conditions, a closed-loop solution is performed. The output is the optimal control solution that simultaneously satisfies the pipeline safety constraints and energy consumption control requirements within a finite control time window.

[0075] For example, the Pontryagin extremum solution module is connected to the objective functional and Hamiltonian construction module to solve the costate differential equation, and calculates the optimal control solution by setting the partial derivative of the Hamiltonian function with respect to the control vector to zero.

[0076] Furthermore, the Pontryagin extreme value solution module is specifically used for: performing partial derivative operations on the Hamiltonian function with the system state vector as the derivative variable; extracting the negative gradient vector from the result of the partial derivative operation, defining the negative gradient vector as the time evolution rate of the costate vector, and generating the costate differential equation; extracting the terminal state penalty weight matrix and the system state vector at the terminal time, and setting the product of the two as the terminal transverse boundary condition of the costate differential equation.

[0077] The Pontryagin extreme value solution module is also used for: performing partial derivative operations on the Hamiltonian function with the control vector as the derivative variable; based on the necessary extreme value condition of the Pontryagin maximum principle, setting the partial derivative of the Hamiltonian function with respect to the control vector to zero to obtain the system stationary point equation; performing matrix inversion on the control energy consumption weight matrix, and using the inverted matrix, the transpose of the control input matrix, and the costate vector to perform cascade multiplication to solve the stationary point equation and output the optimal control solution.

[0078] Specifically, the Pontryagin extreme value calculation module is the core computing power for the entire intelligent remote monitoring system to perform variational deduction and strategy formulation. Its main function is to transform the upstream functional evaluation model with physical penalty weights into specific equipment control command values ​​with mathematical uniqueness for specific spatiotemporal conditions through rigorous calculus and algebraic operations. This module enables the system to move away from the traditional threshold lookup table control mode and achieve proactive and precise intervention based on dynamic future deduction.

[0079] The processor first performs partial derivative operations on the input Hamiltonian function, using the system state vector as an independent derivative variable. The computing unit extracts the negative gradient vector from the result of this partial derivative operation. The algorithm rigorously defines this negative gradient vector as the rate of evolution of the costate vector over time, and generates the costate differential equation accordingly. The corresponding mathematical model is as follows: ; in, The first derivative of the costate vector with respect to time, i.e., the time evolution rate, is represented by this. Represents the partial derivative operator. Represents the Hamiltonian function. Represents the system state vector. The process state penalty weight matrix represents the process state. The transpose of the system state transition matrix. It represents a continuously differentiable costate vector.

[0080] To establish the boundary conditions of the differential equation, the processor extracts the terminal state penalty weight matrix and the system state vector at the terminal moment. After performing an algebraic multiplication of the two, the resulting product is set as the terminal transverse boundary condition of the co-state differential equation: ; in, This represents the costate vector at the defined termination time point. The terminal state penalty weight matrix represents the terminal state. This represents the terminal state vector of the system at the termination time.

[0081] After establishing the costate space evolution trajectory, the algorithm engine transforms the object of differentiation, using the control vector as the differentiation variable to perform partial derivative calculations on the Hamiltonian function again. According to the necessary condition for extrema in Pontryagin's maximum principle, the processor forces the partial derivative of the Hamiltonian function with respect to the control vector to be equal to zero, thereby obtaining the system stationary point equations: ; in, Represents the control vector. This represents the weight matrix for controlling energy consumption. The transpose of the control input matrix. It represents the zero vector.

[0082] During the solution phase, the processor invokes its internal algebra library to perform matrix inversion on the control energy consumption weight matrix. Using the inverted matrix, the transpose of the control input matrix, and the previously derived costate vector, the system performs a multi-stage chain multiplication operation. This operation directly penetrates the analytical stationary point equations, outputting the optimal control solution. ; in, This represents the optimal control solution as the final output. This represents the inverse of the weight matrix controlling energy consumption.

[0083] At the data input / output interaction level, the input port of this module receives the analytical expression of the Hamiltonian function, various penalty weight matrix parameters, and the matrix group related to system state transitions from the target functional and Hamiltonian construction module. The data entering the module flows sequentially through the calculus operator layer and the linear algebra inversion library within the computing unit. After undergoing two partial derivative calculations and boundary substitution of the terminal cross-section condition, the output port sends the calculated optimal control solution digital tensor to the downstream multi-field collaborative intervention drive module. This tensor data constitutes the absolute execution basis for the adjustment range of the underlying physical equipment on-site.

[0084] S105. Generate synchronization control commands based on the optimal control solution.

[0085] In this embodiment, the synchronous control commands include mechanical frequency reduction commands for surface construction machinery and coordinated grouting and pressurization commands for the underground targeted grouting system.

[0086] As one possible implementation, step S105 can be specifically implemented as steps S1051-S1053.

[0087] S1051. Perform protocol reverse analysis on the optimal control solution to restore it to mechanical frequency reduction control signals and grouting pressurization control signals that have physical units and can be directly executed by the equipment.

[0088] S1052. Perform time synchronization calibration on the mechanical frequency reduction control signal and the grouting pressurization control signal to obtain the synchronized calibrated mechanical frequency reduction control signal and grouting pressurization control signal.

[0089] S1053. Based on the synchronized calibrated mechanical frequency reduction control signal and grouting pressurization control signal, generate standardized synchronous control commands according to the preset command encoding protocol.

[0090] For example, the multi-field collaborative intervention driving module is connected to the Pontryagin extreme value solving module to convert the optimal control solution into instructions to drive field devices and feed back the physical state to the transient feature multi-dimensional sensing module. Furthermore, the multi-field collaborative intervention driving module is specifically used to perform protocol inverse analysis on the optimal control solution, extract the mechanical frequency reduction control signal and the targeted grouting pressure control signal that match the communication protocol of the underlying equipment; send the mechanical frequency reduction control signal to the electrical control unit of the surface construction machinery through the industrial communication bus, and simultaneously send the targeted grouting pressure control signal to the hydraulic control unit of the underground targeted grouting system to trigger the physical action of the equipment; when the physical action is completed, send a data reload trigger command to the transient feature multi-dimensional sensing module, drive the transient feature multi-dimensional sensing module to start a new round of physical state parameter synchronous acquisition process, and complete the control closed loop.

[0091] Specifically, the multi-field collaborative intervention driving module serves as the communication and execution hub connecting high-order functional algorithms with underlying industrial hardware. This module undertakes the core task of transforming pure mathematical variational derivation results into real physical control forces on the engineering site, enabling the system to break free from the limitations of off-loop calculations and establish an active physical defense line against shear disasters at pipeline interfaces.

[0092] At the data input / output level, the input of this module is connected to the system's high-speed data bus, receiving the dimensionless optimal control solution digital tensor from the Pontryagin extreme value calculation module. Since this tensor is a purely mathematical independent variable at the physical level, the underlying execution device cannot directly recognize it. The processor must perform a protocol reverse parsing operation on it. The algorithm retrieves the preset operating boundary parameters of the surface construction machinery and the underground targeted grouting system, and through reverse mapping, restores the dimensionless control variables to control signal values ​​with absolute physical units.

[0093] The mathematical transformation model for the reverse parsing of the above protocol is as follows: ; ; in, This represents the absolute value of the mechanical frequency reduction control signal that matches the communication protocol of the underlying device. This represents the lower limit of frequency reduction operation for surface construction machinery. This represents the mechanical frequency reduction component in the optimal control solution. The algebraic difference between the upper limit and the lower limit of frequency reduction operation for surface construction machinery. This represents the absolute value of the targeted grouting pressure control signal that matches the communication protocol of the underlying equipment. This represents the lower limit of the grouting pressure operating for the underground targeted grouting system. This represents the grouting pressure component in the optimal control solution. This represents the algebraic difference between the upper and lower limits of the grouting pressure operating in the underground targeted grouting system.

[0094] After acquiring the actual physical quantity control signals, this module enters the physical distribution phase. The processor encapsulates the control message and dispatches it to the lower-level machine via the industrial communication bus. The mechanical frequency reduction control signal is precisely routed to the electrical control unit of the surface construction machinery. The targeted grouting pressure control signal is synchronously routed to the hydraulic control unit of the underground targeted grouting system. The issuance of electrical signal commands directly triggers the physical action of the actuators. The decrease in the spindle speed of the construction machinery and the sudden increase in the grouting pressure of the underground pump station occur simultaneously, thereby generating a cooperative impedance force in physical space to inhibit the evolution of pipeline displacement.

[0095] At the moment the predetermined physical actions are completed, the soil surrounding the underground pipeline network has established a new mechanical equilibrium state. The main control chip of this module generates a data reload trigger command message, and the data output end sends this command to the front-end transient feature multi-dimensional sensing module. This command forcibly wakes up the underlying acquisition clock of the sensing module, driving it to start a new round of physical state parameter synchronous acquisition process. The unidirectional algorithm data flow completes the spatial and temporal connection here, constructing a tight control closed loop.

[0096] This invention provides an intelligent remote monitoring method for pipeline engineering construction. It acquires transient dynamic parameters such as shear displacement, displacement rate, and pore water pressure in the surrounding soil at real time, and constructs system state and control vectors by combining these parameters with the boundary parameters of the construction machinery and grouting system. This accurately reflects the real-time dynamic state of the pipeline network. A Hamiltonian function is constructed using the pipe-soil coupled dynamic state evolution equation as a constraint and minimizing pipeline state deviation and control energy consumption as the objective. The optimal control solution is then solved based on the Pontryagin principle, enabling rapid deduction of pipeline deformation trends and globally optimal control decisions. Finally, synchronous control commands for mechanical frequency reduction and grouting pressurization are generated. This allows for proactive and coordinated intervention within a very short time after high-frequency shear impact, suppressing transient shear deformation at the pipeline interface, preventing interface shear separation and damage, reducing control energy consumption, and improving the monitoring response speed and safety protection capabilities during pipeline engineering construction.

[0097] Optionally, the intelligent remote monitoring method for pipeline engineering construction provided by the present invention further includes steps S201-S204 after step S105.

[0098] S201. Synchronous control commands are sent to the electrical control unit of the surface construction machinery and the hydraulic control unit of the underground targeted grouting system through the communication transmission link.

[0099] S202. Receive instruction reception confirmation signals from surface construction machinery and underground targeted grouting systems. The instruction reception confirmation signals include a reception timestamp.

[0100] S203. Based on the instruction reception confirmation signal, perform timestamp verification to determine whether the synchronization control instruction has been successfully received.

[0101] S204. If no instruction reception confirmation signal is received or the synchronization control instruction is not successfully received, the synchronization control instruction shall be resent to the surface construction machinery and the underground targeted grouting system until it is successfully received.

[0102] This invention can drive the device by constructing the soil-pipe dynamics equation and combining it with the Pontryagin principle to solve the optimal control solution, thereby achieving active and precise intervention in transient excitation forces. This improves the problem that traditional pipeline monitoring mostly uses static threshold alarms, which are prone to shear damage at pipeline interfaces due to response lag and lack of optimal coordination.

[0103] This invention generates a unified control vector by performing a normalization mapping operation on the operating boundary parameters, thereby eliminating the differences in physical dimensions of the operating space of heterogeneous devices. This improves the problem that traditional joint control systems mostly use raw numerical values ​​for direct calculation, which causes the underlying mathematical matrix to easily diverge due to the large span of the order of magnitude of various parameters.

[0104] This invention establishes the dynamic evolution boundary under real working conditions by extracting stiffness and permeability coefficient to construct a transfer matrix and introducing an external disturbance matrix. This improves the problem that traditional simulations mostly use simplified empirical models, which completely ignore the fluid-solid coupling friction characteristics of the pipe and soil, resulting in a serious deviation between the predicted displacement trajectory and the actual situation.

[0105] This invention achieves precise synchronous intervention of heterogeneous devices at the underlying level by performing protocol reverse parsing on the optimal control solution and synchronously sending control signals, thereby overcoming communication barriers. This improves upon the traditional approach where each system issues instructions separately, which, due to data hardware isolation between underlying devices, easily leads to timing discrepancies in various actions when facing transient shocks.

[0106] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0107] This invention provides an intelligent remote monitoring device for pipeline engineering construction. The remote monitoring device includes a communication unit and a processing unit.

[0108] The communication unit is used to acquire transient dynamic parameters of the underground pipeline network during the construction of the pipeline project, as well as the operating boundary parameters of the surface construction machinery and the underground targeted grouting system; the transient dynamic parameters include the shear displacement, displacement rate and pore water pressure of the surrounding soil at the pipeline interface; The processing unit is used to construct system state vectors and control vectors based on the transient dynamic parameters and operating boundary parameters; construct a Hamiltonian function with the pipe-soil coupling dynamic state evolution equations followed by the system state vectors and control vectors as constraints and minimizing pipe network state deviation and control energy consumption as objectives; solve for the optimal control solution based on the Hamiltonian function and in conjunction with Pontryagin's principle; and generate synchronous control commands based on the optimal control solution, including mechanical frequency reduction commands for surface construction machinery and grouting pressurization coordination commands for the underground targeted grouting system.

[0109] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 300 includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, it implements the steps in the above-described method embodiments. Alternatively, when the processor 301 executes the computer program 303, it implements the functions of each module / unit in the above-described device embodiments.

[0110] For example, the computer program 303 may be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 303 in the electronic device 300.

[0111] The processor 301 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0112] The memory 302 can be an internal storage unit of the electronic device 300, such as a hard disk or memory of the electronic device 300. The memory 302 can also be an external storage device of the electronic device 300, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 300. Furthermore, the memory 302 can include both internal and external storage units of the electronic device 300. The memory 302 is used to store the computer program and other programs and data required by the terminal. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0113] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent remote monitoring during the construction period of a pipeline network project, characterized in that, include: The transient dynamic parameters of the underground pipeline network during the construction of the pipeline project are obtained, as well as the operating boundary parameters of the surface construction machinery and the underground targeted grouting system; the transient dynamic parameters include the shear displacement, displacement rate and pore water pressure of the surrounding soil at the pipeline interface; Based on the transient dynamic parameters and operational boundary parameters, construct the system state vector and control vector; Using the pipe-soil coupling dynamic state evolution equations followed by the system state vector and control vector as constraints, and aiming to minimize the pipe network state deviation and control energy consumption, a Hamiltonian function is constructed. Based on the Hamiltonian function and combined with Pontryagin's principle, the optimal control solution is solved. Based on the optimal control solution, synchronous control commands are generated, including mechanical frequency reduction commands for surface construction machinery and grouting pressurization coordination commands for the underground targeted grouting system.

2. The intelligent remote monitoring method for pipeline engineering construction period according to claim 1, characterized in that, The construction of the system state vector and control vector based on the transient dynamic parameters and operational boundary parameters includes: Based on the transient dynamic parameters, analog-to-digital conversion and filtering denoising are performed under a unified timestamp to extract the effective values ​​of the physical characteristics of each parameter. Based on the effective values ​​of the physical characteristics of each parameter, tensors are spliced ​​according to a preset dimensional order to generate a system state vector that represents the real-time dynamic equilibrium state of the pipeline network. The operational boundary parameters of surface construction machinery and underground targeted grouting system are analyzed to generate mechanical frequency reduction components and grouting pressure components, respectively. The mechanical frequency reduction component and the grouting pressure component are normalized and mapped, and then combined according to a preset dimension order to obtain a control vector representing the multi-equipment collaborative operation command.

3. The intelligent remote monitoring method for pipeline engineering construction period according to claim 1, characterized in that, The Hamiltonian function is constructed using the pipe-soil coupling dynamics state evolution equations followed by the system state vector and control vector as constraints, with the objective of minimizing pipe network state deviation and control energy consumption. This includes: By introducing the excitation force disturbance term generated by surface construction machinery, and combining the tangential stiffness of the pipe-soil interface and the soil permeability coefficient, the system state matrix and control input matrix are calibrated, and a pipe-soil coupled dynamic state evolution equation describing the dynamic change of the system state vector with the control vector and the excitation force disturbance term is constructed. Determine the weight matrix, which includes a process state penalty weight matrix for constraining the deformation deviation of the entire pipeline network, a terminal state penalty weight matrix for constraining the pipeline network safety threshold at the end of the control cycle, and a control energy consumption weight matrix for constraining the energy consumption of equipment operation. Based on the system state vector, control vector and weight matrix, a quadratic integral operation is performed within a finite control time window, and a terminal state penalty term is superimposed to generate an objective functional with the core of minimizing pipeline state deviation and control energy consumption. A costate vector with the same dimension as the system state vector is introduced, and the instantaneous integral kernel term of the objective functional, the inner product term of the costate vector transpose and the pipe-soil coupled dynamic state evolution equation are algebraically superimposed to generate a Hamiltonian function for unconstrained extreme value solving.

4. The intelligent remote monitoring method for pipeline engineering construction period according to claim 1, characterized in that, The process of finding the optimal control solution based on the Hamiltonian function and in conjunction with Pontryagin's principle includes: Using the finite control time window as the time domain boundary and the pipe-soil coupling dynamic state evolution equation as the system state differential equation, the initial boundary conditions of the system state vector are set as the initial state values ​​of the pipe network at the parameter acquisition time, thus completing the time domain and initial value boundary setting before solving. Using the system state vector as the derivative variable, partial derivative operations are performed on the Hamiltonian function. Based on the necessary condition of the costate equation according to the Pontryagin maximum principle, the negative value of the partial derivative result is defined as the time rate of change of the costate vector, thus generating the costate differential equation. Based on the costate differential equation, and combined with the terminal state penalty weight matrix, the terminal cross-sectional boundary conditions of the costate differential equation are determined. Using the control vector as the derivative variable, partial derivative operations are performed on the Hamiltonian function. Based on the necessary condition for the extremum of the Pontryagin maximum principle, the partial derivative result corresponding to the control vector is set to equal the zero vector to obtain the stationary point equation used to solve the optimal control quantity. The stationary point equation is used to solve the optimal control solution. Perform positive definite verification and matrix inversion on the control energy consumption weight matrix, and perform algebraic transformation on the stationary point equation by combining the transpose vector of the control input matrix. Separate the control vector to the left side of the equation to complete the standardized transformation of the solution equation and obtain the standardized stationary point equation. By simultaneously solving the system state differential equations, co-state differential equations, and standardized stationary point equations, and combining the initial boundary conditions with the terminal cross-sectional boundary conditions, a closed-loop solution is performed, outputting the optimal control solution that simultaneously satisfies the pipeline safety constraints and energy consumption control requirements within a finite control time window.

5. The intelligent remote monitoring method for pipeline engineering construction period according to claim 1, characterized in that, The generation of synchronization control commands based on the optimal control solution includes: The optimal control solution is reverse-analyzed to restore it into mechanical frequency reduction control signals and grouting pressurization control signals that have physical units and can be directly executed by the equipment; The mechanical frequency reduction control signal and the grouting pressurization control signal are synchronized and calibrated to obtain synchronized and calibrated mechanical frequency reduction control signal and grouting pressurization control signal; Based on the synchronized calibrated mechanical frequency reduction control signal and grouting pressurization control signal, standardized synchronous control commands are generated according to the preset command encoding protocol.

6. The intelligent remote monitoring method for pipeline engineering construction period according to claim 1, characterized in that, After generating the synchronization control command based on the optimal control solution, the process further includes: The synchronous control command is simultaneously sent to the electrical control unit of the surface construction machinery and the hydraulic control unit of the underground targeted grouting system via a communication transmission link; The system receives instruction reception confirmation signals from surface construction machinery and underground targeted grouting systems, wherein the instruction reception confirmation signals include a reception timestamp. Based on the instruction reception confirmation signal, timestamp verification is performed to determine whether the synchronization control instruction has been successfully received. If no confirmation signal for receiving the instruction is received or the synchronization control instruction is not successfully received, the synchronization control instruction will be resent to the surface construction machinery and the underground targeted grouting system until it is successfully received.

7. An intelligent remote monitoring device for pipeline engineering construction, characterized in that, include: The communication unit is used to acquire transient dynamic parameters of the underground pipeline network during the construction of the pipeline project, as well as the operating boundary parameters of the surface construction machinery and the underground targeted grouting system; the transient dynamic parameters include the shear displacement, displacement rate and pore water pressure of the surrounding soil at the pipeline interface; The processing unit is used to construct system state vectors and control vectors based on the transient dynamic parameters and operating boundary parameters; construct a Hamiltonian function with the pipe-soil coupling dynamic state evolution equations followed by the system state vectors and control vectors as constraints and minimizing pipe network state deviation and control energy consumption as objectives; solve for the optimal control solution based on the Hamiltonian function and in conjunction with Pontryagin's principle; and generate synchronous control commands based on the optimal control solution, including mechanical frequency reduction commands for surface construction machinery and grouting pressurization coordination commands for the underground targeted grouting system.

8. The intelligent remote monitoring device for pipeline engineering construction period according to claim 7, characterized in that, The processing unit is specifically used to perform analog-to-digital conversion and filtering and denoising processing based on the transient dynamic parameters under a unified timestamp, and extract the effective values ​​of the physical characteristics of each parameter. Based on the effective values ​​of the physical characteristics of each parameter, tensors are spliced ​​according to a preset dimensional order to generate a system state vector representing the real-time dynamic equilibrium state of the pipeline network; the operating boundary parameters of the surface construction machinery and the underground targeted grouting system are analyzed to generate mechanical frequency reduction components and grouting pressure components respectively. The mechanical frequency reduction component and the grouting pressure component are normalized and mapped, and then combined according to a preset dimension order to obtain a control vector representing the multi-equipment collaborative operation command.

9. The intelligent remote monitoring device for pipeline engineering construction period according to claim 7, characterized in that, The processing unit is specifically used to introduce the excitation force disturbance term generated by the surface construction machinery, combine the tangential stiffness of the pipe-soil interface and the soil permeability coefficient, calibrate the system state matrix and control input matrix, and construct the pipe-soil coupled dynamic state evolution equation describing the dynamic change of the system state vector with the control vector and the excitation force disturbance term. Determine the weight matrix, which includes a process state penalty weight matrix for constraining the deformation deviation of the entire pipeline network, a terminal state penalty weight matrix for constraining the pipeline network safety threshold at the end of the control cycle, and a control energy consumption weight matrix for constraining the energy consumption of equipment operation. Based on the system state vector, control vector, and weight matrix, a quadratic integral operation is performed within a finite control time window. A terminal state penalty term is superimposed to generate an objective functional with the core objective of minimizing pipeline state deviation and control energy consumption. A costate vector with the same dimension as the system state vector is introduced, and the instantaneous integral kernel term of the objective functional, the inner product term of the costate vector transpose and the pipeline-soil coupled dynamic state evolution equation are algebraically superimposed to generate a Hamiltonian function for unconstrained extreme value solving.

10. An intelligent remote monitoring system for pipeline engineering construction, characterized in that, The remote monitoring system includes an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method as described in any one of claims 1 to 6.

Images