Preparation method and effect prediction system of high-pressure-resistant high-permeability polyurethane grouting material

Abstract

The invention relates to the technical field of preparation of high-pressure-resistant high-permeability polyurethane grouting materials, discloses a preparation method and an effect prediction system of a high-pressure-resistant high-permeability polyurethane grouting material, and discloses the preparation method and the effect prediction system of the high-pressure-resistant high-permeability polyurethane grouting material. The preparation method comprises the following steps: training a ratio optimization network and a temperature control network, and associating output parameters; rheological parameters, temperature and pressure data are collected in real time, osmotic pressure difference is calculated, an injection rate threshold value is generated, and a synthesis or correction instruction is generated after matching verification. The effect prediction system comprises a modeling unit, a monitoring unit, an analysis unit and the like, and multi-parameter dynamic analysis and performance prediction are achieved. According to the scheme, through data-driven regulation and prediction, the material preparation precision and the permeation stability under high pressure are improved, and the problems that a traditional process is large in batch difference, insufficient in parameter collaboration and the like are solved.

Description

Technical Field

[0001] The invention relates to the technical field of preparation of high-pressure-resistant and high-permeability polyurethane grouting materials, in particular to a preparation method of high-pressure-resistant and high-permeability polyurethane grouting materials and an effect prediction system. Background Art

[0002] As an important anti-seepage, leak-proofing and structural reinforcement material in the field of civil engineering, the performance of polyurethane grouting materials directly affects the quality and safety of the project. The application of traditional polyurethane grouting materials in high-pressure environments faces significant technical bottlenecks, mainly reflected in the following aspects:

[0003] The preparation of existing polyurethane grouting materials mostly relies on fixed ratios of polyol and isocyanate components, and no dynamic correlation model between the rheological parameters of the raw materials and reaction conditions has been established. For example, differences in the hydroxyl value, molecular weight distribution, or functionality of isocyanates in different batches of polyols can lead to fluctuations in rheological parameters such as the initial viscosity and gel time of the reaction. However, traditional processes are unable to capture such changes in real time and adjust the ratio, which can easily lead to uneven cross-linking in the reaction system and unstable compressive strength and permeability of the final material. In addition, the reaction temperature control mostly uses a preset constant temperature mode, and does not dynamically optimize the temperature curve in combination with real-time rheological data. This may cause local overheating or incomplete reaction, affecting the uniformity of the material's microstructure.

[0004] In scenarios such as underground engineering and tunnels crossing water-rich strata, grouting materials need to maintain high permeability under high-pressure environments to ensure that the slurry effectively diffuses into small cracks. Traditional methods only set the material injection rate through experience, and no quantitative correlation model between pressure field and permeability is established. For example, when the pressure distribution in the reaction system is uneven, fixed-rate injection may cause local slurry accumulation or premature blockage of the permeation path, reducing grouting efficiency. At the same time, the lack of real-time monitoring of dynamic parameters such as molecular diffusion coefficient and viscosity gradient during the reaction process makes it difficult to accurately predict the permeation path and diffusion range of the material under high pressure, resulting in uncontrollable grouting effect.

[0005] The high-pressure resistance and high permeability of polyurethane grouting materials need to be achieved through the coordinated regulation of multiple parameters such as ratio, temperature, and pressure. In the traditional preparation process, each parameter control module operates independently and lacks a correlation mechanism based on reaction time. For example, if the ratio adjustment and temperature control are not dynamically coupled according to the reaction process, it may cause the early reaction rate to be too fast to form a rigid gel, hindering later penetration; or the reaction rate may be too slow to cause slurry loss. In addition, pressure monitoring is only used for safety warnings and does not form a closed-loop feedback with the material injection rate and ratio optimization. It is impossible to achieve intelligent control of "monitoring-analysis-regulation", and it is difficult to meet the requirements of complex projects for high performance and high reliability of materials.

[0006] Existing predictions of polyurethane grouting material properties are mostly based on static empirical formulas that fail to integrate real-time rheological data, temperature curves, and pressure parameters. For example, the fixed formula for calculating the relationship between osmotic pressure difference and injection rate fails to reflect the impact of dynamic changes in the reaction system on permeability, resulting in significant deviations between predicted results and actual results. The lack of a predictive model that can correlate multiple physical field parameters in real time makes it difficult for engineers to accurately assess material performance during the preparation phase, requiring them to rely on subsequent field testing and adjustments, increasing construction costs and timelines.

[0007] Traditional technologies lack dynamic mix optimization, multi-parameter coordinated control, and real-time performance prediction models, resulting in insufficient permeability and stability of polyurethane grouting materials under high-pressure environments, restricting their application in complex geological conditions. Therefore, there is an urgent need to develop a data-driven intelligent preparation method and prediction system to achieve precise control and reliable prediction of material properties. Summary of the Invention

[0008] The purpose of the present invention is to provide a method for preparing a high-pressure resistant and high-permeability polyurethane grouting material and an effect prediction system to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solution: a method for preparing a high-pressure resistant and high-permeability polyurethane grouting material, the method comprising:

[0010] Step S1, obtaining initial rheological parameters of a polyol component and an isocyanate component, training multiple sets of rheological parameters at different ratios using a rheological analysis model to obtain a ratio optimization network; training multiple sets of reaction temperature curves to obtain a temperature control network; and correlating output parameters of the ratio optimization network and the temperature control network based on reaction time;

[0011] Step S2, obtaining real-time rheological parameters of the polyol component and the isocyanate component of the current batch, and polymerization kettle temperature data collected synchronously when obtaining the real-time rheological parameters;

[0012] Step S3, identifying the real-time rheological parameters through the ratio optimization network to obtain the optimal ratio adjustment amount; identifying the polymerization kettle temperature data through the temperature control network to obtain the temperature control instruction;

[0013] Step S4, obtaining the pressure sensor monitoring value of the current reaction system;

[0014] Step S5, calculating the real-time osmotic pressure difference of the reaction system according to the monitoring value of the pressure sensor;

[0015] Step S6, generating a material injection rate threshold according to the real-time osmotic pressure difference;

[0016] Step S7: If the material injection rate threshold matches the optimal ratio adjustment amount, the set reaction temperature curve is obtained according to the correlation between the ratio optimization network and the temperature control network parameters; it is determined whether the temperature control instruction corresponds to the set reaction temperature curve. If so, a material synthesis instruction is generated; if not, a parameter correction instruction is generated.

[0017] Preferably, the step S2 includes:

[0018] Step S21, installing a rheometer probe on the side wall of the polymerization kettle; the rheometer probe is connected to the data input terminal of the reaction controller;

[0019] Step S22: a first mass flow meter is provided on the outlet pipeline of the polyol storage tank; a second mass flow meter is provided on the outlet pipeline of the isocyanate storage tank;

[0020] Step S23, three temperature sensors are equidistantly distributed axially inside the polymerization vessel; the temperature sensors are connected to the input end of the reaction controller;

[0021] Step S24: When the reaction controller receives a reaction start signal, the output end of the reaction controller drives the rheometer probe to collect real-time rheological parameters; and simultaneously drives the temperature sensor to collect polymerization kettle temperature data.

[0022] Preferably, step S5 includes: obtaining the viscosity gradient monitoring value of the current reaction system, calculating the real-time molecular diffusion coefficient of the reaction system according to the pressure sensor monitoring value and the viscosity gradient monitoring value; obtaining the material penetration path length according to the real-time molecular diffusion coefficient; and generating the reaction start signal according to the material penetration path length.

[0023] Preferably, step S5 includes: dividing the three-dimensional pressure distribution area of ​​the reaction system according to the monitoring value of the pressure sensor; obtaining the osmotic pressure difference change rate of each area and the coordinates of the area boundary intersection point according to the three-dimensional pressure distribution area; generating the reaction start signal according to the osmotic pressure difference change rate and the coordinates of the area boundary intersection point.

[0024] Preferably, the step S2 includes:

[0025] Obtaining a first real-time flow value of a polyol component and a second real-time flow value of an isocyanate component;

[0026] Determine whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range; if so, verify the molar ratio of the first real-time flow rate value to the second real-time flow rate value based on the molecular weight ratio of the polyol to the isocyanate; if the verification passes, obtain the real-time rheological parameters and polymerization kettle temperature data; if not, return to this step to re-obtain the flow value;

[0027] It is determined whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range. If not, a flow abnormality alarm signal is generated.

[0028] Preferably, step S7 includes: if the material injection rate threshold does not match the optimal ratio adjustment amount, obtaining a real-time viscosity value through a viscometer at the outlet at the bottom of the reactor, and returning to this step to determine whether the material injection rate threshold matches the optimal ratio adjustment amount.

[0029] Preferably, the present invention further includes a high-pressure resistant and high-permeability polyurethane grouting material effect prediction system, which system includes:

[0030] A modeling unit is configured to obtain initial rheological parameters of a polyol component and an isocyanate component, train multiple sets of rheological parameters at different ratios using a rheological analysis model to obtain a ratio optimization network; train multiple sets of reaction temperature curves to obtain a temperature control network; and correlate output parameters of the ratio optimization network and the temperature control network based on reaction time;

[0031] A monitoring unit configured to obtain real-time rheological parameters of the polyol component and the isocyanate component of the current batch, and polymerization kettle temperature data collected synchronously when obtaining the real-time rheological parameters;

[0032] An analysis unit is configured to identify the real-time rheological parameters through the ratio optimization network to obtain an optimal ratio adjustment amount; and to identify the polymerization kettle temperature data through the temperature control network to obtain a temperature control instruction;

[0033] A pressure acquisition unit configured to obtain a pressure sensor monitoring value of the current reaction system;

[0034] an osmotic pressure calculation unit configured to calculate a real-time osmotic pressure difference of the reaction system according to the monitoring value of the pressure sensor;

[0035] a rate generating unit configured to generate a material injection rate threshold according to the real-time osmotic pressure difference;

[0036] The execution unit is configured to obtain a set reaction temperature curve based on the correlation between the ratio optimization network and the temperature control network parameters if the material injection rate threshold matches the optimal ratio adjustment amount; determine whether the temperature control instruction corresponds to the set reaction temperature curve, and if so, generate a material synthesis instruction; if not, generate a parameter correction instruction.

[0037] Preferably, the monitoring unit is further configured to:

[0038] A rheometer probe is arranged on the side wall of the polymerization kettle; the rheometer probe is connected to the data input terminal of the reaction controller;

[0039] A first mass flow meter is provided on the outlet pipeline of the polyol storage tank; a second mass flow meter is provided on the outlet pipeline of the isocyanate storage tank;

[0040] Three temperature sensors are equidistantly distributed axially inside the polymerization kettle; the temperature sensors are connected to the input end of the reaction controller;

[0041] When the reaction controller receives a reaction start signal, the output end of the reaction controller drives the rheometer probe to collect real-time rheological parameters; and simultaneously drives the temperature sensor to collect polymerization kettle temperature data.

[0042] Preferably, the permeation calculation unit is further configured to obtain a viscosity gradient monitoring value of the current reaction system, calculate a real-time molecular diffusion coefficient of the reaction system according to the pressure sensor monitoring value and the viscosity gradient monitoring value; obtain a material permeation path length according to the real-time molecular diffusion coefficient; and generate the reaction start signal according to the material permeation path length; or

[0043] The permeation calculation unit is also configured to divide the three-dimensional pressure distribution area of ​​the reaction system according to the monitoring value of the pressure sensor; obtain the permeation pressure difference change rate of each area and the coordinates of the area boundary intersection point according to the three-dimensional pressure distribution area; and generate the reaction start signal according to the permeation pressure difference change rate and the coordinates of the area boundary intersection point.

[0044] Preferably, the monitoring unit is further configured to:

[0045] Obtaining a first real-time flow value of a polyol component and a second real-time flow value of an isocyanate component;

[0046] Determine whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range; if so, verify the molar ratio of the first real-time flow rate value to the second real-time flow rate value based on the molecular weight ratio of the polyol to the isocyanate; if the verification passes, obtain the real-time rheological parameters and polymerization kettle temperature data; if not, return to this step to re-obtain the flow value;

[0047] It is determined whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range. If not, a flow abnormality alarm signal is generated.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] By collecting the initial rheological parameters of polyols and isocyanates (such as viscosity, shear rate, etc.), and using the ratio optimization network to train the rheological characteristics under different ratios, the system can realize intelligent analysis of real-time rheological data. When the rheological parameters of the current batch of raw materials are detected to deviate from the preset range, the system automatically calculates the optimal ratio adjustment to compensate for the performance fluctuations caused by the differences in raw material batches. For example, if the viscosity of a batch of polyols is too high, the system can increase the isocyanate ratio in real time to balance the cross-linking density, ensuring that the compressive strength and permeability coefficient of different batches of materials remain consistent, solving the stability problem of traditional fixed ratio processes.

[0050] The temperature control network trains multiple sets of reaction temperature curves to establish a dynamic correlation model between temperature and reaction time. During the reaction, the system automatically generates a set reaction temperature curve based on real-time rheological data and ratio adjustments, enabling dynamic switching of temperature parameters. For example, increasing the temperature in the early stages of the reaction accelerates the crosslinking induction period, maintaining a constant temperature in the middle stages to control the gelation rate, and cooling the temperature in the later stages to stabilize the microstructure. This avoids the reaction lag or overheating decomposition problems associated with traditional constant temperature control, improves the uniformity of the material's molecular chain distribution, and thus enhances its high-pressure resistance.

[0051] The system monitors the reaction system pressure in real time through pressure sensors. Combining viscosity gradient data, it calculates the molecular diffusion coefficient and permeation path length, dynamically generating a threshold for the material injection rate. When pressure distribution is uneven, the system automatically divides the pressure into three-dimensional zones and adjusts the injection strategy based on the rate of change of the permeation pressure difference in each zone to avoid local blockage or slurry loss. For example, the injection rate is reduced in high-pressure areas to prevent premature gel formation, while the rate is increased in low-pressure areas to expand the permeation range. This ensures uniform diffusion of the slurry in complex pressure fields, enhancing the material's high permeability and grouting efficiency.

[0052] By associating the output parameters of the ratio optimization network and the temperature control network along the reaction timeline, a multi-physics field collaborative control model is established. For example, when the ratio adjustment causes a change in the reaction heat release rate, the temperature control network synchronously adjusts the heating curve to maintain thermal equilibrium, avoiding system explosion or incomplete curing caused by uneven heat release. At the same time, the pressure monitoring and flow calibration modules (such as mass flow meters that monitor the flow ratio of polyols and isocyanates in real time) form dual control to ensure that the molar ratio of the reaction system is accurately matched, fundamentally guaranteeing the stability of the cross-linked structure and improving the compressive strength and impermeability of the material.

[0053] The performance prediction system integrates modeling, monitoring, and analysis units. Using real-time data collected from rheological parameters, temperature data, and pressure values, it dynamically predicts the material's permeability and mechanical properties. Compared to traditional empirical formulas, this system's neural network model, built on extensive training data, accurately captures nonlinear relationships between parameters. For example, it uses pressure sensor values ​​and viscosity gradients to predict molecular diffusion coefficients, and then assesses permeation path length. This provides real-time, reliable performance references for engineering applications, reducing field testing costs and construction risks.

[0054] From raw material flow monitoring (such as real-time molar ratio verification using the first and second mass flow meters) to automatic control of temperature and pressure parameters, the entire preparation process is closed-loop automated. For example, if the flow ratio exceeds the set range, the system automatically triggers an alarm and re-collects data, avoiding imbalances caused by manual operation. The axially equidistant distribution of the rheometer probe and temperature sensor ensures spatial uniformity in data collection, reducing monitoring errors caused by measurement point position deviations, and enhancing the intelligence and standardization of the preparation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a working principle diagram of the method for preparing the high-pressure resistant and high-permeability polyurethane grouting material of the present invention;

[0056] Figure 2 This is the osmotic pressure calculation diagram based on viscosity gradient;

[0057] Figure 3 This is an analysis diagram of three-dimensional pressure distribution penetration;

[0058] Figure 4 Control chart for double calibration of raw material flow;

[0059] Figure 5 Design diagram of the unit architecture of the effect prediction system. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] See also Figure 1-Figure 5 The present invention relates to a method for preparing a high-pressure resistant and high-permeability polyurethane grouting material, and the specific implementation steps are as follows:

[0062] Step S1: Constructing a ratio optimization network and a temperature control network. Initial rheological parameters of the polyol and isocyanate components are first obtained. Using a rheological analysis model, these parameters are trained for multiple sets of different ratios to establish a ratio optimization network. This network can output corresponding ratio adjustment strategies based on the differences in rheological parameters. Simultaneously, multiple sets of reaction temperature curves are trained to obtain a temperature control network. This network can generate corresponding temperature control instructions based on the temperature data. Furthermore, based on the reaction time dimension, a correlation is established between the output parameters of the ratio optimization network and the temperature control network, forming a dynamic collaborative control model.

[0063] Step S2: Real-time data acquisition. The real-time rheological parameters of the polyol component and isocyanate component of the current batch are acquired. Simultaneously, the polymerization kettle temperature data is acquired during the acquisition of the real-time rheological parameters, providing real-time basic data for subsequent parameter analysis.

[0064] Step S3: Parameter Optimization and Control. Real-time rheological parameters are input into the ratio optimization network, and the network algorithm identifies the optimal ratio adjustment to optimize the raw material component ratio. The polymerization kettle temperature data is input into the temperature control network, and the network algorithm identifies and generates temperature control instructions to achieve dynamic control of the reaction temperature.

[0065] Step S4: Obtaining pressure data: The pressure sensor in the reaction system is used to obtain the current pressure monitoring value of the reaction system in real time, providing key data for the calculation of the osmotic pressure difference.

[0066] Step S5: Calculation of osmotic pressure difference: Based on the pressure sensor monitoring value, the real-time osmotic pressure difference of the reaction system is calculated through a specific algorithm. This parameter is used to characterize the osmotic performance status of the reaction system.

[0067] Step S6: Generate injection rate threshold value. Generate material injection rate threshold value based on real-time osmotic pressure difference, combined with material reaction characteristics and process requirements, as a basis for controlling material injection speed.

[0068] Step S7: Instruction Generation and Verification. First, determine whether the material injection rate threshold matches the optimal ratio adjustment amount. If so, obtain the set reaction temperature curve based on the correlation between the ratio optimization network and the temperature control network parameters. Then determine whether the temperature control instruction corresponds to the set reaction temperature curve. If so, generate a material synthesis instruction and start the material synthesis process. If not, generate a parameter correction instruction to modify the relevant network parameters or control strategy.

[0069] The present invention will be further described below in conjunction with Examples 1 to 5:

[0070] Example 1: The core of step S2 is to obtain the real-time rheological parameters of the polyol component and the isocyanate component of the current batch, and to synchronously collect the polymerization kettle temperature data. The implementation method is achieved through the collaborative design of hardware configuration, signal transmission logic and data acquisition process.

[0071] In terms of the hardware structure design of the polymerization kettle, a rheometer probe is set on the side wall of the polymerization kettle. The installation position of the rheometer probe must be able to directly contact the reaction system to ensure that the collected rheological parameters truly reflect the internal state of the system. The rheometer probe is connected to the data input terminal of the reaction controller. The connection method can be wired transmission (such as shielded cable) or wireless transmission (such as Bluetooth, Wi-Fi), but the stability and anti-interference ability of the signal transmission must be guaranteed to avoid data loss or distortion due to signal interruption or noise interference. The type of rheometer probe can be selected according to the characteristics of the reaction system. For example, a cone-plate rheometer probe can be used for high-viscosity systems, and a rotating cylinder rheometer probe can be used for low-viscosity systems. Its function is to monitor the viscosity, shear rate, shear stress and other rheological parameters of the reaction system in real time. These parameters are the key basis for judging whether the material ratio is reasonable and whether the reaction process is normal.

[0072] In the metering link of the raw material delivery pipeline, a first mass flow meter is installed on the outlet pipeline of the polyol storage tank, and a second mass flow meter is installed on the outlet pipeline of the isocyanate storage tank. The installation of the mass flow meter must comply with the pipeline design specifications to ensure the stability of the fluid flow state and avoid the fluid disturbance caused by pipeline elbows, valves and other components affecting the measurement accuracy. The two mass flow meters independently measure the real-time flow of the polyol component and the isocyanate component, and their measurement accuracy must meet the process requirements (such as ±0.1% FS) to achieve accurate monitoring of the feed amount of the two components. The output signal of the mass flow meter (such as 4-20mA current signal, RS485 digital signal) is connected to the input end of the reaction controller, so that the reaction controller can obtain the flow data of the two components in real time, providing basic data support for subsequent flow ratio verification and molar ratio calculation.

[0073] In terms of temperature monitoring of the polymerization kettle, three temperature sensors are equidistantly distributed axially inside the polymerization kettle. The purpose of equidistant axial distribution is to cover areas of different heights in the polymerization kettle, avoid the limitations of single-point temperature monitoring, and ensure that the temperature distribution of the reaction system in the vertical direction can be obtained. The type of temperature sensor can be a thermocouple or a thermistor. Its measurement range must cover the preset range of the reaction temperature (such as 0-200°C), and the accuracy must meet the process control requirements (such as ±0.5°C). The three temperature sensors are connected to the input end of the reaction controller through independent signal lines. The reaction controller can collect the temperature data of each sensor in real time, and process multiple temperature data through algorithms (such as taking the average value, judging the temperature gradient) to more accurately reflect the overall temperature state and distribution characteristics in the polymerization kettle.

[0074] In terms of control logic and data acquisition processes, when the reaction controller receives a reaction start signal, the real-time data acquisition program is triggered. The reaction start signal can be manually issued by the operator through the human-machine interface, or automatically generated by the upper control system according to a preset process sequence. After receiving the start signal, the output end of the reaction controller synchronously drives the rheometer probe and temperature sensor to start working: on the one hand, it sends an acquisition instruction to the rheometer probe, causing it to collect real-time rheological parameters at a set frequency (such as once per second) and feed the collected data back to the reaction controller via a signal transmission link; on the other hand, it sends an activation signal to the temperature sensor, causing it to enter a real-time monitoring state, continuously collect polymerization kettle temperature data and transmit it to the reaction controller. This synchronous drive mechanism ensures that the collection time points of rheological parameters and temperature data are consistent, avoiding data mismatches caused by time differences, thereby ensuring the accuracy of parameter associations in subsequent analysis.

[0075] To ensure the reliability of data collection, hardware equipment needs to be calibrated and maintained regularly. For example, the rheometer probe needs to be regularly zero-point calibrated and sensitivity checked to ensure the accuracy of rheological parameter measurements; the mass flow meter needs to be regularly calibrated for flow, which can be done with a standard volume container or a high-precision calibration device to ensure that the flow measurement error is within the allowable range; the temperature sensor needs to be regularly calibrated for temperature, which can be compared with a constant temperature bath or a standard temperature source to ensure the authenticity of the temperature measurement value. In addition, the software system of the reaction controller needs to have data filtering and outlier detection functions, which can pre-process the collected raw data, eliminate abnormal data points caused by factors such as equipment jitter and electromagnetic interference, and ensure the quality of data input to the ratio optimization network and temperature control network.

[0076] During actual operation, operators can view rheological parameters, temperature data, and flow information in real time through the human-machine interface of the reaction controller. The human-machine interface can be designed as a graphical interface, dynamically displaying the changing trends of various parameters in the form of curves, tables, etc., allowing operators to intuitively judge the status of the reaction system. For example, a sudden change in the rheological parameter curve may indicate an abnormal material ratio or a sudden change in reaction rate, abnormal fluctuations in temperature data may indicate a malfunction in the heating or cooling system, and deviations in flow information may indicate a blockage in the metering equipment or a leak in the pipeline. Operators can take appropriate adjustment measures in a timely manner according to the prompts on the interface, such as manually adjusting the ratio and checking the operating status of the equipment, thereby achieving manual intervention and monitoring of the preparation process.

[0077] Example 2: This example expands the calculation logic of step S5. The core of this example is to calculate the real-time molecular diffusion coefficient and material permeation path length of the reaction system by introducing a collaborative analysis of the viscosity gradient monitoring value and the pressure sensor monitoring value, thereby generating a reaction start signal. The details are as follows:

[0078] In the data collection process, it is necessary to obtain the viscosity gradient monitoring value and pressure sensor monitoring value of the current reaction system. The viscosity gradient monitoring value is collected in real time by a viscosity monitoring device installed in the polymerization kettle. The device can be composed of multiple viscosity sensors distributed radially or axially along the polymerization kettle. For example, sensors are installed at different radial positions or different height positions on the inner wall of the polymerization kettle to monitor the viscosity difference of the reaction system in the spatial dimension. The measurement principle of each viscosity sensor can be based on the rotation method, vibration method or ultrasonic method. The appropriate type needs to be selected according to the physical properties of the reaction system (such as viscosity range, fluidity) to ensure that subtle changes in the viscosity gradient can be accurately captured. The pressure sensor monitoring value is obtained by a pressure sensor installed inside the polymerization kettle or in the pipeline. The sensor must have high sensitivity and stability, and be able to respond to the dynamic fluctuations of the pressure in the reaction system in real time. Its measurement range must cover the pressure range that may occur in the preparation process.

[0079] In the parameter calculation stage, the real-time molecular diffusion coefficient of the reaction system is first calculated using the pressure sensor monitoring value and the viscosity gradient monitoring value. The molecular diffusion coefficient is a physical quantity that characterizes the diffusion ability of molecules in a medium. Its calculation requires a combination of fluid mechanics theory and the characteristic parameters of the reaction system. Specifically, the pressure sensor monitoring value reflects the overall pressure state of the reaction system, while the viscosity gradient monitoring value reflects the difference in viscous resistance in different regions of the system. By establishing a coupled model of pressure and viscosity gradient, the movement law of molecules to overcome viscous resistance under pressure drive is analyzed, and then the real-time molecular diffusion coefficient is derived. The construction of this model requires comprehensive consideration of factors such as the molecular structure of polyols and isocyanates, the chemical state of the reaction stage (such as the degree of prepolymer formation), etc., to ensure that the calculation results can truly reflect the actual ability of molecular diffusion.

[0080] After obtaining the real-time molecular diffusion coefficient, the material penetration path length is further calculated. The material penetration path length refers to the spatial distance in which the material can effectively diffuse and undergo chemical reactions in the reaction system. Its calculation requires a combination of the real-time molecular diffusion coefficient, reaction time, material characteristic parameters (such as molecular weight, diffusion activation energy) and the geometric structure parameters of the polymerization reactor (such as inner diameter and height). For example, by integrating the curve of the change of the molecular diffusion coefficient over time and combining it with the spatial coordinates of the reaction system, the diffusion distance of the material molecules in different directions can be simulated, thereby determining the specific length of the material penetration path. This process requires the use of numerical calculation methods (such as the finite difference method and the finite element method) to discretize the diffusion process in order to achieve accurate calculation of the penetration path in a complex three-dimensional space.

[0081] In the logic judgment and signal generation link, a reaction start signal is generated according to the length of the material penetration path. The triggering conditions of the reaction start signal need to be set in advance. For example, when the length of the material penetration path reaches a certain proportion of the diameter of the polymerization kettle (such as 80%) or the preset minimum effective reaction distance, it is considered that the material has been fully diffused and has the conditions for uniform reaction. At this time, a reaction start signal is generated. This signal can be transmitted to the stirring system, heating / cooling system and other actuators of the polymerization kettle through the output port of the reaction controller to trigger the formal start of the reaction program. If the material penetration path length does not reach the preset threshold, the real-time molecular diffusion coefficient and the material penetration path length will continue to be monitored until the conditions are met.

[0082] To ensure the accuracy of the calculation process, relevant parameters must be calibrated and verified. For example, viscosity monitoring devices require regular multi-point calibration, correcting for sensor measurement errors by testing in standard fluids of known viscosity. Pressure sensors must be calibrated using a standard pressure source to ensure pressure measurement accuracy. Furthermore, molecular diffusion models and permeation path calculation methods require theoretical verification and experimental calibration. By comparing simulation results with actual material diffusion experimental data (such as observing the material diffusion range through dye tracer methods), model parameters and calculation coefficients can be adjusted to improve model reliability.

[0083] In practical applications, the viscosity gradient and pressure state of the reaction system may be affected by a variety of factors, such as fluctuations in the raw material ratio, temperature changes, stirring rate, etc. Therefore, the implementation method of this embodiment needs to have dynamic adaptability and be able to respond to changes in these factors in real time and adjust the calculation results. For example, when a sudden increase in the temperature of the polymerization kettle is detected, the reaction controller can automatically call the temperature correction coefficient and adjust the calculation model of the molecular diffusion coefficient to reflect the effect of temperature changes on the molecular mobility; when it is found that the viscosity gradient increases abnormally, the system can automatically trigger an early warning mechanism to prompt the operator to check the raw material ratio or the operating status of the stirring device to avoid deviations in the calculation results due to abnormal parameters.

[0084] The system's monitoring interface allows operators to view dynamic changes in parameters such as viscosity gradient, pressure, real-time molecular diffusion coefficient, and material permeation path length in real time. The monitoring interface can be designed as a three-dimensional visualization model, visually displaying the distribution of viscosity and pressure within the reaction system and the expansion of the material permeation path. For example, by mapping the viscosity gradient with different colors, representing the pressure distribution with contour lines, and tracking the extension of the material permeation path with dynamic curves, operators can quickly understand the internal state of the reaction system, promptly identify potential problems, and take intervention measures.

[0085] Example 3: This example provides another implementation of step S5. This method uses pressure sensor monitoring values ​​to construct a three-dimensional pressure distribution model of the reaction system, thereby generating a reaction initiation signal. The specific implementation includes pressure data acquisition, three-dimensional region division, parameter calculation, signal generation, and system interaction, each of which is implemented through the coordinated hardware configuration and algorithmic logic.

[0086] Pressure data acquisition relies on pressure sensors installed inside the polymerization kettle or on key pipelines. The pressure sensor needs to have a multi-point layout feature, such as being evenly distributed at different heights on the top, bottom and side walls of the polymerization kettle to obtain the pressure value of the reaction system in the spatial dimension. The type of sensor can be a piezoresistive or capacitive pressure sensor, and its measurement accuracy must meet the process requirements (such as ±0.5% FS), and the measurement range covers 0 to the designed maximum reaction pressure (such as 150MPa). Each pressure sensor is connected to the reaction controller through an independent signal transmission line (such as a shielded cable) to ensure that real-time pressure data is transmitted to the system in a low-latency, high-fidelity manner.

[0087] During the three-dimensional pressure distribution area division phase, the reaction controller processes the pressure sensor monitoring values ​​using a three-dimensional spatial modeling algorithm. This algorithm, based on the principles of finite element analysis, discretizes the internal space of the polymerization reactor into multiple tiny cubic units (grids). The pressure value of each unit is calculated by interpolating the data from neighboring sensors. The specific formula is:

[0088]

[0089] Among them, P(x,y,z,t) represents the pressure value at the spatial coordinate (x,y,z) at time t, n is the number of sensors involved in interpolation, P i (t) is the pressure value measured by the i-th sensor at time t, w i (t) is the weight coefficient of the i-th sensor at time t. This coefficient is dynamically adjusted based on the spatial distance between the sensor and the target coordinates and the signal reliability (the closer the distance and the higher the reliability, the greater the weight). Using this formula, the system can construct a three-dimensional pressure distribution cloud map of the reaction system at any time, intuitively displaying the spatial distribution characteristics of pressure (such as the location and range of high-pressure and low-pressure areas).

[0090] After the area division is completed, the system needs to calculate the osmotic pressure difference change rate of each three-dimensional pressure distribution area. The osmotic pressure difference change rate reflects the rate of change of pressure in a specific area over time. The calculation formula is:

[0091]

[0092] Where ΔP rate(t) is the rate of change of the osmotic pressure difference at time t, P(t) is the average pressure value in the region at the current time, and P(t-Δt) is the average pressure value in the region at the previous time Δt (time interval, such as 1 second). This parameter is used to measure the stability of the pressure distribution: a large absolute value of the rate of change indicates that the pressure in the region is fluctuating violently, possibly due to uneven reaction or fluid disturbance; a rate of change close to zero indicates that the pressure state is stable.

[0093] Boundary intersection points are the intersections of two or more pressure distribution regions. Their coordinates are obtained by solving the intersection of pressure contour surfaces of different regions. For example, for high-pressure and low-pressure regions, the boundary is formed by contour surfaces corresponding to a pressure threshold (e.g., set at 80 MPa). The intersection of these contour surfaces is the region boundary, and the intersection of these boundaries is the intersection point. These coordinate points are key locations for sudden pressure changes, and their positional changes can reflect the movement of fluid interfaces within a reaction system or the direction of chemical reaction propagation.

[0094] In the reaction start signal generation logic, the system first presets the osmotic pressure difference change rate threshold (such as ±5MPa / s) and the trigger conditions of the boundary intersection coordinates (such as the intersection moving distance exceeds 10% of the diameter of the polymerization kettle). When the osmotic pressure difference change rate in any area exceeds the threshold, or the boundary intersection coordinate change meets the trigger conditions, the system determines that the reaction system has reached a pressure state suitable for starting the reaction and generates a reaction start signal. This signal is transmitted to the agitator, heating device and other actuators of the polymerization kettle through the digital output module to start the material mixing and chemical reaction process. If the conditions are not met, the pressure distribution changes are continuously monitored until the parameters meet the preset standards.

[0095] To ensure the accuracy of 3D modeling and parameter calculations, the system requires regular sensor calibration and algorithm verification. Sensor calibration is performed using a standard pressure source to ensure the absolute accuracy of pressure values ​​at each point. Algorithm verification compares actual pressure test data (such as placing a pressure test ball in a polymerization reactor to obtain multi-point measured values) with model calculation results, adjusting interpolation weight coefficients and regional division parameters to minimize the deviation between theoretical calculations and actual conditions.

[0096] The operator can use the human-machine interface to view real-time 3D pressure distribution cloud maps, osmotic pressure differential change rate curves for each region, and the coordinate dynamics of boundary intersection points. The interface offers interactive functions such as zooming in and out of the 3D model, selecting a specific region to view detailed parameters, and exporting historical data. For example, the operator can click on a high-pressure area to view the pressure trend and pressure differential data for that area and adjacent areas. By observing the movement of the boundary intersection point, the uniformity of material mixing and the speed of the reaction front can be determined, thereby assisting in adjusting process parameters (such as increasing stirring intensity to promote pressure homogenization).

[0097] In terms of hardware compatibility, the 3D pressure distribution analysis module can be integrated into the reaction controller's industrial-grade computer or distributed through edge computing nodes to reduce the computational load on the main controller. The data storage module simultaneously records pressure data, zoning results, and signal generation logs, facilitating subsequent process traceability and optimization. The network interface supports integration with factory-level monitoring systems, enabling remote real-time monitoring and process parameter adjustment.

[0098] Example 4: This example focuses on the flow control logic in step S2. Through real-time flow monitoring, ratio verification, and exception handling mechanisms, it ensures that the polyol component and the isocyanate component participate in the reaction in a precise ratio. Specific implementation method Taking the preparation process of a batch of polyurethane grouting materials as an example, the hardware configuration, control process, and interaction logic are detailed as follows:

[0099] During the raw material delivery process, the polyol storage tank and the isocyanate storage tank are connected to the polymerization kettle via independent pipelines. A first mass flowmeter is installed on the outlet pipeline of the polyol storage tank, and a second mass flowmeter is installed on the outlet pipeline of the isocyanate storage tank. Taking the example of polyether polyol as the polyol component and MDI (diphenylmethane diisocyanate) as the isocyanate component, the flow characteristics of the two materials differ significantly (polyether polyol has a higher viscosity, while MDI has a lower viscosity). Therefore, the mass flowmeter must be selected according to the material characteristics: a Coriolis mass flowmeter is used for the polyether polyol pipeline to ensure the metering accuracy of high-viscosity fluids; a thermal mass flowmeter is used for the MDI pipeline to meet the measurement requirements of low-viscosity, volatile fluids. The measuring range of both flowmeters is set according to the process design flow range (e.g., 0-50kg / h), with an accuracy of ±0.1%. Their output signals are connected to the reaction controller via a 4-20mA analog line.

[0100] When the operator triggers the "Feed Preparation" command on the human-machine interface (HMI), the reaction controller first initializes the flow monitoring program. The first and second mass flow meters begin to collect the first real-time flow value of the polyol component (denoted as Q1) and the second real-time flow value of the isocyanate component (denoted as Q2) in real time, and transmit the data to the controller memory. For example, using a preset material mass ratio of 3:1 (polyether polyol:MDI), the controller first determines whether the real-time ratio of Q1 to Q2 falls within the set ratio range (e.g., 3:1 ± 5%). If the ratio is between 2.85:1 and 3.15:1, it is considered to be within the set ratio range and the next step, molar ratio verification, is initiated. If the ratio exceeds this range, the controller immediately generates a flow anomaly alarm signal, notifying the operator through a flashing red warning light on the interface and an audible buzzer.

[0101] The molar ratio verification step requires calculations based on the material's molecular weight. The average molecular weight of the polyether polyol is set at 2000 g / mol, and the molecular weight of MDI is 250 g / mol. According to the chemical reaction equation, the ideal molar ratio of the two is 1:2. The controller calculates the real-time molar flow rate according to the formula "molar flow rate = mass flow rate / molecular weight": polyol molar flow rate n1 = Q1 / 2000, MDI molar flow rate n2 = Q2 / 250, and the ideal molar ratio threshold is n1:n2 = 1:2 (i.e., n2 = 8n1). The system presets a molar ratio tolerance of ±2%. This means that the verification passes when 7.84n1 ≤ n2 ≤ 8.16n1. If this range is exceeded, the controller determines that there is a stoichiometric deviation in the flow ratio and triggers the "reacquire flow value" command, closing the tank outlet valve, clearing the current flow data, and reopening the valve to collect flow until the verification passes.

[0102] For example, if Q1 = 30 kg / h and Q2 = 10 kg / h, the mass ratio is 3:1, which falls within the set ratio range. The molar flow rate is calculated as follows: n1 = 30,000 g / h ÷ 2,000 g / mol = 15 mol / h, and n2 = 10,000 g / h ÷ 250 g / mol = 40 mol / h. At this point, n2 = 2.67n1, significantly deviating from the ideal molar ratio of 8:1, indicating insufficient MDI flow. The controller determines that the calibration has failed and immediately closes the valves on both tanks. Clearing the data, it restarts the feed process until Q1 = 25 kg / h and Q2 = 10 kg / h. At this point, the mass ratio is 2.5:1 (exceeding the lower limit of the set ratio range of 2.85:1). The controller generates a flow anomaly alarm, prompting the operator to check the MDI tank outlet piping for blockage or flowmeter zero drift.

[0103] If both the flow rate ratio and molar ratio pass verification, the controller confirms that the current feed ratio meets the process requirements and triggers the subsequent data collection process: the rheometer probe is driven to collect real-time rheological parameters (such as viscosity and shear stress), while the temperature sensor in the polymerization vessel collects temperature data. This data is stored and combined with the flow rate information to form the initial parameter set for the batch reaction, which is used for real-time calculations in the ratio optimization network and the temperature control network.

[0104] In exception handling scenarios, if flow rate values ​​repeatedly fail to pass ratio or mole ratio verification, the system automatically locks the feed process and generates a detailed fault log, recording the time, value, verification results, and type of exception (such as ratio deviation or mole ratio imbalance) for each flow acquisition. Operators can use the log query function to trace the problem. For example, if an MDI flowmeter shows low flow in multiple measurements, it can be determined that the flowmeter is faulty or the pipeline valve is not open enough, requiring equipment shutdown and maintenance.

[0105] To enhance operational convenience, the human-machine interface features a "Flow Calibration" shortcut button, allowing operators to perform zero and span calibration on the mass flowmeter while the equipment is shut down. During calibration, the system automatically disables the feed control logic to prevent safety risks caused by misoperation. Furthermore, the interface provides a historical flow data curve query function, displaying flow fluctuation trends by hour, shift, and date, helping process engineers analyze feed stability and optimize tank pressure control or pipeline layout.

[0106] Example 5: This example is about the exception handling mechanism of step S7. Taking the scenario where the material injection rate threshold and the optimal ratio adjustment amount do not match during the preparation of a batch of polyurethane grouting materials as an example, the hardware configuration, data feedback process, and dynamic control logic are detailed as follows:

[0107] When the reaction system enters the parameter matching verification stage, the system first calculates the real-time osmotic pressure difference based on the pressure sensor monitoring value and generates a material injection rate threshold (such as setting it to 5-8L / min). At the same time, the ratio optimization network outputs the optimal ratio adjustment amount based on the real-time rheological parameters (such as recommending an increase of 0.5% mass ratio of the isocyanate component). If the comparison finds that the two do not match (such as the ratio adjustment amount corresponding to the maximum injection amount allowed by the rate threshold needs to be increased by 1.2%), the system determines that the permeability performance of the current reaction system and the raw material ratio have not been optimized synergistically, and the exception handling mechanism needs to be triggered.

[0108] At this time, the viscometer installed at the discharge port at the bottom of the reactor starts working. The viscometer uses a vibration measurement principle and can monitor the viscosity value of the discharge end of the reaction system in real time (measuring range 0-5000mPa·s, accuracy ±1%). Its sensor probe is directly immersed in the material flow to ensure that the measured value truly reflects the overall viscosity state of the system. Taking the reaction system of polyether polyol and MDI as raw materials as an example, the viscosity in the initial stage of a normal reaction is about 800mPa·s. If the reaction rate lags due to an imbalance in the ratio, the viscosity may remain below 500mPa·s. The viscometer transmits the real-time viscosity value (denoted as μ) to the reaction controller via the RS485 bus, forming a closed-loop feedback with the ratio optimization network and the permeation calculation unit.

[0109] After receiving the viscosity value, the reaction controller first calls up the viscosity-permeability correlation data for similar raw material ratios in the historical database. For example, when μ = 600 mPa·s is detected, the system finds that the optimal material injection rate threshold corresponding to this viscosity value should be 3-5 L / min, while the current set threshold is 5-8 L / min, indicating that the actual viscosity is low and the allowable injection rate should be reduced to avoid material scouring and unstable permeation paths. At the same time, the ratio optimization network recalculates the optimal ratio adjustment based on the viscosity feedback value: since the low viscosity may be due to insufficient isocyanate component, the network output adjustment is to increase the isocyanate mass ratio by 1.0%, and simultaneously correct the viscosity influencing factor in the osmotic pressure difference calculation model.

[0110] The system again compares the newly generated material injection rate threshold (3-5L / min) with the optimal ratio adjustment amount (+1.0% isocyanate) for compatibility. If the two match (for example, the adjusted ratio can increase the system viscosity to 800mPa·s, corresponding to the threshold of 5-8L / min), the temperature curve calibration process is entered; if they still do not match (for example, the viscosity rises to 700mPa·s but the threshold is still 3-5L / min), the viscometer continues to collect real-time viscosity at a frequency of 1 time per second, and the above calculation process is repeated. During this process, the operator can observe the viscosity curve fluctuation trend through the human-machine interface to determine whether manual intervention is required (such as checking whether the agitator speed is normal or whether there is a fault in the temperature control system).

[0111] Take another scenario as an example: If the viscosity of the reaction system increases abnormally (μ = 1200mPa·s) due to temperature fluctuations, exceeding the normal range (800-1000mPa·s), the material injection rate threshold is automatically lowered to 2-4L / min, and the ratio optimization network recommends reducing the polyol component by 0.8% to reduce viscosity. After system comparison, it was found that the minimum ratio adjustment corresponding to the lower threshold of 2L / min needs to be reduced by 1.2%, which is different from the recommended 0.8%. Therefore, the viscosity-ratio linkage adjustment is triggered: first perform a 0.8% ratio adjustment, wait 5 minutes for the materials to mix evenly, and then collect a new viscosity value (such as reducing it to 1050mPa·s). The threshold is recalculated to 3-6L / min, matching the remaining 0.4% ratio adjustment, and finally completing the parameter calibration.

[0112] At the hardware level, the discharge port viscometer adopts a quick-release structure design, which is convenient for rapid disassembly and cleaning during shutdown, avoiding the impact of material residue on measurement accuracy. The reaction controller has a built-in adaptive filtering algorithm that can denoise the real-time viscosity data, eliminate instantaneous spike data caused by stirring turbulence, and ensure that the viscosity value input to the model is a stable and effective value. At the same time, the system sets a viscosity over-limit alarm threshold (such as below 300mPa·s or above 1500mPa·s). If the collected values ​​exceed the threshold for three consecutive times, the emergency shutdown procedure is automatically triggered to prevent the polymerization kettle pressure from getting out of control due to abnormal viscosity.

[0113] For process traceability, each viscosity data collection, ratio adjustment record, and threshold generation result are stored in the database with a timestamp, allowing for quick retrieval by order or batch number. For example, three parameter mismatches occurred during the preparation of a batch of material. By querying the logs, operators discovered that the first mismatch was caused by insufficient opening of the isocyanate tank valve, resulting in a ratio deviation; the second mismatch was caused by a temperature sensor malfunction, resulting in viscosity fluctuations; and the third mismatch was caused by the algorithm model failing to promptly update the molecular weight data for the new batch of raw materials. Based on these records, the process department can optimize equipment maintenance plans, improve sensor calibration procedures, and update the training dataset for the ratio optimization network.

[0114] The human-machine interface provides a visualization module for "Viscosity-Ratio Linkage Adjustment," displaying the dynamic relationship between real-time viscosity (left axis) and ratio adjustment (right axis) as a dual-axis curve, allowing operators to intuitively observe the coupling relationship between the two. The module also offers a manual intervention option, allowing the program to be paused during the automatic adjustment process to enter empirical parameters for correction. After system verification, the corrected parameters can be incorporated into the historical database and used to optimize the control model for subsequent batches.

[0115] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0116] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for preparing a high-pressure resistant and high-permeability polyurethane grouting material, characterized in that: The methods include: Step S1, obtaining initial rheological parameters of a polyol component and an isocyanate component, training multiple sets of rheological parameters at different ratios using a rheological analysis model to obtain a ratio optimization network; training multiple sets of reaction temperature curves to obtain a temperature control network; and correlating output parameters of the ratio optimization network and the temperature control network based on reaction time; Step S2, obtaining real-time rheological parameters of the polyol component and the isocyanate component of the current batch, and polymerization kettle temperature data collected synchronously when obtaining the real-time rheological parameters; Step S3, identifying the real-time rheological parameters through the ratio optimization network to obtain the optimal ratio adjustment amount; identifying the polymerization kettle temperature data through the temperature control network to obtain the temperature control instruction; Step S4, obtaining the pressure sensor monitoring value of the current reaction system; Step S5, calculating the real-time osmotic pressure difference of the reaction system according to the monitoring value of the pressure sensor; Step S6, generating a material injection rate threshold according to the real-time osmotic pressure difference; Step S7: If the material injection rate threshold matches the optimal ratio adjustment amount, the set reaction temperature curve is obtained according to the correlation between the ratio optimization network and the temperature control network parameters; it is determined whether the temperature control instruction corresponds to the set reaction temperature curve. If so, a material synthesis instruction is generated; if not, a parameter correction instruction is generated.

2. The method for preparing a high-pressure-resistant and high-permeability polyurethane grouting material according to claim 1, wherein: The step S2 comprises: Step S21, installing a rheometer probe on the side wall of the polymerization vessel; the rheometer probe is connected to the data input terminal of the reaction controller; Step S22: a first mass flow meter is provided on the outlet pipeline of the polyol storage tank; a second mass flow meter is provided on the outlet pipeline of the isocyanate storage tank; Step S23, three temperature sensors are equidistantly distributed axially inside the polymerization kettle; the temperature sensors are connected to the input end of the reaction controller; Step S24: When the reaction controller receives a reaction start signal, the output end of the reaction controller drives the rheometer probe to collect real-time rheological parameters; and simultaneously drives the temperature sensor to collect polymerization kettle temperature data.

3. The method for preparing a high-pressure-resistant and high-permeability polyurethane grouting material according to claim 1, wherein: The step S5 includes: obtaining the viscosity gradient monitoring value of the current reaction system, calculating the real-time molecular diffusion coefficient of the reaction system according to the pressure sensor monitoring value and the viscosity gradient monitoring value; obtaining the material penetration path length according to the real-time molecular diffusion coefficient; and generating the reaction start signal according to the material penetration path length.

4. The method for preparing the high-pressure-resistant and high-permeability polyurethane grouting material according to claim 3, characterized in that: The step S5 also includes: dividing the three-dimensional pressure distribution area of ​​the reaction system according to the monitoring value of the pressure sensor; obtaining the osmotic pressure difference change rate of each area and the coordinates of the area boundary intersection point according to the three-dimensional pressure distribution area; and generating the reaction start signal according to the osmotic pressure difference change rate and the coordinates of the area boundary intersection point.

5. The method for preparing the high-pressure-resistant and high-permeability polyurethane grouting material according to claim 2, wherein: The step S22 includes: Obtaining a first real-time flow value of a polyol component and a second real-time flow value of an isocyanate component; Determine whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range; if so, verify the molar ratio of the first real-time flow rate value to the second real-time flow rate value based on the molecular weight ratio of the polyol to the isocyanate; if the verification passes, obtain the real-time rheological parameters and polymerization kettle temperature data; if not, return to this step to re-obtain the flow value; It is determined whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range. If not, a flow abnormality alarm signal is generated.

6. The method for preparing the high-pressure-resistant and high-permeability polyurethane grouting material according to claim 1, characterized in that: Step S7 includes: if the material injection rate threshold does not match the optimal ratio adjustment amount, obtaining a real-time viscosity value through a viscometer at the outlet of the reactor bottom, and returning to this step to determine whether the material injection rate threshold matches the optimal ratio adjustment amount.

7. A high-pressure-resistant and high-permeability polyurethane grouting material effect prediction system, characterized in that: Its systems include: A modeling unit is configured to obtain initial rheological parameters of a polyol component and an isocyanate component, train multiple sets of rheological parameters at different ratios using a rheological analysis model to obtain a ratio optimization network; train multiple sets of reaction temperature curves to obtain a temperature control network; and correlate output parameters of the ratio optimization network and the temperature control network based on reaction time; A monitoring unit configured to obtain real-time rheological parameters of the polyol component and the isocyanate component of the current batch, and polymerization kettle temperature data collected synchronously when obtaining the real-time rheological parameters; An analysis unit is configured to identify the real-time rheological parameters through the ratio optimization network to obtain an optimal ratio adjustment amount; and to identify the polymerization kettle temperature data through the temperature control network to obtain a temperature control instruction; A pressure acquisition unit configured to obtain a pressure sensor monitoring value of the current reaction system; an osmotic pressure calculation unit configured to calculate a real-time osmotic pressure difference of the reaction system according to the monitoring value of the pressure sensor; a rate generating unit configured to generate a material injection rate threshold according to the real-time osmotic pressure difference; The execution unit is configured to obtain a set reaction temperature curve based on the correlation between the ratio optimization network and the temperature control network parameters if the material injection rate threshold matches the optimal ratio adjustment amount; determine whether the temperature control instruction corresponds to the set reaction temperature curve, and if so, generate a material synthesis instruction; if not, generate a parameter correction instruction.

8. The high-pressure-resistant and high-permeability polyurethane grouting material effect prediction system according to claim 7, characterized in that: The monitoring unit is further configured to: A rheometer probe is arranged on the side wall of the polymerization kettle; the rheometer probe is connected to the data input terminal of the reaction controller; A first mass flow meter is provided on the outlet pipeline of the polyol storage tank; a second mass flow meter is provided on the outlet pipeline of the isocyanate storage tank; Three temperature sensors are equidistantly distributed axially inside the polymerization kettle; the temperature sensors are connected to the input end of the reaction controller; When the reaction controller receives a reaction start signal, the output end of the reaction controller drives the rheometer probe to collect real-time rheological parameters; and simultaneously drives the temperature sensor to collect polymerization kettle temperature data.

9. The high-pressure-resistant and high-permeability polyurethane grouting material effect prediction system according to claim 8, characterized in that: The permeation calculation unit is further configured to obtain a viscosity gradient monitoring value of the current reaction system, calculate a real-time molecular diffusion coefficient of the reaction system according to the pressure sensor monitoring value and the viscosity gradient monitoring value; obtain a material permeation path length according to the real-time molecular diffusion coefficient; and generate the reaction start signal according to the material permeation path length; or The permeation calculation unit is also configured to divide the three-dimensional pressure distribution area of ​​the reaction system according to the monitoring value of the pressure sensor; obtain the permeation pressure difference change rate of each area and the coordinates of the area boundary intersection point according to the three-dimensional pressure distribution area; and generate the reaction start signal according to the permeation pressure difference change rate and the coordinates of the area boundary intersection point.

10. The high-pressure-resistant and high-permeability polyurethane grouting material effect prediction system according to claim 7, characterized in that: The monitoring unit is further configured to: Obtaining a first real-time flow value of a polyol component and a second real-time flow value of an isocyanate component; Determine whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range; if so, verify the molar ratio of the first real-time flow rate value to the second real-time flow rate value based on the molecular weight ratio of the polyol to the isocyanate; if the verification passes, obtain the real-time rheological parameters and polymerization kettle temperature data; if not, return to this step to re-obtain the flow value; It is determined whether the first real-time flow rate value and the second real-time flow rate value reach a set ratio range. If not, a flow abnormality alarm signal is generated.

Images