Method and system for monitoring and dynamically regulating and controlling hydration heat in mass concrete pouring process

Abstract

The invention discloses a hydration heat monitoring and dynamic regulation and control method and system in a mass concrete pouring process, and relates to the technical field of concrete pouring, and the method comprises the steps: pre-burying a plurality of dual-mode temperature measurement probes in concrete, collecting dual-mode temperature field data in the concrete in real time, and synchronously collecting environmental parameters; carrying out preprocessing, dynamic weight distribution and data fusion on the obtained dual-mode temperature field data; according to the unsteady state heat transfer equation and the hydration heat model, a finite element heat conduction model is constructed, and the total hydration heat and the temperature difference trend are inverted through actually measured temperature field data; predicting a concrete core and surface temperature difference and a surface and environment temperature difference in a future set time period by combining an LSTM neural network model; and according to the predicted temperature difference result, the cooling water flow rate and the cooling water temperature are subjected to closed-loop regulation. Through the combination of dual-mode sensor temperature measurement and heat inversion, the hydration heat temperature difference in the concrete can be predicted in advance, a cooling scheme is regulated and controlled in real time in a linkage mode, and temperature stress cracks are avoided.

Description

Technical Field

[0001] The invention relates to the technical field of concrete pouring, and in particular to a method and system for monitoring and dynamically regulating hydration heat in a mass concrete pouring process. Background Art

[0002] During the pouring process of large-volume concrete caps, such as continuous rigid frame aqueducts, due to their large volume and one-time casting, there is a risk of violent release of hydration heat, which can easily cause temperature cracks.

[0003] At present, the traditional method for monitoring the temperature of large-volume concrete caps mainly relies on single-point temperature sensors, the most common of which are resistance temperature probes and vibrating-wire temperature probes. Among them, the resistance temperature probe reflects the temperature through resistance changes, which has low cost but is highly susceptible to environmental interference; the vibrating-wire temperature probe measures temperature through frequency changes, which has high accuracy but cannot be directly associated with heat.

[0004] It can be seen that the technical problems of single-point temperature sensors are: on the one hand, only monitoring the local temperature through temperature sensors cannot directly quantify the total hydration heat inside the concrete, resulting in delayed heat control; on the other hand, it is difficult to accurately judge the heat distribution by relying solely on temperature data, and it is impossible to adjust the cooling plan in real time, such as the water pipe flow rate and cooling water temperature.

[0005] Furthermore, the traditional temperature control system driven by a single temperature data mainly controls the opening and closing of the cooling water pipe according to the pre-set temperature threshold. This temperature control method has serious lag and lacks predictive ability, because it only relies on the currently measured temperature data and lacks the ability to predict the dynamic changes in the heat inside the concrete. During the rapid release of hydration heat of large-volume concrete foundations, the cooling water pipe is not started until the temperature reaches the threshold. At this time, a large amount of heat has accumulated inside the concrete, which may have caused potential damage to the concrete structure and cannot effectively prevent the occurrence of temperature cracks. Summary of the invention

[0006] In a first aspect of the present invention, in order to solve the above technical problems, a method for monitoring and dynamically controlling hydration heat during mass concrete pouring is provided, the method comprising: Embed a number of dual-mode temperature measuring probes in the concrete to collect dual-mode temperature field data inside the concrete in real time and simultaneously collect environmental parameters; wherein the dual-mode temperature measuring probes integrate resistive and vibrating-wire sensors or resistive and fiber grating sensors; Preprocessing the acquired dual-mode temperature field data to eliminate electromagnetic interference and vibration noise, and dynamically assigning weights and fusing the dual-mode temperature field data to output calibrated measured temperature field data; According to the non-steady-state heat transfer equation and the hydration heat model, a finite element heat conduction model is constructed, and the total hydration heat and temperature difference trend are inverted through the measured temperature field data; the temperature difference between the concrete core and the surface and the temperature difference between the surface and the environment in the future set period are predicted by combining the LSTM neural network model; According to the temperature difference results predicted by the LSTM neural network model, the cooling water flow rate and cooling water temperature are closed-loop regulated through a dynamic optimization strategy to ensure that the temperature difference fluctuation is stable within a safe threshold.

[0007] Furthermore, the temperature difference result predicted by the LSTM neural network model triggers hierarchical regulation: When the predicted temperature difference exceeds the primary threshold, the cooling water flow rate is increased according to the PID control algorithm; When the predicted temperature difference result exceeds the secondary threshold, the refrigerator is started to lower the cooling water temperature.

[0008] Furthermore, the adjustment step size of the cooling water flow rate is ±0.2 m / s; and the adjustment step size of the cooling water temperature is ±2°C.

[0009] Furthermore, the cooling water flow rate is increased according to the PID control algorithm, which satisfies the expression:

[0010] In the formula, is the deviation between the predicted temperature difference and the target value; is the current cooling water flow rate; , , are proportional coefficient, integral coefficient and differential coefficient respectively, and the above , , The parameter setting of .

[0011] Furthermore, the dynamic optimization strategy includes rolling time domain control and exception handling mechanism, wherein: The rolling time domain control is to optimize the control sequence of the cooling water flow rate and cooling water temperature at the future rated time in a fixed cycle; The abnormal handling mechanism is that if the temperature difference drop rate after three or more consecutive adjustments is less than <5%, the expert system diagnosis is triggered.

[0012] Furthermore, the objective function of the rolling horizon control is:

[0013] In the formula, To control the number of times; is the temperature difference; is the flow rate of the cooling water; is the temperature of the cooling water.

[0014] Furthermore, the preprocessing of the obtained dual-mode temperature field data specifically includes: Unify the sampling time of the dual-mode sensors based on the interpolation method; Adopt the 3σ criterion to eliminate data points exceeding ±3 times the standard deviation; Perform wavelet noise reduction and electromagnetic interference compensation on the resistive sensor data; perform median filtering and vibration compensation on the vibrating wire sensor data.

[0015] Furthermore, the dynamic weight assignment and data fusion of the dual-mode temperature field data specifically include: Calculate the confidence index of the dual-mode sensors integrated in the dual-mode temperature measurement probe respectively: , where is the confidence index of the resistive sensor in the dual-mode temperature measurement probe, is the confidence index of the vibrating wire sensor in the dual-mode temperature measurement probe; is the short-term temperature standard deviation of the resistive sensor in the dual-mode temperature measurement probe, is the short-term temperature standard deviation of the vibrating wire sensor in the dual-mode temperature measurement probe; Determine the fusion coefficient of the dual-mode data according to the environmental interference intensity : ; Calculate the fusion temperature of the dual-mode data, which satisfies the expression:

[0016] In the formula, , are the collected dual-mode temperature field data respectively.

[0017] Furthermore, the finite element heat conduction model is constructed through the following steps: Use non-uniform hexahedron meshes to divide the concrete structure, and use tetrahedron meshes to encrypt near the cooling pipes; Embed the hydration heat model , which satisfies the expression:

[0018] In the formula, is the total hydration heat, with the unit of J / m³; is the degree of hydration: , where are relevant material parameters and are iteratively updated by the Levenberg-Marquardt algorithm to minimize the residual between the measured temperature field data and the predicted temperature field data.

[0019] Further, the step of inversely calculating the total hydration heat from the measured temperature field data is: inputting the measured temperature field data into the unsteady heat transfer equation to inversely calculate the total hydration heat , where the unsteady heat transfer equation satisfies the expression:

[0020] In the formula, is the concrete density, with the unit of kg / m³; is the specific heat capacity of concrete, with the unit of J / (kg·K); is the thermal conductivity of concrete, with the unit of W / (m·K); is the boundary heat exchange amount, with the unit of W / m³.

[0021] Further, the training method of the LSTM neural network model includes: Its input includes the historical temperature sequences of the concrete core and surface, the environmental parameters, the cooling water flow rate, and the cooling water temperature; Its output is the temperature prediction value for a future set time period; The loss function of the LSTM neural network model uses the mean square error.

[0022] In the second aspect of the present invention, a hydration heat monitoring and dynamic regulation system for mass concrete pouring is provided, including: A dual-mode temperature measurement probe, which is embedded inside the concrete foundation, and the dual-mode temperature measurement probe is integrated with a resistive and vibrating wire sensor or a resistive and fiber Bragg grating sensor; A dual-mode data fusion module, configured to receive the original data of the dual-mode temperature measurement probe and output the calibrated measured temperature field data through a dynamic weighted fusion algorithm; A finite element heat conduction model, which constructs a three-dimensional heat conduction model of concrete based on the unsteady heat transfer equation; A heat inversion module, which iteratively updates the relevant parameters in the finite element heat conduction model by using an optimization algorithm, and predicts the temperature difference between the concrete core and surface and the temperature difference between the surface and the environment for a future set time period according to the optimized parameters, in combination with the LSTM neural network model; and A dynamic regulation module, configured to trigger the hierarchical regulation of the cooling water flow rate and the cooling water temperature according to the comparison result between the predicted temperature difference result and the threshold, and trigger the finite element heat conduction model to recalculate the temperature field.

[0023] Furthermore, the three-dimensional heat conduction model of the concrete satisfies the expression:

[0024] In the formula, is the density of the concrete, with the unit of kg / m³; is the specific heat capacity of the concrete, with the unit of J / (kg·K); is the thermal conductivity of the concrete, with the unit of W / (m·K); is the boundary heat exchange amount, with the unit of W / m³; is the total hydration heat amount, with the unit of J / m³; is a relevant material parameter and is preset according to the type of concrete.

[0025] Preferably, the dual-mode temperature measurement probe is provided with a stainless steel armored shell and is cooperated with epoxy resin potting. One end of the stainless steel armored shell leads out a vibrating wire signal line and an RTD lead from the inside to the outside; the dual-mode sensors are separated by a stainless steel partition wall. Among them, the vibrating wire sensor is provided with an invar frame.

[0026] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: By combining the temperature measurement of the dual-mode sensor with heat inversion, the present invention realizes the early prediction of the internal hydration heat temperature difference of the concrete during the pouring process of the concrete pile cap, and then realizes the real-time linkage control of the cooling scheme, greatly avoiding the occurrence of temperature stress cracks. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 is the flow block diagram disclosed in the embodiment of the present invention; Figure 2 is the overall framework diagram disclosed in the embodiment of the present invention; Figure 3 is the system architecture flow chart disclosed in the embodiment of the present invention; Figure 4 is the structural schematic diagram of the dual-mode temperature measurement probe disclosed in the embodiment of the present invention.

[0029] In the figure: 100. Dual-mode temperature measurement probe; 101. Stainless steel armored shell; 102. Epoxy resin filler; 103. Stainless steel partition wall; 104. 4-core waterproof cable; 110, platinum resistance wire; 111, ceramic substrate; 112, 2-core RTD lead wire; 120. Excited body; 121. Excitation / pickup coil; 122. Steel string; 123. 2-core vibrating string signal line; 124. Invar frame. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0031] The present invention aims to provide a method and system for monitoring and dynamically controlling the hydration heat during the pouring of large-volume concrete, so as to solve the problems that, on the one hand, the total hydration heat inside the concrete cannot be directly quantified during the traditional pouring of large-volume concrete caps; on the other hand, the hydration heat temperature difference cannot be predicted in advance and the cooling scheme cannot be adjusted in real time.

[0032] See also Figure 1-2 The method for monitoring and dynamically controlling hydration heat during mass concrete pouring provided by the present invention comprises the following steps: S1. Pre-embed several dual-mode temperature probes in the concrete to collect real-time dual-mode temperature field data inside the concrete and simultaneously collect environmental parameters. The dual-mode temperature probes integrate resistive and vibrating-string sensors or resistive and fiber grating sensors. Environmental parameters include wind speed, humidity and sunshine intensity.

[0033] The following is an explanation using resistive and vibrating-wire sensors as examples.

[0034] The resistive sensor preferably uses a Pt100 platinum resistor with a range of -50°C to 150°C, which is encapsulated in a 316L stainless steel housing and can withstand the alkaline environment of concrete. The resistive sensor needs to be calibrated in an ice-water mixture (0°C) and boiling water (100°C) before use.

[0035] The preferred vibrating wire material of the vibrating wire sensor is tungsten steel, and its frame is invar steel (thermal expansion coefficient ≤ 1.2×10 -6 / ℃) to reduce non-target thermal strain interference; built-in triaxial MEMS accelerometer with a range of ±5g for vibration compensation. The vibrating wire sensor is fixed on the steel frame, and the vibrating wire must be pre-tensioned according to the manufacturer's requirements before installation to ensure that the frequency output is within the calibration range.

[0036] The dual-mode temperature probes are arranged in a three-dimensional grid in the concrete foundation. Optionally, the core area (≥1.5m from the surface) has a spacing of 0.5 m; the surface area has a spacing of 1.0 m. The dual-mode temperature probes are led out to the data acquisition module through a 4-core waterproof cable 104. The resistive sensor adopts a 4-wire wiring method, a constant current source drive, and a voltage resolution of ≤1μV; the vibrating string sensor is electromagnetically excited (frequency 800~1200 Hz), and the signal is transmitted to the reader through a shielded cable, and the frequency resolution is ≤0.1 Hz.

[0037] S2. Preprocess the acquired dual-mode temperature field data to eliminate electromagnetic interference and vibration noise, and dynamically assign weights and fuse the dual-mode temperature field data to output calibrated measured temperature field data.

[0038] The process of dual-mode temperature field data preprocessing mainly includes the following steps: The sampling time of dual-mode sensors is unified based on the interpolation method; the 3σ criterion is used to eliminate data points exceeding ±3 times the standard deviation; wavelet noise reduction and electromagnetic interference compensation are performed on the resistive sensor data; median filtering and vibration compensation are performed on the vibrating string sensor data.

[0039] Regarding the dynamic weight allocation and data fusion of dual-mode temperature field data, specifically including: S21. Calculate the confidence index of the dual-mode sensor integrated in the dual-mode temperature measuring probe respectively: ,in, It is the confidence index of the resistive sensor in the dual-mode temperature probe. It is the confidence index of the vibrating wire sensor in the dual-mode temperature probe; is the short-term temperature standard deviation of the resistive sensor in the dual-mode temperature probe, is the short-term temperature standard deviation of the vibrating wire sensor in the dual-mode temperature probe.

[0040] S22. Determine the fusion coefficient of dual-mode data according to the intensity of environmental interference : .

[0041] S23, calculate the fusion temperature of the dual-mode data, which satisfies the expression:

[0042] In the formula, , They are the collected dual-mode temperature field data respectively.

[0043] S3. Based on the unsteady heat transfer equation and the hydration heat model, a finite element heat conduction model is constructed, and the total hydration heat and the temperature difference trend are inverted through the measured temperature field data; combined with the LSTM neural network model, the temperature difference between the core and the surface of the concrete and the temperature difference between the surface and the environment in a future set period are predicted.

[0044] In a further solution of this embodiment, the construction of the finite element heat conduction model includes the following steps: S31. The concrete structure is divided by non-uniform hexahedral meshes, and the tetrahedral meshes are encrypted near the cooling pipes.

[0045] S32. Embed the hydration heat model , which satisfies the expression:

[0046] In the formula, is the total hydration heat, and the unit is J / m³; is the degree of hydration: , where are the relevant material parameters and are iteratively updated by the Levenberg-Marquardt algorithm to minimize the residual between the measured temperature field data and the predicted temperature field data.

[0047] This finite element model provides an accurate forward calculation tool for the heat inversion algorithm. By adjusting the material parameters and the hydration heat parameters , the measured temperature field data can be iteratively approximated.

[0048] In this embodiment, the forward calculation of the finite element heat conduction model is discretized in time using the Crank-Nicolson format, and the calculation speed is improved by GPU parallel computing.

[0049] In a further solution of this embodiment, the process of inverting the total hydration heat through the measured temperature field data includes the following steps: S33. Input the measured temperature field data into the unsteady heat transfer equation to invert the total hydration heat , where the unsteady heat transfer equation satisfies the expression:

[0050] In the formula, is the concrete density, and the unit is kg / m³; is the specific heat capacity of the concrete, and the unit is J / (kg·K); is the thermal conductivity of the concrete, and the unit is W / (m·K); is the boundary heat exchange amount, and the unit is W / m³.

[0051] S34, call the finite element heat conduction model to calculate the temperature field .

[0052] S35. Calculate residuals ,If the residual is larger than 1.0℃, the formula parameters are updated by the Levenberg-Marquardt algorithm.

[0053] S36. Repeat the iteration until the residual converges or the maximum number of iterations is reached.

[0054] In a further scheme of this embodiment, the training method of the LSTM neural network model includes: its input includes the historical temperature series of the concrete core and surface, environmental parameters, cooling water flow rate and cooling water temperature; its output is the temperature prediction value of the future set time period; wherein, the loss function of the LSTM neural network model adopts mean square error.

[0055] S4. Based on the temperature difference results predicted by the LSTM neural network model, the cooling water flow rate and cooling water temperature are closed-loop controlled through a dynamic optimization strategy to ensure that the temperature difference fluctuation is stable within the safety threshold.

[0056] In this embodiment, hierarchical regulation is triggered according to the temperature difference result predicted by the LSTM neural network model: When the predicted temperature difference exceeds the primary threshold (ΔT ≥ 22° C. in this embodiment), the cooling water flow rate is increased according to the PID control algorithm.

[0057] When the predicted temperature difference exceeds the secondary threshold (ΔT≥25° C. in this embodiment), the refrigerator is started to reduce the cooling water inlet temperature.

[0058] When the predicted temperature difference reaches the threshold of the fuse mechanism (ΔT ≥ 28°C in this embodiment), pouring is suspended, liquid nitrogen emergency refrigeration is started, and an alarm signal is pushed to the monitoring terminal.

[0059] Optionally, the adjustment step of the cooling water flow rate is ±0.2 m / s; the adjustment step of the cooling water temperature is ±2°C.

[0060] In a further solution of this embodiment, the cooling water flow rate is increased according to the PID control algorithm, which satisfies the expression:

[0061] In the formula, is the deviation between the predicted temperature difference and the target value; is the current cooling water flow rate; , , are proportional coefficient, integral coefficient and differential coefficient respectively, according to the Ziegler-Nichols method , , parameter tuning of .

[0062] In this embodiment, regarding the dynamic optimization strategy, it mainly includes rolling horizon control and exception handling mechanism.

[0063] Rolling horizon control: That is, optimize the control sequence of the future rated time cooling water flow rate and cooling water temperature at a fixed period. In this embodiment, the control sequence of the next 2 hours is re-optimized every 30 minutes. The objective function of the rolling horizon control is:

[0064] In the formula, is the number of regulation times; is the temperature difference; is the cooling water flow rate; is the cooling water temperature.

[0065] Exception handling mechanism: That is, if the temperature difference reduction rate is less than <5% after three or more consecutive regulations, the expert system diagnosis is triggered, and the possible reasons include sensor failure, material parameter deviation, etc.

[0066] Through the above closed-loop control system, the engineering-level temperature control objectives of temperature difference prediction accuracy of ±1.5°C, regulation response time of <15 minutes, and maximum temperature difference fluctuation of ≤3°C can be achieved.

[0067] Please refer to Figure 3-4 , the present invention also provides a hydration heat monitoring and dynamic regulation system for the large-volume concrete pouring process using the above method, which mainly includes: dual-mode temperature measurement probe, dual-mode data fusion module, finite element heat conduction model, heat inversion module, dynamic regulation module, edge computing module and digital twin platform.

[0068] The dual-mode temperature measurement probe is embedded inside the concrete pile cap, and the dual-mode temperature measurement probe is integrated with a resistive and vibrating wire sensor or a resistive and fiber Bragg grating sensor.

[0069] The dual-mode data fusion module is used to receive the original data of the dual-mode temperature measurement probe and output the calibrated measured temperature field data through the dynamic weighted fusion algorithm.

[0070] The finite element heat conduction model is based on the unsteady heat transfer equation to construct a three-dimensional heat conduction model of concrete, and the three-dimensional heat conduction model of concrete satisfies the expression:

[0071] In the formula, is the concrete density, and the unit is kg / m³; is the specific heat capacity of concrete, and the unit is J / (kg·K); is the thermal conductivity of concrete, with the unit of W / (m·K); is the boundary heat exchange quantity, with the unit of W / m³; is the total hydration heat quantity, with the unit of J / m³; is a relevant material parameter and is preset according to the type of concrete.

[0072] The heat inversion module uses an optimization algorithm to iteratively update the relevant parameters in the finite element heat conduction model. According to the optimized parameters, combined with the LSTM neural network model, it predicts the temperature difference between the core and the surface of the concrete and the temperature difference between the surface and the environment in a set future period.

[0073] The dynamic regulation module is configured to trigger the hierarchical regulation of the cooling water flow rate and the cooling water temperature according to the comparison result between the predicted temperature difference result and the threshold, and trigger the finite element heat conduction model to recalculate the temperature field.

[0074] The edge computing module is used to deploy the FPGA chip on one side of the dual-mode sensor to achieve a fusion computing delay < 50ms.

[0075] The digital twin platform is used to establish the three-dimensional temperature field mapping relationship between the dual-mode sensor and the concrete structure, correct the spatial temperature measurement deviation, and construct the three-dimensional heat conduction model of the concrete.

[0076] In this embodiment, the dual-mode temperature measurement probe 100 is provided with a stainless steel armored shell 101, which is filled with an epoxy resin filler 102. The dual-mode sensors are separated by a stainless steel partition wall 103. One end of the stainless steel armored shell 101 leads out a 4-core waterproof cable 104 from the inside to the outside.

[0077] The resistive sensor includes a platinum resistance wire 110, a ceramic substrate 111, and a 2-core RTD lead 112. The vibrating wire sensor includes a stimulator 120 and an excitation / pickup coil 121 arranged in parallel. The stimulator 120 and the excitation / pickup coil 121 are arranged on the axial direction of the steel wire 122, and a 2-core vibrating wire signal line 123 is led out. The vibrating wire sensor is also provided with an invar frame 124.

[0078] The present invention can use a fiber Bragg grating sensor to replace the vibrating wire sensor to achieve higher-precision temperature measurement. Its technical solution needs to redesign the data fusion algorithm, but the core heat inversion logic remains unchanged.

[0079] In addition, the present invention can also use the LSTM neural network model to replace the finite element heat conduction model to directly predict the heat distribution and simplify the complexity of the physical model. Its technical solution needs to rely on a large amount of historical data for training.

[0080] The core innovation of the present invention lies in the combination of dual-mode temperature measurement and heat inversion. The above alternative solutions can achieve similar goals in specific scenarios, but the technical solution provided by the present invention has more advantages in engineering applicability and cost control.

[0081] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete, characterized in that, The method comprises: Embed a number of dual-mode temperature measuring probes in the concrete to collect dual-mode temperature field data inside the concrete in real time and simultaneously collect environmental parameters; wherein the dual-mode temperature measuring probes integrate resistive and vibrating-wire sensors or resistive and fiber grating sensors; Preprocessing the acquired dual-mode temperature field data to eliminate electromagnetic interference and vibration noise, and dynamically assigning weights and fusing the dual-mode temperature field data to output calibrated measured temperature field data; According to the non-steady-state heat transfer equation and the hydration heat model, a finite element heat conduction model is constructed, and the total hydration heat and temperature difference trend are inverted through the measured temperature field data; the temperature difference between the concrete core and the surface and the temperature difference between the surface and the environment in the future set period are predicted by combining the LSTM neural network model; According to the temperature difference results predicted by the LSTM neural network model, the cooling water flow rate and cooling water temperature are closed-loop regulated through a dynamic optimization strategy to ensure that the temperature difference fluctuation is stable within a safe threshold.

2. The monitoring method for hydration heat and dynamic regulation method during the casting process of mass concrete according to claim 1, wherein The temperature difference result predicted by the LSTM neural network model triggers hierarchical regulation: When the predicted temperature difference exceeds the primary threshold, the cooling water flow rate is increased according to the PID control algorithm; When the predicted temperature difference result exceeds the secondary threshold, the refrigerator is started to lower the cooling water temperature.

3. The hydration heat monitoring and dynamic regulation method for mass concrete pouring process according to claim 2, characterized in that The adjustment step of the cooling water flow rate is ±0.2 m / s; the adjustment step of the cooling water temperature is ±2°C.

4. The method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete according to claim 2, wherein The cooling water flow rate is increased according to the PID control algorithm, which satisfies the expression: In the formula, is the deviation between the predicted temperature difference and the target value; is the current cooling water flow rate; , , are the proportional coefficient, integral coefficient, and differential coefficient respectively, and the parameters of , , are set according to the Ziegler-Nichols method, where .

5. The method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete according to claim 1, wherein The dynamic optimization strategy includes rolling time domain control and exception handling mechanism, wherein: The rolling time domain control is to optimize the control sequence of the cooling water flow rate and the cooling water temperature at the future rated time in a fixed cycle; The abnormal handling mechanism is that if the temperature difference drop rate after three or more consecutive adjustments is less than <5%, the expert system diagnosis is triggered.

6. The method for monitoring hydration heat and dynamic regulation during the casting process of mass concrete according to claim 5, characterized in that, The objective function of the rolling horizon control is: In the formula, is the number of regulation times; is the maximum temperature difference inside and outside during the th regulation; is the flow rate of the cooling water; is the temperature of the cooling water.

7. The method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete according to claim 1, wherein The preprocessing of the acquired dual-mode temperature field data specifically includes: Unify the sampling time of dual-mode sensors based on interpolation method; The 3σ criterion was used to eliminate data points exceeding ±3 times the standard deviation; Wavelet noise reduction and electromagnetic interference compensation are performed on the resistive sensor data; median filtering and vibration compensation are performed on the vibrating string sensor data.

8. The method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete according to claim 1, characterized in that The dynamic weight allocation and data fusion of the dual-mode temperature field data specifically includes: Calculate the confidence index of the dual-mode sensors integrated in the dual-mode temperature measurement probe respectively: , where is the confidence index of the resistive sensor in the dual-mode temperature measurement probe, is the confidence index of the vibrating wire sensor in the dual-mode temperature measurement probe; is the short-term temperature standard deviation of the resistive sensor in the dual-mode temperature measurement probe, is the short-term temperature standard deviation of the vibrating wire sensor in the dual-mode temperature measurement probe; Determine the fusion coefficient of dual-mode data according to the environmental interference intensity : ; The fusion temperature of the dual-mode data is calculated, which satisfies the expression: In the formula, and are respectively the collected dual-mode temperature field data.

9. The method for monitoring and dynamically regulating the hydration heat during the casting process of mass concrete according to claim 1, wherein The finite element heat conduction model is constructed by the following steps: The concrete structure is divided by non-uniform hexahedral mesh, and the tetrahedral mesh is used to encrypt the area near the cooling pipe. Embedding the hydration heat model , which satisfies the expression: In the formula, is the total hydration heat, with the unit of J / m³; is the degree of hydration: , where are relevant material parameters and are iteratively updated by the Levenberg-Marquardt algorithm to minimize the residual between the measured temperature field data and the predicted temperature field data.

10. The method for monitoring and dynamically controlling the hydration heat during the casting process of mass concrete according to claim 9, wherein The steps for inversely calculating the total hydration heat from the measured temperature field data are as follows: input the measured temperature field data into the unsteady heat transfer equation to inversely calculate the total hydration heat , where the unsteady heat transfer equation satisfies the expression: In the formula, is the density of concrete, with the unit of kg / m³; is the specific heat capacity of concrete, with the unit of J / (kg·K); is the thermal conductivity of concrete, with the unit of W / (m·K); is the boundary heat exchange amount, with the unit of W / m³.

11. The method for monitoring hydration heat and dynamic regulation during the casting process of mass concrete according to claim 1, wherein The training method of the LSTM neural network model includes: Its input includes the historical temperature series of the concrete core and surface, the environmental parameters, the cooling water flow rate and the cooling water temperature; Its output is the predicted temperature value for the future set period; The loss function of the LSTM neural network model adopts mean square error.

12. A hydration heat monitoring and dynamic regulation system for mass concrete pouring process, characterized in that, include: A dual-mode temperature measuring probe, which is pre-buried in the concrete cap, and the dual-mode temperature measuring probe integrates a resistive and vibrating-wire sensor or a resistive and fiber grating sensor; A dual-mode data fusion module, configured to receive the original data of the dual-mode temperature measurement probe and output calibrated measured temperature field data through a dynamic weighted fusion algorithm; A finite element heat conduction model, which constructs a three-dimensional concrete heat conduction model based on the unsteady heat transfer equation; A heat inversion module, which uses an optimization algorithm to iteratively update the relevant parameters in the finite element heat conduction model. According to the optimized parameters, it combines with the LSTM neural network model to predict the temperature difference between the core and the surface and the temperature difference between the surface and the environment of the concrete in a future set period; and A dynamic regulation module, configured to trigger the hierarchical regulation of the cooling water flow rate and the cooling water temperature according to the comparison result between the predicted temperature difference result and the threshold, and trigger the finite element heat conduction model to recalculate the temperature field.

13. The hydration heat monitoring and dynamic regulation system for mass concrete pouring process according to claim 12, characterized in that, The three-dimensional concrete heat conduction model satisfies the expression: In the formula, is the density of concrete, with the unit of kg / m³; is the specific heat capacity of concrete, with the unit of J / (kg·K); is the thermal conductivity of concrete, with the unit of W / (m·K); is the boundary heat exchange amount, with the unit of W / m³; is the total heat of hydration, with the unit of J / m³; is the relevant material parameter and is preset according to the type of concrete.

14. The hydration heat monitoring and dynamic regulation system for mass concrete pouring process according to claim 12, characterized in that, The dual-mode temperature measurement probe is provided with a stainless steel armored shell and is cooperated with epoxy resin potting. One end of the stainless steel armored shell leads out a vibrating wire signal line and an RTD lead from the inside to the outside; the dual-mode sensors are separated by a stainless steel partition wall. Among them, the vibrating wire sensor is provided with an invar frame.

Images