Internet of Things temperature control method and system for precooled concrete production

Abstract

The invention discloses a pre-cooled concrete production Internet of Things temperature control system and method, and the system comprises a region delimiting module, a temperature control module, an environment data obtaining module, a data analysis and reasoning module, an equipment control module and a visual display module, all the modules cooperate with one another, and precise temperature control of different pre-cooled concrete production regions is achieved. The system uses a laser radar point cloud and hyperspectral image imaging technology to demarcate different temperature control areas, and the fiber bragg grating temperature sensing network array, the model prediction MPC controller and the magnetic suspension frequency conversion refrigeration assembly ensure accurate temperature control. Meanwhile, the data analysis reasoning module is combined with a deep learning time sequence prediction model and a reasoning rule mining algorithm to provide support for production equipment to assist temperature control; according to the overall temperature control scheme, the intelligence and precision of temperature control of the pre-cooled concrete production Internet of Things are improved, and the method is suitable for various pre-cooled concrete production scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent temperature control of pre-cooled concrete, and in particular to an Internet of Things temperature control method and system for pre-cooled concrete production. Background Art

[0002] With the continuous development of the construction industry, concrete has been widely used in various construction projects. However, temperature control has always been a key factor affecting concrete quality during the concrete production process. Especially for large-volume concrete, the temperature stress and shrinkage stress generated by the heat of cement hydration can cause cracks in the concrete structure, affecting its durability and safety. Traditional concrete temperature control methods rely primarily on manual monitoring and simple cooling water circulation systems, which are subject to problems such as data collection lag, inaccurate monitoring data, and low temperature control efficiency.

[0003] In recent years, the rapid development of the Internet of Things (IoT) has provided new solutions for concrete temperature control. IoT technology enables interconnectivity between devices, collects real-time temperature data from the concrete production process through sensors, and leverages network transmission and data analysis to achieve temperature control.

[0004] However, most existing temperature control systems focus on temperature control throughout the entire production process. However, temperature control throughout the concrete production process is very complex, making it difficult to achieve precise temperature control throughout the entire process. Less attention has been paid to temperature control during the pouring and curing process of concrete production. During the pouring and curing process of concrete production, the layout of the pouring structure, environmental factors, and the setting of pouring and curing equipment parameters all have a significant impact on the final quality of the concrete. Therefore, developing an IoT-based pre-cooling concrete production temperature control method and system that can monitor and control the temperature of the pouring and curing process during concrete production is of great significance for improving concrete quality. Summary of the Invention

[0005] The object of the present invention is to provide an Internet of Things temperature control method and system for pre-cooling concrete production to solve the above-mentioned problems existing in the prior art.

[0006] The specific application is as follows:

[0007] An Internet of Things temperature control system for pre-cooling concrete production, comprising:

[0008] A zone demarcation module is used to automatically demarcate the pre-cooling concrete production casting structure into multiple separate pre-cooling concrete production temperature control zones according to the spatial layout of the casting structure; the zone demarcation module outputs the zone demarcation information to the temperature control module, the environmental data acquisition module and the data analysis and reasoning module;

[0009] A temperature control module, linked to the area demarcation module, is used to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions given by the data analysis and reasoning module in real time;

[0010] An environmental data acquisition module is used to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmit the environmental data to the data analysis and reasoning module in real time;

[0011] The data analysis and reasoning module analyzes and reasons the received area demarcation results, temperature and environmental data, analyzes the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete and the environmental data, and then further reasons the aforementioned data based on the data reasoning network model, and outputs control instructions to the equipment control module and the temperature control module;

[0012] an equipment control module that dynamically adjusts operating parameters of pre-cooled concrete production equipment according to control instructions from the data analysis and reasoning module, and simultaneously pushes operating parameter information of the pre-cooled concrete production equipment to a visual display module, wherein the pre-cooled concrete production equipment includes concrete pouring equipment and concrete curing equipment;

[0013] The visual display module is used to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allows the operator to manually set the temperature parameters and transmit the operator's manual setting instructions to the temperature control module.

[0014] Furthermore, the area demarcation module includes:

[0015] A cast unit space acquisition unit uses LiDAR point cloud and hyperspectral imaging technology to acquire spatial distribution information of cast unit structures produced by pre-cooled concrete and transmits the acquired spatial distribution information to the area demarcation decision unit;

[0016] A zone demarcation decision unit, having a built-in partitioning decision model based on the particle swarm optimization algorithm and the ant colony optimization algorithm, is used to demarcate the cast structure of pre-cooled concrete production into multiple zones based on the spatial distribution information, and output zone demarcation schemes that meet the requirements of different pre-cooled concrete production scenarios. The multiple zones are collectively named pre-cooled concrete production zones, and different pre-cooled concrete production scenarios include at least large-volume concrete, precast components, and super-high-rise building core tubes;

[0017] The cast unit space acquisition unit further includes:

[0018] The LiDAR scanning subunit is equipped with multiple sets of LiDARs with adjustable orientation and accuracy, which are distributed in a matrix at key points in the pre-cooling concrete production area to scan the features of the internal space of the pre-cooling concrete production area and generate point cloud data;

[0019] The hyperspectral image acquisition subunit uses a hyperspectral camera with visible light to short-wave infrared imaging capabilities to capture the color and crack information of the surface concrete in the pre-cooling concrete production area, and matches it with the point cloud data through an image fusion algorithm to output complete spatial distribution information of the pre-cooling concrete production area to the area demarcation decision unit;

[0020] The area demarcation decision unit includes:

[0021] The initial plan determination subunit has a built-in expert database of pre-cooled concrete production scenario cases. It predicts the pre-cooled concrete production scenario based on the spatial distribution information, the type of concrete raw materials, and the use information after concrete production, and retrieves the corresponding sub-region basic template to form an initial area demarcation plan. The use information at least includes the distance information from the concrete production to the construction site.

[0022] The algorithm optimization execution subunit uses the particle swarm optimization algorithm for rapid convergence of high-dimensional parameter space and the discrete partition boundary optimization strategy of the ant colony optimization algorithm to iteratively optimize the initial region demarcation scheme;

[0023] The specific implementation process of the algorithm optimization execution subunit is as follows:

[0024] The particle swarm optimization algorithm is used to optimize the temperature control area division scheme for pre-cooling concrete production in the high-dimensional parameter space. The speed update formula satisfies:

[0025]

[0026] in, Indicates the current speed, reflecting the search direction and step size of the particle in the parameter space, pbest id Indicates individual optimality, reflecting the particle's own historical optimal position, gbest id It represents the global optimum, reflecting the optimal position found by all particles in the population. c1 and c2 represent learning factors, r1 and r2 represent random numbers, k represents the current number of iterations, and k max Indicates the maximum number of iterations of the algorithm;

[0027] Combined with the ant colony optimization algorithm, the discrete partition boundary is topologically optimized, and the pheromone concentration update rule is:

[0028]

[0029]

[0030] Among them, π ij represents the pheromone concentration, ρ represents the pheromone volatility coefficient, T i 、T j Represent the temperature values ​​of nodes i and j respectively, L k1 It is represented as the path length of the k1th ant, Q is a constant, and m is the number of ants.

[0031] Furthermore, the temperature control module includes:

[0032] A temperature data acquisition unit, using a fiber Bragg grating temperature sensor network array, is used to measure the temperature of each of the pre-cooling concrete production temperature control areas and report the temperature data to the temperature control unit;

[0033] The temperature control unit is an integrated model prediction MPC controller and a magnetic levitation variable frequency refrigeration component, and is used to adjust the temperature of each of the pre-cooling concrete production temperature control areas according to the measurement results of the temperature data acquisition unit.

[0034] Furthermore, the temperature data acquisition unit includes:

[0035] The fiber Bragg grating temperature sensor network array layout subunit uses a dynamic placement algorithm based on geometric features to calculate the first sensor density of all nodes in the pre-cooling concrete production temperature control area based on the volume eigenvalue, shape complexity index, and historical temperature fluctuation characteristics of the pre-cooling concrete production temperature control area. Through finite element heat conduction simulation, sensitive areas are marked as having temperature gradients greater than the fourth threshold, and nodes in these sensitive areas are represented as sensitive nodes. A second sensor density is generated by arranging a bidirectional staggered array at the intersection of sensitive nodes and adjacent temperature control areas. If a pre-cooling concrete production temperature control area is detected to have exceeded the fifth threshold three times in a row, additional mobile sensors are automatically added to that area to generate a third sensor density.

[0036] The data processing and transmission subunit integrates the Kalman adaptive filtering algorithm and the adversarial generative network to pre-process the field collected data, remove outliers, perform noise reduction on the data, and transmit the pre-processed temperature data to the temperature control unit;

[0037] The temperature control unit includes:

[0038] The model prediction MPC control subunit takes the temperature deviation and its changing trend as input, dynamically generates the optimal control sequence through the rolling time domain optimization algorithm, and outputs the control signal to drive the magnetic suspension variable frequency refrigeration component;

[0039] The magnetic levitation variable frequency refrigeration execution subunit is equipped with a magnetic levitation centrifugal compressor, a digital pulse electronic expansion valve and a bionic air guide duct mechanism. It dynamically adjusts the cooling capacity, cold air speed and refrigerant flow based on the control signal of the MPC control subunit predicted by the model.

[0040] Furthermore, the environmental data acquisition module includes:

[0041] A humidity data acquisition and processing unit, equipped with a distributed optical fiber acoustic wave sensor, is used to measure the humidity data of each of the pre-cooled concrete production temperature control areas and pre-process the humidity data errors in real time;

[0042] The light intensity collection and processing unit uses a quantum dot spectrum sensor to measure the light intensity of each pre-cooling concrete production temperature control area, constructs a real-time light intensity field model in the pre-cooling concrete production temperature control area, and dynamically updates it.

[0043] Furthermore, the humidity data acquisition and processing unit further includes:

[0044] Distributed fiber optic acoustic wave sensor sub-units monitor the acoustic vibration signals in the temperature control area of ​​pre-cooled concrete production in real time, input the acoustic vibration signals into the hydration reaction acoustic signature library, and then invert the humidity changes;

[0045] The data correction subunit sets the start and end points of the time period correction, combines the multi-parameter decoupling algorithm to eliminate the temperature-humidity cross-sensitivity, and outputs the accurate humidity value to the data analysis and reasoning module;

[0046] The light intensity acquisition and processing unit further includes:

[0047] The quantum dot spectral sensor subunit is used to output the sub-band irradiance data of the temperature control area of ​​the pre-cooled concrete production;

[0048] The geometric correction module eliminates the error of sub-band irradiance data caused by the zenith angle based on astronomical algorithms;

[0049] The light intensity modeling and analysis module calculates the regional light field and generates light field data based on the band-based irradiance data and the Monte Carlo ray tracing algorithm. It predicts the shadow movement path based on the building BIM model and the light trajectory, marks the light intensity blind spot area data, and sends the light field data and light intensity blind spot area data to the data analysis and inference module.

[0050] Furthermore, the data analysis and reasoning module includes:

[0051] The pre-cooled concrete property analysis unit integrates the big data pre-cooled concrete property knowledge base to analyze the pouring and curing requirements of pre-cooled concrete and generate a pouring and curing strategy based on the pre-cooled concrete properties;

[0052] The integrated data analysis unit uses a deep learning time series prediction model and an inference rule mining algorithm to analyze the impact of temperature and environmental data on pouring and curing, predict temperature and environmental change trends and associated risks in advance, generate control suggestions, and provide the control suggestions to the temperature control module and the equipment control module;

[0053] The fusion data analysis unit includes:

[0054] The deep learning time series prediction subunit uses an improved radial basis function interpolation algorithm and an improved U-Net++ network model to mine the time series data patterns of historical temperature, humidity, and light intensity, predict future trends in temperature and environmental data, and generate trend prediction data.

[0055] The rule reasoning sub-unit inputs the predicted data of future temperature and environmental data change trends into the data reasoning network model to obtain reasoning results. The reasoning results are used to output early warning information and regulation suggestions to the equipment control module and temperature control module. The reasoning results are used to quantify the impact of temperature changes and environmental data changes on the pouring and curing quality;

[0056] The specific implementation process of the deep learning time series prediction subunit is as follows:

[0057] Multi-source data fusion: The temperature and humidity of discrete points within the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate discrete data. The surface temperature field, humidity field, and light intensity field of the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate surface data. Based on the improved radial basis function interpolation algorithm, the discrete data and surface data are fused to construct a three-dimensional temperature distribution voxel model.

[0058] Intelligent temperature field segmentation and feature extraction: The three-dimensional temperature voxel model is sliced ​​according to the XY, XZ, and YZ planes. The sliced ​​data is input into the improved U-Net++ network. The improved U-Net++ network output includes a binary mask of the isothermal surface, a semantic label of the abnormally high temperature area, and a temperature gradient field tensor. The encoder of the improved U-Net++ network uses a ResNet34 skeleton and an embedded coordinate attention module. The decoder of the improved U-Net++ network introduces dense skip connections and uses sub-pixel convolution.

[0059] The temperature gradient field tensor is subjected to CP decomposition feature extraction to generate a spatiotemporal feature vector group {a r , b r , c r , d r}, where a r Characterizes the spatial distribution pattern of the temperature field in the X direction, reflecting the temperature gradient of the concrete structure along the casting length; br Characterizes the spatial distribution pattern of the temperature field in the Y direction, reflecting the temperature transfer characteristics between layers during layered pouring; c r Characterizes the distribution pattern of the temperature field in the Z direction, reflecting the attenuation relationship between the internal core temperature and the surface temperature; d r Characterizes the weight coefficient of the temperature field over time, reflecting the influence of the ambient temperature change and the time-varying factors of hydration heat release on the overall temperature field; the CP decomposition represents a factorization method of a high-order tensor;

[0060] Constructing a physical information neural network (PINN) to output change trend prediction data within the next N minutes through the PINN. The input of the physical information neural network (PINN) is a group of spatiotemporal feature vectors and environmental data. The change trend prediction data includes temperature field evolution prediction data and confidence interval data. The environmental data includes ambient temperature, ambient humidity, and ambient light intensity.

[0061] The rule reasoning subunit inputs the future temperature and environmental data change trend prediction data into the data reasoning network model, and obtains the reasoning results including:

[0062] Extracting representation vectors from the future temperature change trend prediction data based on the first layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first temperature vector and a first temperature basis vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset first correlation threshold;

[0063] Extracting representation vectors from the future environmental data change trend prediction data based on the second-layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first environmental vector and a first environmental base vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset second correlation threshold;

[0064] Based on the first weight calculation unit in the data reasoning network model, the first temperature basis vector and the first environment basis vector are respectively corrected to fuse the corrected basis vectors with the first temperature vector and the first environment vector respectively to obtain a first fusion vector. Finally, based on the reasoning unit in the data reasoning network model, data reasoning is performed on the first fusion vector to obtain an inference result, which includes at least a general reasoning result and an emergency risk reasoning result. The general reasoning result represents non-emergency processing matters, and the emergency risk reasoning result represents emergency processing matters.

[0065] Furthermore, the device control module includes:

[0066] a general algorithm processing unit, embedded with a deep reinforcement learning model, wherein the deep reinforcement learning model is used to dynamically adjust the operating parameters of the pre-cooling concrete production equipment according to the general reasoning results, and push the operating parameters and energy consumption parameters to the visualization display module;

[0067] The emergency processing unit adjusts the heating operation mode of the pre-cooling concrete production equipment to increase the heating power and accelerate the concrete forming speed when the surface temperature of the concrete is lower than the first emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result; and activates the cooling operation mode of the pre-cooling concrete production equipment to increase the cooling power to quickly reduce the surface temperature of the concrete and prevent cracks in the concrete due to overheating when the surface temperature of the concrete exceeds the second emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result.

[0068] The energy consumption equipment operation optimization unit increases the fan speed of the pre-cooling concrete production equipment to promote cooling when the surface temperature of the concrete exceeds the temperature optimization threshold of the concrete pouring. When the surface temperature of the concrete is lower than the temperature optimization threshold of the concrete pouring, the fan speed of the pre-cooling concrete production equipment is reduced to promote heat retention. The formula is:

[0069]

[0070] If(T cur (t)andT inner (t)>T set ), and we get F fan rise,

[0071] If(T cur (t)andT inner (t) <T set ), and we get F fan decline,

[0072] Among them, F fan represents the adjusted energy consumption rate of pre-cooling concrete production equipment, F base is the basic fan speed, b f is the fan speed coefficient, T cur (t) represents the average outer surface temperature of the pre-cooled concrete production temperature control area at time t, T inner (t) represents the mean inner surface temperature of the pre-cooled concrete production temperature control area at time t, T set Indicates the temperature optimization threshold.

[0073] A temperature control method for pre-cooling concrete production using the Internet of Things, used to implement any one of the temperature control systems for pre-cooling concrete production using the Internet of Things, comprises the following steps:

[0074] S1. Using a region demarcation module to automatically demarcate a plurality of separate pre-cooling concrete production temperature control zones according to the spatial layout of the cast unit structure for pre-cooling concrete production; the region demarcation module outputs the demarcation information of each zone to the temperature control module, the environmental data acquisition module, and the data analysis and reasoning module;

[0075] S2. Use the temperature control module to work in conjunction with the area demarcation module to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions from the data analysis and reasoning module in real time;

[0076] S3. Using the environmental data acquisition module to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmitting the environmental data to the data analysis and reasoning module in real time;

[0077] S4. Analyze and reason the received area demarcation results, temperature, and environmental data using a data analysis and reasoning module, analyze the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete, and the environmental data, and then further reason about the aforementioned data based on a data reasoning network model, and output control instructions to the equipment control module and the temperature control module;

[0078] S5. Dynamically adjust operating parameters of pre-cooling concrete production equipment using an equipment control module based on control instructions from the data analysis and reasoning module, and simultaneously push information about the operating parameters of the pre-cooling concrete production equipment to a visualization display module, wherein the pre-cooling concrete production equipment includes concrete pouring production equipment and concrete curing production equipment;

[0079] S6. Use a visual display module to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allow the operator to manually set the temperature parameters, and transmit the operator's manual setting instructions to the temperature control module.

[0080] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0081] The embodiment of the present invention provides an area demarcation module, a temperature control module, an environmental data acquisition module, a data analysis and reasoning module, an equipment control module and a visualization display module. The modules work together to achieve precise temperature control of different pre-cooling concrete production areas. The system uses lidar point cloud and hyperspectral imaging technology to demarcate different temperature control areas. The fiber grating temperature sensor network array, model prediction MPC controller and magnetic levitation variable frequency refrigeration component ensure precise temperature control. At the same time, the data analysis and reasoning module combines the deep learning time series prediction model and the inference rule mining algorithm to provide support for production equipment to assist in temperature control. The overall temperature control solution of the present invention improves the intelligence and accuracy of the Internet of Things temperature control in pre-cooling concrete production, and is suitable for a variety of pre-cooling concrete production scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 This is an architecture diagram of an IoT temperature control system for pre-cooling concrete production provided by an embodiment of the present invention;

[0083] Figure 2 The present invention provides a flow chart of an IoT temperature control method for pre-cooling concrete production. DETAILED DESCRIPTION

[0084] The present invention will be described in detail below with reference to the accompanying drawings.

[0085] Example 1

[0086] The embodiment of the present invention provides an Internet of Things temperature control system for pre-cooling concrete production, such as Figure 1 ,include:

[0087] A zone demarcation module is used to automatically demarcate the pre-cooling concrete production casting structure into multiple separate pre-cooling concrete production temperature control zones according to the spatial layout of the casting structure; the zone demarcation module outputs the zone demarcation information to the temperature control module, the environmental data acquisition module and the data analysis and reasoning module;

[0088] A temperature control module, linked to the area demarcation module, is used to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions given by the data analysis and reasoning module in real time;

[0089] An environmental data acquisition module is used to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmit the environmental data to the data analysis and reasoning module in real time;

[0090] The data analysis and reasoning module analyzes and reasons the received area demarcation results, temperature and environmental data, analyzes the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete and the environmental data, and then further reasons the aforementioned data based on the data reasoning network model, and outputs control instructions to the equipment control module and the temperature control module;

[0091] an equipment control module that dynamically adjusts operating parameters of pre-cooled concrete production equipment according to control instructions from the data analysis and reasoning module, and simultaneously pushes operating parameter information of the pre-cooled concrete production equipment to a visual display module, wherein the pre-cooled concrete production equipment includes concrete pouring equipment and concrete curing equipment;

[0092] The visual display module is used to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allows the operator to manually set the temperature parameters and transmit the operator's manual setting instructions to the temperature control module.

[0093] Specifically, the system of this embodiment includes an area demarcation module, a temperature control module, an environmental data acquisition module, a data analysis and reasoning module, an equipment control module and a visualization display module. The modules work together to achieve precise temperature control of different pre-cooling concrete production areas. The system uses lidar point cloud and hyperspectral imaging technology to demarcate different temperature control areas. The fiber grating temperature sensor network array, model prediction MPC controller and magnetic levitation variable frequency refrigeration component ensure precise temperature control. At the same time, the data analysis and reasoning module combines the deep learning time series prediction model and the inference rule mining algorithm to provide support for production equipment to assist in temperature control. The overall temperature control solution of the present invention improves the intelligence and accuracy of the temperature control of the Internet of Things in pre-cooling concrete production, and is suitable for a variety of outdoor pre-cooling concrete production scenarios.

[0094] In the above embodiment, specifically, the area demarcation module includes:

[0095] A cast unit space acquisition unit uses LiDAR point cloud and hyperspectral imaging technology to acquire spatial distribution information of cast unit structures produced by pre-cooled concrete and transmits the acquired spatial distribution information to the area demarcation decision unit;

[0096] A zone demarcation decision unit, having a built-in partitioning decision model based on the particle swarm optimization algorithm and the ant colony optimization algorithm, is used to demarcate the cast structure of pre-cooled concrete production into multiple zones based on the spatial distribution information, and output zone demarcation schemes that meet the requirements of different pre-cooled concrete production scenarios. The multiple zones are collectively named pre-cooled concrete production zones, and different pre-cooled concrete production scenarios include at least large-volume concrete, precast components, and super-high-rise building core tubes;

[0097] The cast unit space acquisition unit further includes:

[0098] The LiDAR scanning subunit is equipped with multiple sets of LiDARs with adjustable orientation and accuracy, which are distributed in a matrix at key points in the pre-cooling concrete production area to scan the features of the internal space of the pre-cooling concrete production area and generate point cloud data;

[0099] The hyperspectral image acquisition subunit uses a hyperspectral camera with visible light to short-wave infrared imaging capabilities to capture the color and crack information of the surface concrete in the pre-cooling concrete production area, and matches it with the point cloud data through an image fusion algorithm to output complete spatial distribution information of the pre-cooling concrete production area to the area demarcation decision unit;

[0100] The area demarcation decision unit includes:

[0101] The initial plan determination subunit has a built-in expert database of pre-cooled concrete production scenario cases. It predicts the pre-cooled concrete production scenario based on the spatial distribution information, the type of concrete raw materials, and the use information after concrete production, and retrieves the corresponding sub-region basic template to form an initial area demarcation plan. The use information at least includes the distance information from the concrete production to the construction site.

[0102] It should be noted that the sub-regional basic templates are built into the pre-cooling concrete production scenario case expert database. Multiple sub-regional basic templates are pre-determined by the pre-cooling concrete production scenario case expert database. The sub-regional basic templates are generated by clustering the massive case analysis in the expert database. The multiple sub-regional basic templates are subsequently used to determine the initial area demarcation plan.

[0103] Specifically, the initial plan determination subunit includes:

[0104] Scene feature extraction, calculation of the scene's geometric complexity, raw material uniformity, and transportation distance coefficient;

[0105] Expert case matching engine, which retrieves the scenarios with the most similar historical solutions through Euclidean distance;

[0106] The algorithm optimization execution subunit uses the particle swarm optimization algorithm for rapid convergence in high-dimensional parameter space and the discrete partition boundary optimization strategy of the ant colony optimization algorithm to iteratively optimize the initial area demarcation scheme, balancing the independence of the temperature control areas in the pre-cooling concrete production, the process connection, and the synergy of multi-modal sensors;

[0107] Specifically, the specific implementation process of the algorithm optimization execution sub-unit is as follows:

[0108] The particle swarm optimization algorithm is used to optimize the temperature control area division scheme for pre-cooling concrete production in the high-dimensional parameter space. The speed update formula satisfies:

[0109]

[0110] in, Indicates the current speed, reflecting the search direction and step size of the particle in the parameter space, pbest id Indicates individual optimality, reflecting the particle's own historical optimal position, gbest id It represents the global optimum, reflecting the optimal position found by all particles in the population. c1 and c2 represent learning factors, r1 and r2 represent random numbers, k represents the current number of iterations, and k max Indicates the maximum number of iterations of the algorithm;

[0111] Combined with the ant colony optimization algorithm, the discrete partition boundary is topologically optimized, and the pheromone concentration update rule is:

[0112]

[0113]

[0114] Among them, π ij represents the pheromone concentration, ρ represents the pheromone volatility coefficient, T i 、T j Represent the temperature values ​​of nodes i and j respectively, L k1 It is represented as the path length of the k1th ant, Q is a constant, and m is the number of ants.

[0115] In the above embodiment, specifically, the temperature control module includes:

[0116] A temperature data acquisition unit, using a fiber Bragg grating temperature sensor network array, is used to measure the temperature of each of the pre-cooling concrete production temperature control areas and report the temperature data to the temperature control unit;

[0117] The temperature control unit is an integrated model prediction MPC controller and a magnetic levitation variable frequency refrigeration component, and is used to adjust the temperature of each of the pre-cooling concrete production temperature control areas according to the measurement results of the temperature data acquisition unit.

[0118] In the above embodiment, specifically, the temperature data acquisition unit includes:

[0119] The fiber Bragg grating temperature sensor network array layout subunit uses a dynamic placement algorithm based on geometric features to calculate the first sensor density of all nodes in the pre-cooling concrete production temperature control area based on the volume eigenvalue, shape complexity index, and historical temperature fluctuation characteristics of the pre-cooling concrete production temperature control area. Through finite element heat conduction simulation, sensitive areas are marked as having temperature gradients greater than the fourth threshold, and nodes in these sensitive areas are represented as sensitive nodes. A second sensor density is generated by arranging a bidirectional staggered array at the intersection of sensitive nodes and adjacent temperature control areas. If a pre-cooling concrete production temperature control area is detected to have exceeded the fifth threshold three times in a row, additional mobile sensors are automatically added to that area to generate a third sensor density.

[0120] The data processing and transmission subunit integrates the Kalman adaptive filtering algorithm and the adversarial generative network to pre-process the field collected data, remove outliers, perform noise reduction on the data, and transmit the pre-processed temperature data to the temperature control unit;

[0121] The temperature control unit includes:

[0122] The model prediction MPC control subunit takes the temperature deviation and its changing trend as input, dynamically generates the optimal control sequence through the rolling time domain optimization algorithm, and outputs the control signal to drive the magnetic suspension variable frequency refrigeration component;

[0123] The magnetic levitation variable frequency refrigeration execution subunit is equipped with a magnetic levitation centrifugal compressor, a digital pulse electronic expansion valve and a bionic air guide duct mechanism. It dynamically adjusts the cooling capacity, cold air speed and refrigerant flow based on the control signal of the MPC control subunit predicted by the model.

[0124] It should be noted that the prediction model of the model prediction MPC control subunit is:

[0125] Construct a state space model based on the concrete heat conduction equation:

[0126] T(t+1)=AT(t)+Bu(t)+Cd(t),

[0127] Among them, A represents the state matrix, which describes the self-evolution characteristics of the temperature field inside the concrete and reflects the diffusion and accumulation of heat; B represents the control matrix, which quantifies the control ability of the refrigeration equipment (such as cooling pipes and spray systems) on the temperature field; C represents the disturbance matrix, which reflects the impact of external interference such as ambient temperature changes and light intensity on the system; T(t) represents the state vector, which describes the column vector composed of the temperature values ​​of each temperature control area; u(t) represents the control input, which consists of the cooling water flow rate, the refrigeration compressor frequency, and the spray valve opening; d(t) represents the disturbance input, which consists of the ambient temperature, solar radiation intensity, and humidity.

[0128] In the above embodiment, specifically, the environment data acquisition module includes:

[0129] A humidity data acquisition and processing unit, equipped with a distributed optical fiber acoustic wave sensor, is used to measure the humidity data of each of the pre-cooled concrete production temperature control areas and pre-process the humidity data errors in real time;

[0130] The light intensity collection and processing unit uses a quantum dot spectrum sensor to measure the light intensity of each pre-cooling concrete production temperature control area, constructs a real-time light intensity field model in the pre-cooling concrete production temperature control area, and dynamically updates it.

[0131] In the above embodiment, specifically, the humidity data acquisition and processing unit further includes:

[0132] Distributed fiber optic acoustic wave sensor sub-units monitor the acoustic vibration signals in the temperature control area of ​​pre-cooled concrete production in real time, input the acoustic vibration signals into the hydration reaction acoustic signature library, and then invert the humidity changes;

[0133] The data correction subunit sets the start and end points of the time period correction, combines the multi-parameter decoupling algorithm to eliminate the temperature-humidity cross-sensitivity, and outputs the accurate humidity value to the data analysis and reasoning module;

[0134] The light intensity acquisition and processing unit further includes:

[0135] The quantum dot spectral sensor subunit is used to output the sub-band irradiance data of the temperature control area of ​​the pre-cooled concrete production;

[0136] The geometric correction module eliminates the error of sub-band irradiance data caused by the zenith angle based on astronomical algorithms;

[0137] The light intensity modeling and analysis module calculates the regional light field and generates light field data based on the band-based irradiance data and the Monte Carlo ray tracing algorithm. It predicts the shadow movement path based on the building BIM model and the light trajectory, marks the light intensity blind spot area data, and sends the light field data and light intensity blind spot area data to the data analysis and inference module.

[0138] It should be noted that quantum dot spectral sensors:

[0139] Hardware configuration:

[0140] Visible light band (400-700nm): using silicon-based photodiode array, resolution ±5W / m 2 ;

[0141] Near infrared band (700-1100nm): InGaAs sensor, sensitivity 0.1mV / (W / m 2 );

[0142] Ultraviolet band (300-400nm): used to monitor photoaging effects;

[0143] Data calibration:

[0144] Daily calibration with standard light source (such as AM1.5G spectrum) to eliminate sensor attenuation;

[0145] Monte Carlo ray tracing algorithm implementation:

[0146] 1. Modeling process:

[0147] Light Emission:

[0148] Generate 10 according to the sun's position (declination angle δ, hour angle ω) 6 a ray of light;

[0149] Wavelength weight distribution: visible light:near infrared:ultraviolet=0.6:0.3:0.1;

[0150] 2. Collision Detection

[0151] BIM model meshing (accuracy ≤ 0.1m), using BVH (Bounding Volume Hierarchy) to accelerate intersection calculations;

[0152] Concrete surface roughness modeling (microplane normal follows GGX distribution);

[0153] 3. Energy accumulation:

[0154] Each temperature control area is divided into grid units, and each grid unit receives irradiance:

[0155]

[0156] Among them, E cell Indicates the irradiance received by the grid cell, I i represents the light intensity, cosθ i represents the cosine of the incident angle, a represents the attenuation coefficient, d i Indicates the propagation distance, reflecting the straight-line distance of light from the light source (sun or reflective surface) to the grid unit, and N represents the total number of light rays;

[0157] Shadow path prediction and blind spot marking:

[0158] Dynamic shadow calculation:

[0159] Input: BIM model geometry data + sun trajectory calculated by astronomical algorithms;

[0160] Output: time-varying curve of shadow coverage;

[0161] Marking rules: If the slope of the shadow coverage time-varying curve is greater than the preset threshold within 10 minutes, it is marked as a potential maintenance risk area and determined to be a blind spot;

[0162] The specific implementation process of the astronomical algorithm is as follows:

[0163] Step 1: Synchronization of time and space references

[0164] High-precision spatiotemporal calibration:

[0165] Obtain the latitude and longitude of the measuring station through the GPS / Beidou module;

[0166] Use atomic clock to synchronize UTC time;

[0167] Terrain data loading:

[0168] Read the elevation and slope / aspect of the measuring point from the DEM database;

[0169] Calculate terrain roughness factor;

[0170] Step 2: Solve the sun position

[0171] The improved Jean Meeus algorithm is used to calculate the declination angle;

[0172] The solar zenith angle formula is used to calculate the longitude and latitude, declination angle, and solar hour angle of the measuring station, and the mean error formula is used to eliminate the error caused by the zenith angle calculation;

[0173] It should be noted that the pre-cooling concrete production scenario case expert library has a built-in hydration reaction sound feature library, which outputs a humidity-acoustic vibration signal feature mapping model through experimental simulation data.

[0174] In the above embodiment, specifically, the data analysis and reasoning module includes:

[0175] The pre-cooled concrete property analysis unit integrates the big data pre-cooled concrete property knowledge base to analyze the pouring and curing requirements of pre-cooled concrete and generate a pouring and curing strategy based on the pre-cooled concrete properties;

[0176] The integrated data analysis unit uses a deep learning time series prediction model and an inference rule mining algorithm to analyze the impact of temperature and environmental data on pouring and curing, predict temperature and environmental change trends and associated risks in advance, generate control suggestions, and provide the control suggestions to the temperature control module and the equipment control module;

[0177] The fusion data analysis unit includes:

[0178] The deep learning time series prediction subunit uses an improved radial basis function interpolation algorithm and an improved U-Net++ network model to mine the time series data patterns of historical temperature, humidity, and light intensity, predict future trends in temperature and environmental data, and generate trend prediction data.

[0179] The rule reasoning sub-unit inputs the predicted data of future temperature and environmental data change trends into the data reasoning network model to obtain reasoning results. The reasoning results are used to output early warning information and regulation suggestions to the equipment control module and temperature control module. The reasoning results are used to quantify the impact of temperature changes and environmental data changes on the pouring and curing quality;

[0180] The specific implementation process of the deep learning time series prediction subunit is as follows:

[0181] Multi-source data fusion: The temperature and humidity of discrete points within the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate discrete data. The surface temperature field, humidity field, and light intensity field of the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate surface data. Based on the improved radial basis function interpolation algorithm, the discrete data and surface data are fused to construct a three-dimensional temperature distribution voxel model.

[0182] Intelligent temperature field segmentation and feature extraction: The three-dimensional temperature voxel model is sliced ​​according to the XY, XZ, and YZ planes. The sliced ​​data is input into the improved U-Net++ network. The improved U-Net++ network output includes a binary mask of the isothermal surface, a semantic label of the abnormally high temperature area, and a temperature gradient field tensor. The encoder of the improved U-Net++ network uses a ResNet34 skeleton and an embedded coordinate attention module. The decoder of the improved U-Net++ network introduces dense skip connections and uses sub-pixel convolution.

[0183] The temperature gradient field tensor is subjected to CP decomposition feature extraction to generate a spatiotemporal feature vector group {a r , b r , c r , d r}, where a r Characterizes the spatial distribution pattern of the temperature field in the X direction, reflecting the temperature gradient of the concrete structure along the casting length; b r Characterizes the spatial distribution pattern of the temperature field in the Y direction, reflecting the temperature transfer characteristics between layers during layered pouring; c r Characterizes the distribution pattern of the temperature field in the Z direction, reflecting the attenuation relationship between the internal core temperature and the surface temperature; d r Characterizes the weight coefficient of the temperature field over time, reflecting the influence of the ambient temperature change and the time-varying factors of hydration heat release on the overall temperature field; the CP decomposition represents a factorization method of a high-order tensor;

[0184] Constructing a physical information neural network (PINN) to output change trend prediction data within the next N minutes through the PINN. The input of the physical information neural network (PINN) is a group of spatiotemporal feature vectors and environmental data. The change trend prediction data includes temperature field evolution prediction data and confidence interval data. The environmental data includes ambient temperature, ambient humidity, and ambient light intensity.

[0185] The rule reasoning subunit inputs the future temperature and environmental data change trend prediction data into the data reasoning network model, and obtains the reasoning results including:

[0186] Extracting representation vectors from the future temperature change trend prediction data based on the first layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first temperature vector and a first temperature basis vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset first correlation threshold;

[0187] Extracting representation vectors from the future environmental data change trend prediction data based on the second-layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first environmental vector and a first environmental base vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset second correlation threshold;

[0188] Based on the first weight calculation unit in the data reasoning network model, the first temperature basis vector and the first environment basis vector are respectively corrected to fuse the corrected basis vectors with the first temperature vector and the first environment vector respectively to obtain a first fusion vector. Finally, based on the reasoning unit in the data reasoning network model, data reasoning is performed on the first fusion vector to obtain an inference result, which includes at least a general reasoning result and an emergency risk reasoning result. The general reasoning result represents non-emergency processing matters, and the emergency risk reasoning result represents emergency processing matters.

[0189] It should be noted that the key steps of the data inference network model are as follows:

[0190] 1. Characterization vector extraction (taking temperature data as an example)

[0191] Input data:

[0192] Temperature change trend prediction sequence for the next 6 hours (sampling interval 10 minutes): T = [T1, T2, ...T 36 ];

[0193] Environmental change trend data (ambient temperature, ambient humidity and ambient light intensity): E = [H1, W1, S1, ...H 36, W 36 , S 36 ];

[0194] The first layer of perceptron (temperature branch):

[0195] The first layer of perceptron structure: fully connected layer (input 36 dimensions, output 64 dimensions) + ReLU activation;

[0196] The first layer of perceptron output: the first temperature vector (high-order features), first temperature basis vector (low-dimensional features with clear physical meaning, such as slope and curvature);

[0197] Correlation threshold: The first correlation threshold is preset, and the actual calculation is verified by the Pearson coefficient;

[0198] 2.Basic vector correction

[0199] Correction algorithm:

[0200] V′ temp_base =V temp_base +a*MLP([V temp ||V env ]),

[0201] Among them, a represents a learnable parameter, || represents vector concatenation, MLP represents the perceptron function, V env represents the environment vector;

[0202] 3. Vector fusion and reasoning include the fusion layer and the reasoning unit;

[0203] General reasoning results (non-urgent matters):

[0204] Output: Maintenance recommendations (e.g. "Start spraying after 6 hours");

[0205] Model: Softmax classifier (10 types of general operation);

[0206] Urgent risk reasoning results:

[0207] Output: Risk type and level (e.g., "Core temperature rise exceeds limit within 2 hours: Level 3");

[0208] Model: binary threshold judgment (Sigmoid output > 0.8 triggers);

[0209] It should be noted that the multi-layer perceptron in the data reasoning network model is an expert neural network, and the weight calculation unit is a gated neural network. The data reasoning network model includes an input layer, a core multi-layer perceptron, a first-layer perceptron, a second-layer perceptron, a first weight calculation unit, and an inference unit. Based on the data reasoning network model, the future temperature and environmental data change trend prediction data are accurately inferred, and the relationship between the parameter adjustment control and temperature control of the concrete pouring equipment and the concrete curing equipment is inferred, and then precise control instructions are obtained, and the precise control instructions are output to the equipment control module and the temperature control module. The above technical features are one of the technical highlights of this embodiment. Most of the existing technologies only adjust the temperature control parameters in the temperature control module, and do not adjust the parameters of the concrete pouring equipment and concrete curing equipment involved in the pouring and curing process to achieve further precise adjustment of the concrete temperature.

[0210] In the above embodiment, specifically, the device control module includes:

[0211] a general algorithm processing unit, embedded with a deep reinforcement learning model, wherein the deep reinforcement learning model is used to dynamically adjust the operating parameters of the pre-cooling concrete production equipment according to the general reasoning results, and push the operating parameters and energy consumption parameters to the visualization display module;

[0212] The emergency processing unit adjusts the heating operation mode of the pre-cooling concrete production equipment to increase the heating power and accelerate the concrete forming speed when the surface temperature of the concrete is lower than the first emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result; and activates the cooling operation mode of the pre-cooling concrete production equipment to increase the cooling power to quickly reduce the surface temperature of the concrete and prevent cracks in the concrete due to overheating when the surface temperature of the concrete exceeds the second emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result.

[0213] It should be noted that pre-cooling concrete production equipment all has built-in cooling and heating functions to assist in temperature intervention during concrete pouring and curing. Most pre-cooling concrete production equipment in the prior art does not intervene in concrete temperature control. However, in the actual production process, pre-cooling concrete production equipment can improve concrete temperature control efficiency by intervening in concrete temperature in real time, which is also one of the technical highlights of the present invention.

[0214] The energy consumption optimization unit increases the fan speed of the pre-cooling concrete production equipment to promote cooling when the surface temperature of the concrete exceeds the temperature optimization threshold for concrete pouring. When the surface temperature of the concrete is lower than the temperature optimization threshold for concrete pouring, the fan speed of the pre-cooling concrete production equipment is reduced to promote heat retention. The formula is:

[0215]

[0216] If(T cur (t)andT inner (t)>T set ), and we get F fan rise,

[0217] If(T cur (t)andT inner (t) <T set ), and we get F fan decline,

[0218] Among them, F fan represents the adjusted energy consumption rate of pre-cooling concrete production equipment, F base is the basic fan speed, b f is the fan speed coefficient, T cur (t) represents the average outer surface temperature of the pre-cooled concrete production temperature control area at time t, T inner (t) represents the mean inner surface temperature of the pre-cooled concrete production temperature control area at time t, T set Indicates the temperature optimization threshold.

[0219] It should be noted that the energy consumption optimization unit in this embodiment only considers the surface temperature of the concrete.

[0220] Example 2

[0221] A temperature control method for pre-cooling concrete production using the Internet of Things, comprising the following steps:

[0222] S1. Using a region demarcation module to automatically demarcate a plurality of separate pre-cooling concrete production temperature control zones according to the spatial layout of the cast unit structure for pre-cooling concrete production; the region demarcation module outputs the demarcation information of each zone to the temperature control module, the environmental data acquisition module, and the data analysis and reasoning module;

[0223] S2. Use the temperature control module to work in conjunction with the area demarcation module to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions from the data analysis and reasoning module in real time;

[0224] S3. Using the environmental data acquisition module to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmitting the environmental data to the data analysis and reasoning module in real time;

[0225] S4. Analyze and reason the received area demarcation results, temperature, and environmental data using a data analysis and reasoning module, analyze the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete, and the environmental data, and then further reason about the aforementioned data based on a data reasoning network model, and output control instructions to the equipment control module and the temperature control module;

[0226] S5. Dynamically adjust operating parameters of pre-cooling concrete production equipment using an equipment control module based on control instructions from the data analysis and reasoning module, and simultaneously push information about the operating parameters of the pre-cooling concrete production equipment to a visualization display module, wherein the pre-cooling concrete production equipment includes concrete pouring production equipment and concrete curing production equipment;

[0227] S6. Use a visual display module to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allow the operator to manually set the temperature parameters, and transmit the operator's manual setting instructions to the temperature control module.

[0228] It should be understood that the above embodiments are one or more embodiments of the present invention, and there are many other embodiments and variations thereof based on the present invention; the variations and modifications made by ordinary technicians in this industry through the present invention without making groundbreaking innovations all fall within the scope of protection of the present invention.

Claims

1. A pre-cooling concrete production Internet of Things temperature control system, characterized in that: include: The zone demarcation module is used to automatically demarcate the pre-cooling concrete production casting structure into multiple separate pre-cooling concrete production temperature control zones according to the spatial layout of the pre-cooling concrete production casting structure; The area demarcation module outputs the area demarcation information to the temperature control module, the environmental data acquisition module and the data analysis and reasoning module; A temperature control module, linked to the area demarcation module, is used to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions given by the data analysis and reasoning module in real time; An environmental data acquisition module is used to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmit the environmental data to the data analysis and reasoning module in real time; The data analysis and reasoning module analyzes and reasons the received area demarcation results, temperature and environmental data, analyzes the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete and the environmental data, and then further reasons the aforementioned data based on the data reasoning network model, and outputs control instructions to the equipment control module and the temperature control module; an equipment control module that dynamically adjusts operating parameters of pre-cooled concrete production equipment according to control instructions from the data analysis and reasoning module, and simultaneously pushes operating parameter information and energy consumption parameter information of the pre-cooled concrete production equipment to the visual display module, wherein the pre-cooled concrete production equipment includes concrete pouring equipment and concrete curing equipment; The visual display module is used to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allows the operator to manually set the temperature parameters and transmit the operator's manual setting instructions to the temperature control module.

2. The pre-cooling concrete production Internet of Things temperature control system according to claim 1 is characterized in that: The area demarcation module includes: A cast unit space acquisition unit uses LiDAR point cloud and hyperspectral imaging technology to acquire spatial distribution information of cast unit structures produced by pre-cooled concrete and transmits the acquired spatial distribution information to the area demarcation decision unit; A zone demarcation decision unit, having a built-in partitioning decision model based on the particle swarm optimization algorithm and the ant colony optimization algorithm, is used to demarcate the cast structure of pre-cooled concrete production into multiple zones based on the spatial distribution information, and output zone demarcation schemes that meet the requirements of different pre-cooled concrete production scenarios. The multiple zones are collectively named pre-cooled concrete production zones, and different pre-cooled concrete production scenarios include at least large-volume concrete, precast components, and super-high-rise building core tubes; The cast unit space acquisition unit further includes: The LiDAR scanning subunit is equipped with multiple sets of LiDARs with adjustable orientation and accuracy, which are distributed in a matrix at key points in the pre-cooling concrete production area to scan the features of the internal space of the pre-cooling concrete production area and generate point cloud data; The hyperspectral image acquisition subunit uses a hyperspectral camera with visible light to short-wave infrared imaging capabilities to capture the color and crack information of the surface concrete in the pre-cooling concrete production area, and matches it with the point cloud data through an image fusion algorithm to output complete spatial distribution information of the pre-cooling concrete production area to the area demarcation decision unit; The area demarcation decision unit includes: The initial plan determination subunit has a built-in expert database of pre-cooled concrete production scenario cases. It predicts the pre-cooled concrete production scenario based on the spatial distribution information, the type of concrete raw materials, and the use information after concrete production, and retrieves the corresponding sub-region basic template to form an initial area demarcation plan. The use information at least includes the distance information from the concrete production to the construction site. The algorithm optimization execution subunit uses the particle swarm optimization algorithm for rapid convergence of high-dimensional parameter space and the discrete partition boundary optimization strategy of the ant colony optimization algorithm to iteratively optimize the initial region demarcation scheme; The specific implementation process of the algorithm optimization execution subunit is as follows: The particle swarm optimization algorithm is used to optimize the temperature control area division scheme for pre-cooling concrete production in the high-dimensional parameter space. The speed update formula satisfies: in, Indicates the current speed, reflecting the search direction and step size of the particle in the parameter space, pbest id Indicates individual optimality, reflecting the particle's own historical optimal position, gbest id It represents the global optimum, reflecting the optimal position found by all particles in the population. c1 and c2 represent learning factors, r1 and r2 represent random numbers, k represents the current number of iterations, and k max Indicates the maximum number of iterations of the algorithm; Combined with the ant colony optimization algorithm, the discrete partition boundary is topologically optimized, and the pheromone concentration update rule is: Among them, π ij represents the pheromone concentration, ρ represents the pheromone volatility coefficient, T i 、T j Represent the temperature values ​​of nodes i and j respectively, L k1 It is expressed as the path length of the k1th ant, Q is a constant, and m is the number of ants.

3. The pre-cooling concrete production Internet of Things temperature control system according to claim 1 is characterized in that: The temperature control module includes: A temperature data acquisition unit, using a fiber Bragg grating temperature sensor network array, is used to measure the temperature of each of the pre-cooling concrete production temperature control areas and report the temperature data to the temperature control unit; The temperature control unit is an integrated model prediction MPC controller and a magnetic levitation variable frequency refrigeration component, and is used to adjust the temperature of each of the pre-cooling concrete production temperature control areas according to the measurement results of the temperature data acquisition unit.

4. The pre-cooling concrete production Internet of Things temperature control system according to claim 3 is characterized in that: The temperature data acquisition unit includes: The fiber Bragg grating temperature sensor network array layout subunit uses a dynamic placement algorithm based on geometric features to calculate the first sensor density of all nodes in the pre-cooling concrete production temperature control area based on the volume eigenvalue, shape complexity index, and historical temperature fluctuation characteristics of the pre-cooling concrete production temperature control area. Through finite element heat conduction simulation, sensitive areas are marked as having temperature gradients greater than the fourth threshold, and nodes in these sensitive areas are represented as sensitive nodes. A second sensor density is generated by arranging a bidirectional staggered array at the intersection of sensitive nodes and adjacent temperature control areas. If a pre-cooling concrete production temperature control area is detected to have exceeded the fifth threshold three times in a row, additional mobile sensors are automatically added to that area to generate a third sensor density. The data processing and transmission subunit integrates the Kalman adaptive filtering algorithm and the adversarial generative network to pre-process the field collected data, remove outliers, perform noise reduction on the data, and transmit the pre-processed temperature data to the temperature control unit; The temperature control unit includes: The model prediction MPC control subunit takes the temperature deviation and its changing trend as input, dynamically generates the optimal control sequence through the rolling time domain optimization algorithm, and outputs the control signal to drive the magnetic suspension variable frequency refrigeration component; The magnetic levitation variable frequency refrigeration execution subunit is equipped with a magnetic levitation centrifugal compressor, a digital pulse electronic expansion valve and a bionic air guide duct mechanism. It dynamically adjusts the cooling capacity, cold air speed and refrigerant flow based on the control signal of the MPC control subunit predicted by the model.

5. The pre-cooling concrete production Internet of Things temperature control system according to claim 1, characterized in that: The environmental data acquisition module includes: A humidity data acquisition and processing unit, equipped with a distributed optical fiber acoustic wave sensor, is used to measure the humidity data of each of the pre-cooled concrete production temperature control areas and pre-process the humidity data errors in real time; The light intensity collection and processing unit uses a quantum dot spectrum sensor to measure the light intensity of each pre-cooling concrete production temperature control area, constructs a real-time light intensity field model in the pre-cooling concrete production temperature control area, and dynamically updates it.

6. The pre-cooling concrete production Internet of Things temperature control system according to claim 5, characterized in that: The humidity data acquisition and processing unit also includes: Distributed fiber optic acoustic wave sensor sub-units monitor the acoustic vibration signals in the temperature control area of ​​pre-cooled concrete production in real time, input the acoustic vibration signals into the hydration reaction acoustic signature library, and then invert the humidity changes; The data correction subunit sets the start and end points of the time period correction, combines the multi-parameter decoupling algorithm to eliminate the temperature-humidity cross-sensitivity, and outputs the accurate humidity value to the data analysis and reasoning module; The light intensity acquisition and processing unit further includes: The quantum dot spectral sensor subunit is used to output the sub-band irradiance data of the temperature control area of ​​the pre-cooled concrete production; The geometric correction module eliminates the error of sub-band irradiance data caused by the zenith angle based on astronomical algorithms; The light intensity modeling and analysis module calculates the regional light field and generates light field data based on the band-based irradiance data and the Monte Carlo ray tracing algorithm. It predicts the shadow movement path based on the building BIM model and the light trajectory, marks the light intensity blind spot area data, and sends the light field data and light intensity blind spot area data to the data analysis and inference module.

7. The pre-cooling concrete production Internet of Things temperature control system according to claim 1, characterized in that: The data analysis and reasoning module includes: The pre-cooled concrete property analysis unit integrates the big data pre-cooled concrete property knowledge base to analyze the pouring and curing requirements of pre-cooled concrete and generate a pouring and curing strategy based on the pre-cooled concrete properties; The integrated data analysis unit uses a deep learning time series prediction model and an inference rule mining algorithm to analyze the impact of temperature and environmental data on pouring and curing, predict temperature and environmental change trends and associated risks in advance, generate control suggestions, and provide the control suggestions to the temperature control module and the equipment control module; The fusion data analysis unit includes: The deep learning time series prediction subunit uses an improved radial basis function interpolation algorithm and an improved U-Net++ network model to mine the time series data patterns of historical temperature, humidity, and light intensity, predict future trends in temperature and environmental data, and generate trend prediction data. The rule reasoning sub-unit inputs the predicted data of future temperature and environmental data change trends into the data reasoning network model to obtain reasoning results. The reasoning results are used to output early warning information and regulation suggestions to the equipment control module and temperature control module. The reasoning results are used to quantify the impact of temperature changes and environmental data changes on the pouring and curing quality; The specific implementation process of the deep learning time series prediction subunit is as follows: Multi-source data fusion: The temperature and humidity of discrete points within the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate discrete data. The surface temperature field, humidity field, and light intensity field of the pre-cooled concrete production temperature control area are acquired through the temperature control module and the environmental data acquisition module to generate surface data. Based on the improved radial basis function interpolation algorithm, the discrete data and surface data are fused to construct a three-dimensional temperature distribution voxel model. Intelligent temperature field segmentation and feature extraction: The three-dimensional temperature voxel model is sliced ​​according to the XY, XZ, and YZ planes. The sliced ​​data is input into the improved U-Net++ network. The improved U-Net++ network output includes a binary mask of the isothermal surface, a semantic label of the abnormally high temperature area, and a temperature gradient field tensor. The encoder of the improved U-Net++ network uses a ResNet34 skeleton and an embedded coordinate attention module. The decoder of the improved U-Net++ network introduces dense skip connections and uses sub-pixel convolution. The temperature gradient field tensor is subjected to CP decomposition feature extraction to generate a spatiotemporal feature vector group {a r , b r , c r , d r }, where a r Characterizes the spatial distribution pattern of the temperature field in the X direction, reflecting the temperature gradient of the concrete structure along the casting length; b r Characterizes the spatial distribution pattern of the temperature field in the Y direction, reflecting the temperature transfer characteristics between layers during layered pouring; c r Characterizes the distribution pattern of the temperature field in the Z direction, reflecting the attenuation relationship between the internal core temperature and the surface temperature; d r Characterizes the weight coefficient of the temperature field over time, reflecting the influence of the ambient temperature change and the time-varying factors of hydration heat release on the overall temperature field; the CP decomposition represents a factorization method of a high-order tensor; Constructing a physical information neural network (PINN) to output change trend prediction data within the next N minutes through the PINN. The input of the physical information neural network (PINN) is a group of spatiotemporal feature vectors and environmental data. The change trend prediction data includes temperature field evolution prediction data and confidence interval data. The environmental data includes ambient temperature, ambient humidity, and ambient light intensity. The rule reasoning subunit inputs the future temperature and environmental data change trend prediction data into the data reasoning network model, and obtains the reasoning results including: Extracting representation vectors from the future temperature change trend prediction data based on the first layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first temperature vector and a first temperature basis vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset first correlation threshold; Extracting representation vectors from the future environmental data change trend prediction data based on the second-layer perceptron and the core multi-layer perceptron in the data inference network model to obtain a first environmental vector and a first environmental base vector, wherein the extraction of the representation vectors includes obtaining representation vectors whose correlation is not less than a preset second correlation threshold; Based on the first weight calculation unit in the data reasoning network model, the first temperature basis vector and the first environment basis vector are respectively corrected to fuse the corrected basis vectors with the first temperature vector and the first environment vector respectively to obtain a first fusion vector. Finally, based on the reasoning unit in the data reasoning network model, data reasoning is performed on the first fusion vector to obtain an inference result, which includes at least a general reasoning result and an emergency risk reasoning result. The general reasoning result represents non-emergency processing matters, and the emergency risk reasoning result represents emergency processing matters.

8. The pre-cooling concrete production Internet of Things temperature control system according to claim 7, characterized in that: The device control module includes: a general algorithm processing unit, embedded with a deep reinforcement learning model, wherein the deep reinforcement learning model is used to dynamically adjust the operating parameters of the pre-cooling concrete production equipment according to the general reasoning results, and push the operating parameters and energy consumption parameters to the visualization display module; The emergency processing unit adjusts the heating operation mode of the pre-cooling concrete production equipment to increase the heating power and accelerate the concrete forming speed when the surface temperature of the concrete is lower than the first emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result; and activates the cooling operation mode of the pre-cooling concrete production equipment to increase the cooling power to quickly reduce the surface temperature of the concrete and prevent cracks in the concrete due to overheating when the surface temperature of the concrete exceeds the second emergency threshold value for concrete pouring and curing according to the emergency risk reasoning result. The energy consumption equipment operation optimization unit increases the fan speed of the pre-cooling concrete production equipment to promote cooling when the surface temperature of the concrete exceeds the temperature optimization threshold of the concrete pouring. When the surface temperature of the concrete is lower than the temperature optimization threshold of the concrete pouring, the fan speed of the pre-cooling concrete production equipment is reduced to promote heat retention. The formula is: If(T cur (t)andT inner (t)>T set ), and we get F fan rise, If(T cur (t)andT inner (t) <T set ), and we get F fan decline, Among them, F fan represents the adjusted energy consumption rate of pre-cooling concrete production equipment, F base is the basic fan speed, b f is the fan speed coefficient, T cur (t) represents the average outer surface temperature of the pre-cooled concrete production temperature control area at time t, T inner (t) represents the mean inner surface temperature of the pre-cooled concrete production temperature control area at time t, T set Indicates the temperature optimization threshold.

9. A temperature control method for pre-cooling concrete production Internet of Things, used to implement a temperature control system for pre-cooling concrete production Internet of Things according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1. Using a region demarcation module to automatically demarcate a plurality of separate pre-cooling concrete production temperature control zones according to the spatial layout of the cast unit structure for pre-cooling concrete production; the region demarcation module outputs the demarcation information of each zone to the temperature control module, the environmental data acquisition module, and the data analysis and reasoning module; S2. Use the temperature control module to work in conjunction with the area demarcation module to control the temperature of each pre-cooled concrete production temperature control area, feed the temperature back to the data analysis and reasoning module in real time, and receive control suggestions from the data analysis and reasoning module in real time; S3. Using the environmental data acquisition module to monitor the environmental data of each pre-cooled concrete production temperature control area, including humidity and light intensity, and transmitting the environmental data to the data analysis and reasoning module in real time; S4. Analyze and reason the received area demarcation results, temperature, and environmental data using a data analysis and reasoning module, analyze the temperature of each pre-cooled concrete production temperature control area, the characteristics of the pre-cooled concrete, and the environmental data, and then further reason about the aforementioned data based on a data reasoning network model, and output control instructions to the equipment control module and the temperature control module; S5. Dynamically adjust operating parameters of pre-cooling concrete production equipment using an equipment control module based on control instructions from the data analysis and reasoning module, and simultaneously push information about the operating parameters of the pre-cooling concrete production equipment to a visualization display module, wherein the pre-cooling concrete production equipment includes concrete pouring production equipment and concrete curing production equipment; S6. Use a visual display module to display the temperature of each of the pre-cooling concrete production temperature control areas, the environmental data, and the operating parameter information of the pre-cooling concrete production equipment, and allow the operator to manually set the temperature parameters, and transmit the operator's manual setting instructions to the temperature control module.

Images