Intelligent temperature control method and device for fan foundation construction in alpine region

Abstract

The invention relates to the field of construction temperature regulation and control, in particular to an intelligent temperature control method and device for fan foundation construction in an alpine region. The method comprises the following steps: collecting real-time concrete temperature monitoring parameters based on a distributed temperature sensor, carrying out time sequence temperature discrete trend analysis and spatial temperature fluctuation distribution evolution, and constructing a temperature fluctuation distribution evolution diagram; concrete surface environment parameters are extracted, heat exchange simulation processing is carried out on the temperature fluctuation distribution evolution diagram, multivariate coupling correlation analysis is carried out, and a temperature-environment quantitative relation model is constructed; and obtaining historical meteorological logs and meteorological environment data of the construction area, carrying out similar meteorological condition matching calculation, carrying out short-term meteorological trend prediction, and generating short-term meteorological trend prediction features. According to the dynamic temperature regulation and control requirements, safe construction of the fan foundation concrete in the high and cold environment is guaranteed, and the construction quality is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the field of intelligent temperature control methods and devices for high-cold-region fan foundation construction. BACKGROUND

[0002] In the construction process of high-power fans in high-cold regions, temperature monitoring and regulation of concrete foundations are key links to ensure structural safety and construction quality. Due to the slow hydration reaction of concrete in low-temperature environments and the easy occurrence of freezing damage, abnormal fluctuations in temperature not only affect the formation of concrete strength, but also may cause structural damage such as cracks and peeling, thereby threatening the long-term stability of the fan foundation. Traditional construction temperature management relies on manual inspection and simple temperature measurement equipment, and the monitoring means is single and lagging, which makes it difficult to achieve fine and dynamic management of the internal temperature of concrete and cannot meet the complex temperature control requirements in extreme cold environments.

[0003] In addition, the temperature of concrete is affected by multiple factors such as environmental climate change, construction technology and material characteristics, and the complexity and real-time requirements of temperature regulation are extremely high. Existing temperature regulation techniques are usually based on fixed parameter settings, lack intelligent identification and adaptive adjustment capabilities for dynamic changes in construction site temperature, resulting in unsatisfactory temperature control effects, low energy utilization efficiency, and difficulty in responding to sudden environmental changes in a timely manner, which cannot effectively prevent low-temperature freezing damage and related quality accidents. At the same time, the construction environment in high-cold regions is complex and variable, and temperature monitoring equipment is easily disturbed by external interference, which challenges the accuracy and stability of the data and increases the construction risk. In the face of the above problems, there is an urgent need for a comprehensive monitoring and regulation system based on advanced sensing technology, intelligent data analysis and adaptive temperature control strategies. SUMMARY

[0004] To solve the above technical problems, the application provides an intelligent temperature control method and device for high-cold-region fan foundation construction to solve at least one of the above technical problems.

[0005] To achieve the above purpose, the application provides an intelligent temperature control method for high-cold-region fan foundation construction, comprising the following steps:

[0006] Based on the distributed temperature sensor, real-time concrete temperature monitoring parameters are collected, time series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution are performed, and a temperature fluctuation distribution evolution diagram is constructed;

[0007] Environmental parameters of the concrete surface are extracted, heat exchange simulation processing of the temperature fluctuation distribution evolution diagram is performed, and multivariate coupling correlation analysis is performed to construct a temperature-environment quantitative relationship model;

[0008] The meteorological trend prediction module is configured to acquire historical meteorological logs of a construction area and meteorological environment data of the construction area, perform similar meteorological condition matching calculation, and perform short-term meteorological trend prediction to generate short-term meteorological trend prediction features.

[0009] The temperature trend prediction module is configured to perform short-term multi-region temperature trend prediction and regional temperature change distribution fitting on the temperature-environment quantitative relationship model based on the short-term meteorological trend prediction features, and construct a natural temperature change prediction distribution field.

[0010] The differential temperature regulation module is configured to perform differential regional heating power demand analysis and preventive temperature regulation according to the natural temperature change prediction distribution field, and generate regional differential temperature regulation instructions.

[0011] The intelligent temperature control optimization module is configured to perform warm air temperature control execution based on the regional differential temperature regulation instructions, and perform iterative regulation learning to construct a warm air temperature control optimization model.

[0012] In the present specification, an intelligent temperature control device for wind turbine foundation construction in high-cold regions is provided for executing the intelligent temperature control method for wind turbine foundation construction in high-cold regions as described above, comprising:

[0013] The temperature fluctuation distribution module is configured to collect real-time concrete temperature monitoring parameters based on distributed temperature sensors, perform time series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution, and construct a temperature fluctuation distribution evolution diagram.

[0014] The coupling correlation module is configured to extract concrete surface environment parameters, perform heat exchange simulation processing on the temperature fluctuation distribution evolution diagram, and perform multi-element coupling correlation analysis to construct a temperature-environment quantitative relationship model.

[0015] The meteorological trend prediction module is configured to acquire historical meteorological logs of a construction area and meteorological environment data of the construction area, perform similar meteorological condition matching calculation, and perform short-term meteorological trend prediction to generate short-term meteorological trend prediction features.

[0016] The temperature trend prediction module is configured to perform short-term multi-region temperature trend prediction and regional temperature change distribution fitting on the temperature-environment quantitative relationship model based on the short-term meteorological trend prediction features, and construct a natural temperature change prediction distribution field.

[0017] The differential temperature regulation module is configured to perform differential regional heating power demand analysis and preventive temperature regulation according to the natural temperature change prediction distribution field, and generate regional differential temperature regulation instructions.

[0018] The intelligent temperature control optimization module is configured to perform warm air temperature control execution based on the regional differential temperature regulation instructions, and perform iterative regulation learning to construct a warm air temperature control optimization model.

[0019] The beneficial effects of the present application are as follows: a temperature sensing network covering all levels and positions in the structure is formed by distributed temperature sensors (such as optical fiber DTS or multi-point thermocouple), which can capture the temperature change trend and distribution pattern in the curing process of concrete in real time. Using sequence analysis and spatial interpolation technology, local supercooling, overheating and temperature difference sudden change points can be accurately identified, and a complete temperature fluctuation evolution map can be constructed, providing basic support for subsequent differentiated heat control and significantly improving the real-time visualization of temperature field evolution and control response. By synchronously collecting environmental factors (air temperature, wind speed, radiation, humidity, etc.) on the surface of the concrete and inputting them into the heat exchange simulation model, the conduction path and influence strength of external weather on internal heat field changes can be simulated. Combined with machine learning algorithm for multi-factor coupling analysis, the quantitative correlation between "environment-concrete temperature" in high-cold environment is established, forming the core of model-driven prediction. This model can explain the environmental factors behind temperature changes, improving the predictability and pertinence of subsequent temperature control adjustment.

[0020] By calling the local historical meteorological database and combining the current measured meteorological data for multi-dimensional feature similarity matching, the current weather and the most similar weather evolution situation in the past can be quickly identified, and the local weather trend prediction in the near period (1-6 hours) can be constructed. This method breaks through the problem of insufficient accuracy of traditional prediction models in remote areas, realizes the fine prediction of local microclimate, and provides dynamic, real-time and scene-adapted environmental prior information for preventive temperature regulation. The short-term weather trend prediction results are used as driving input, combined with the temperature-environment quantitative model constructed in the second step, the heat field evolution of the concrete structure in the future can be predicted in high resolution and multiple regions. This prediction process not only considers the current state, but also reflects the feedforward influence of climate change, and finally generates the temperature change distribution field under natural conditions. This distribution field is the "baseline prediction before heating", which provides objective quantitative basis for formulating differentiated temperature control scheme and verifying temperature control effect.

[0021] According to the difference in the future temperature drop speed and amplitude of each region in the prediction distribution field, the system can intelligently analyze the heating power level and duration required by different regions, realize the on-demand allocation of thermal control resources, and avoid the "big pot" type uniform heating. By generating regional precise control instructions (such as adjusting the heating cable power, directional heating on-off timing), the construction temperature control is realized to be fine, energy-saving and intelligent, which greatly improves the insulation efficiency and energy consumption ratio, effectively reduces the frost damage risk and construction cost. After the actual implementation of the differentiated temperature control strategy, the deviation between the control effect and the actual temperature response is continuously monitored, and the weather change feedback is combined to build a closed-loop control mechanism, and then the model is iteratively learned and the parameters are optimized. This mechanism enables the system to gradually acquire "experience memory" and "strategy evolution" capabilities, continuously improving the adaptability and intelligence of temperature control decisions. Finally, a warm air heater temperature control optimization model with self-learning and self-regulating capabilities is formed, which continuously ensures the safe maintenance and construction quality of the fan foundation concrete in the high-cold environment. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A step flowchart of an intelligent temperature control method for fan foundation construction in high-cold regions according to the present application is shown in the figure.

[0023] Figure 2 A detailed implementation step flowchart of the temperature fluctuation distribution evolution graph constructed by the real-time concrete temperature monitoring parameters collected by the distributed temperature sensor, the time series temperature discrete trend analysis and the spatial temperature fluctuation distribution evolution is shown in the figure.

[0024] Figure 3 A detailed implementation step flowchart of the temperature-ambient quantitative relationship model constructed by the temperature fluctuation distribution evolution graph heat exchange simulation processing and the multi-element coupling correlation analysis based on the extracted concrete surface environmental parameters is shown in the figure.

[0025] Figure 4 A detailed implementation step flowchart of the short-term weather trend prediction feature generated by the short-term weather trend prediction based on the historical weather log of the construction area and the weather data of the construction area is shown in the figure. DETAILED DESCRIPTION

[0026] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0027] The application example provides an intelligent temperature control method and device for fan foundation construction in high-cold regions.

[0028] Please refer to Figures 1 to 4 The application provides an intelligent temperature control method for fan foundation construction in high-cold regions, including the following steps:

[0029] Based on the distributed temperature sensor, real-time concrete temperature monitoring parameters are collected, time series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution are carried out, and a temperature fluctuation distribution evolution diagram is constructed.

[0030] The concrete surface environment parameters are extracted, the temperature fluctuation distribution evolution diagram is simulated for heat exchange, and multi-element coupling correlation analysis is carried out, and a temperature-environment quantitative relationship model is constructed.

[0031] The historical meteorological log of the construction area and the meteorological environment data of the construction area are obtained, similar meteorological condition matching calculation is carried out, short-term meteorological trend prediction is carried out, and short-term meteorological trend prediction characteristics are generated.

[0032] Based on the short-term meteorological trend prediction characteristics, the temperature-environment quantitative relationship model is used for short-term multi-region temperature trend prediction and regional temperature change distribution fitting, and a natural temperature change prediction distribution field is constructed.

[0033] According to the natural temperature change prediction distribution field, differential regional heating power demand analysis is carried out, and preventive temperature regulation is carried out, and regional differential temperature regulation instructions are generated.

[0034] Based on the regional differential temperature regulation instruction, the warm air temperature control is executed, and iterative regulation learning is carried out, and a warm air temperature control optimization model is constructed.

[0035] In the embodiment of the application, please refer to Figure 1 The steps of the intelligent temperature control method for fan foundation construction in high-cold regions are shown in the schematic diagram, and in this example, the steps of the intelligent temperature control method for fan foundation construction in high-cold regions include:

[0036] Based on the distributed temperature sensor, real-time concrete temperature monitoring parameters are collected, time series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution are carried out, and a temperature fluctuation distribution evolution diagram is constructed.

[0037] In this embodiment, real-time concrete temperature monitoring parameters are collected based on distributed temperature sensors, time series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution are performed, and a temperature fluctuation distribution evolution diagram is constructed. A multi-point distributed temperature sensor array is deployed in the middle of the fan foundation concrete structure, and a PT100 platinum resistance temperature sensor is used to achieve high-precision temperature measurement of ±0.1°C. The sensor nodes are arranged in a three-dimensional grid, with core monitoring points (0.5m apart) set inside the concrete and boundary monitoring points (0.3m apart) set on the surface, forming a three-dimensional monitoring network covering the entire concrete structure. Through LoRa wireless communication technology, real-time collection of sensor data is realized, with a sampling frequency of once every 60 seconds to ensure stable operation of the sensor network in extreme environments of-40°C. Time series analysis method is used to analyze the discrete trend of the collected temperature data, and sliding average algorithm is used to process temperature data noise, with a window length of 10 minutes. The temperature change rate is calculated by the first-order difference method to identify the periodic characteristics of temperature fluctuations. Based on the spatial interpolation algorithm, the Kriging interpolation method is used to reconstruct the temperature distribution between monitoring points, with a grid resolution of 0.1m x 0.1m, and a three-dimensional temperature field distribution diagram is generated. Through temperature gradient calculation, high-risk areas with temperature difference exceeding 5°C in the concrete are identified, a temperature fluctuation intensity evaluation index is established, and the temperature stability of different areas is quantified.

[0038] Extracting concrete surface environmental parameters, simulating heat exchange of temperature fluctuation distribution evolution diagram, and performing multi-element coupling correlation analysis to construct temperature-environment quantitative relationship model;

[0039] In this embodiment, concrete surface environmental parameters are extracted, heat exchange simulation of temperature fluctuation distribution evolution diagram is performed, and multi-element coupling correlation analysis is performed to construct a temperature-environment quantitative relationship model. Environmental parameter monitoring equipment is deployed, including an anemometer (measurement range 0-60m / s, accuracy ±0.1m / s), a humidity sensor (measurement range 0-100% RH, accuracy ±2% RH), a pyranometer (measurement range 0-2000W / m 2 , accuracy ±5W / m 2 ) and a barometer (measurement range 300-1100hPa, accuracy ±0.1hPa). A mathematical model of heat exchange on the surface of concrete is established, based on Fourier's law of heat conduction and Newton's law of cooling, to calculate the convective heat transfer coefficient between the surface of concrete and the environment. This coefficient varies in the range of 15-45W / (m 2• K). The heat exchange simulation was conducted by finite element analysis method, and a three-dimensional model of concrete-environment heat exchange was established. Tetrahedral elements were used for meshing, with element size controlled within 0.05 m. The boundary conditions were set as time-varying functions of ambient temperature and convective heat transfer coefficient. Through multiple linear regression analysis, the quantitative relationship between temperature change and environmental parameters was established, and the regression equation was in the form of ΔT = a1 x Wind + a2 x Humidity + a3 x Radiation + a4 x Pressure + b, where the coefficients were solved by the least squares method, and the correlation coefficient R 2 was greater than 0.85. Principal component analysis was used to identify the key environmental factors affecting temperature change, and contribution rate analysis showed that the influence weights of wind speed and humidity on temperature change were 35% and 28%, respectively. An environmental parameter-temperature response time lag model was established, and cross-correlation analysis was used to determine the time delay of different environmental factors on temperature. The wind speed influence delay was about 15 minutes, and the humidity influence delay was about 30 minutes.

[0040] Obtain historical meteorological logs and meteorological environmental data of the construction area, perform similar meteorological condition matching calculation, and perform short-term meteorological trend prediction to generate short-term meteorological trend prediction features;

[0041] In this embodiment, the historical meteorological log of the construction area and the meteorological environmental data of the construction area are obtained, the similar meteorological condition matching calculation is performed, and the short-term meteorological trend prediction is performed to generate the short-term meteorological trend prediction feature. The historical meteorological data of the construction area in the past 10 years are collected, including daily average temperature, maximum and minimum temperature, wind speed, humidity, precipitation and air pressure and other parameters, and the data are derived from local meteorological stations and satellite remote sensing data. The meteorological similarity matching algorithm is established, the Euclidean distance and cosine similarity are combined, the similarity of the current meteorological condition and the historical meteorological mode is calculated, the similarity threshold is set to 0.8, and the matching window length is 72 hours. Through the clustering analysis method, the historical meteorological data are divided into typical meteorological mode categories, including 6 typical modes such as sunny high pressure type, cold air invasion type and warm wet air flow type, each mode contains temperature change characteristics, duration and conversion probability and other parameters. The long short-term memory (LSTM) neural network model is used for short-term meteorological prediction, the network structure contains 3 hidden layers, each layer contains 128 neurons, the learning rate is set to 0.001, and the training period is 500 rounds. The input features include the time series of meteorological parameters in the past 72 hours, and the output is the predicted value of the meteorological parameters in the future 24-72 hours. The model training uses the historical 5-year data, the validation set accounts for 20%, and the test set accounts for 10%, the prediction accuracy is evaluated by the root mean square error (RMSE) and the mean absolute error (MAE) indexes, the temperature prediction RMSE is controlled within 1.5°C, and the wind speed prediction MAE is controlled within 0.8m / s. The key features of meteorological change are extracted through trend analysis, including temperature change rate, wind speed change amplitude, humidity fluctuation period and the like, the short-term meteorological trend prediction feature vector is constructed, and the feature dimension is 15, covering the trend parameters of temperature, wind speed, humidity and other main meteorological elements.

[0042] Based on the short-term meteorological trend prediction feature, the short-term multi-region temperature trend prediction and the regional temperature change distribution fitting are performed on the temperature-environmental quantitative relationship model, and the natural temperature change prediction distribution field is constructed;

[0043] In this embodiment, based on the short-term weather trend prediction characteristics, the short-term multi-region temperature trend prediction and the regional temperature change distribution fitting of the temperature-environment quantitative relationship model are performed, and the natural temperature change prediction distribution field is constructed. The short-term weather trend prediction characteristics generated in step S3 are input into the temperature-environment quantitative relationship model established in step S2, and the temperature response prediction value of different regions of the concrete is obtained by model calculation. The Monte Carlo simulation method is used to process the prediction uncertainty, 1000 random samplings are set, the influence of the weather prediction error on the temperature prediction is considered, the confidence interval of the temperature prediction is generated, and the confidence degree is set to 95%. A multi-region temperature trend prediction model is established, the concrete structure is divided into three main regions of core region, transition region and boundary region, each region is further subdivided into a 2x2x2 sub-region grid, and a total of 24 prediction units are obtained. Through spatial autocorrelation analysis, the correlation of temperature changes between different regions is calculated, the correlation coefficient is between 0.6-0.9, a temperature propagation model between regions is established, and the propagation coefficient is obtained by historical data regression. The Gaussian process regression method is used for regional temperature change distribution fitting, the kernel function is selected as the radial basis function (RBF), and the length scale parameter is determined as 0.5m by cross-validation optimization. The mathematical expression of the temperature change prediction distribution field is established, a three-dimensional spatial interpolation method is used to expand the discrete prediction points into a continuous temperature distribution field, and the resolution is set to 0.1m x 0.1m x 0.1m. Through the space-time interpolation algorithm, the temperature distribution field of each hour within 24 hours in the future is generated, and a four-dimensional (x, y, z, t) natural temperature change prediction distribution field is formed. A temperature prediction accuracy evaluation mechanism is established, and the prediction accuracy is verified by historical data. The prediction accuracy reaches 85% within 6 hours, 78% within 12 hours, and 70% within 24 hours.

[0044] According to the natural temperature change prediction distribution field, the differential regional heating power demand analysis is performed, and the preventive temperature regulation is performed to generate the regional differential temperature regulation instruction;

[0045] In this embodiment, according to the natural temperature change prediction distribution field, the differential regional heating power demand analysis is performed, and the preventive temperature regulation is performed to generate the regional differential temperature regulation instruction. Based on the natural temperature change prediction distribution field constructed in step S4, the time point and the duration when the temperature of each region is lower than the set threshold (5°C) are analyzed, and the key period and the region needing heating intervention are identified. A heating power demand calculation model is established, the required heating power density is calculated according to the concrete heat capacity (about 2.4x10 6 J / (m 3 ·K)), the target temperature difference and the time constraint, and the formula is: P=ρxcxVxΔT / Δt, wherein ρ is the concrete density 2400kg / m 3, c is the specific heat capacity 1000 J / (kg·K). The heating power allocation is performed using a multi-objective optimization algorithm, the objective functions include maximizing temperature control accuracy, minimizing energy consumption cost, and maximizing equipment utilization, the constraint conditions include the maximum power limit of a single heating unit (5 kW / m 2 ) and the total power budget constraint. The multi-objective optimization problem is solved by genetic algorithm, the population size is set to 100, the evolution number is 300, the crossover probability is 0.8, and the mutation probability is 0.1. A preventive temperature regulation strategy is established, the heating system is started 1-3 hours in advance according to the temperature prediction results to avoid temperature fluctuations caused by passive response. A hierarchical heating control strategy is designed, the heating power is divided into low-power preheating mode (1-2 kW / m 2 ), medium-power maintenance mode (2-4 kW / m 2 ) and high-power rapid heating mode (4-5 kW / m 2 ), and the heating mode is dynamically switched according to the predicted temperature change trend. A regional differentiation regulation instruction generation mechanism is established, a constant temperature control strategy is used for the core area, the target temperature range is 8-12℃; a gradient control strategy is used for the transition area, the temperature range is 5-10℃; a freeze-proof control strategy is used for the boundary area, the minimum temperature is kept above 2℃. The generated temperature regulation instruction includes heating area coordinates, power setting value, start time, duration and priority, etc.

[0046] The warm air temperature control is executed based on the regional differentiation temperature regulation instruction, and iterative regulation learning is performed to construct a warm air temperature control optimization model.

[0047] In this embodiment, the warm air temperature control is executed based on the regional differentiation temperature regulation instruction, and iterative regulation learning is performed to construct a warm air temperature control optimization model. A distributed heating system execution architecture is established, including resistance heater (power range 1-5 kW, temperature response time 10-15 minutes), infrared radiation heater (power range 2-8 kW, temperature response time 5-8 minutes) and hot air circulation system (air volume 50-200 m 3(h, temperature response time 15-20 minutes). The centralized control of the heating equipment is realized through field bus technology (CAN bus), the communication rate is set to 250 kbit / s, and the response time is controlled within 100 ms. An execution effect evaluation mechanism is established to monitor the heating effect in real time through the temperature monitoring network of step S1, calculate the deviation of the actual temperature change from the expected temperature change, and trigger the adjustment of the control parameters when the deviation exceeds ±1℃. An iterative control learning model is constructed using a reinforcement learning algorithm, the Q-learning algorithm is selected, the learning rate is set to 0.1, the discount factor is 0.9, the exploration rate uses an ε-greedy strategy, the initial ε value is 0.3, and the decay rate is 0.995. The state space is defined as the combination of temperature distribution, environmental parameters and heating equipment state, and the action space includes heating power adjustment, heating time adjustment and heating area selection, etc. A reward function is established, considering factors such as temperature control accuracy, energy efficiency and equipment life, the reward function form is: R = α × precision score - β × energy cost - γ × equipment wear, where α = 0.6, β = 0.3, γ = 0.1. The warm air heater temperature control optimization model is trained through historical control data, the training data includes 100 temperature control records of construction periods, the model training uses batch update method, the batch size is set to 32, and the training period is 1000 rounds. Model performance evaluation indicators are established, including temperature control accuracy (target ± 0.5℃), energy efficiency (more than 15% energy saving compared with traditional methods) and prediction accuracy (more than 85%). An adaptive parameter adjustment mechanism is established to dynamically adjust the model parameters according to seasonal changes, construction progress and equipment state, realizing the continuous improvement and performance improvement of the warm air heater temperature control optimization model.

[0048] In this embodiment, referring to Figure 2 , the real-time concrete temperature monitoring parameters are collected based on the distributed temperature sensors, the time series temperature discrete trend analysis and the spatial temperature fluctuation distribution evolution are performed, and the specific steps of constructing the temperature fluctuation distribution evolution are as follows:

[0049] The real-time concrete temperature monitoring parameters of the fan foundation construction area are collected based on the distributed temperature sensors;

[0050] The real-time concrete temperature monitoring parameters are filtered to obtain abnormal optimized temperature monitoring parameters;

[0051] The distributed temperature sensors are calculated and positioned one by one in space, and the spatial position coordinates of multiple sensors are extracted;

[0052] The abnormal optimized temperature monitoring parameters are analyzed for time series temperature discrete trend, and a time series temperature discrete trend curve is generated;

[0053] The time-series temperature discrete trend curve is evolved based on the spatial position coordinates of the plurality of sensors, and a temperature fluctuation distribution evolution graph is constructed.

[0054] In this embodiment, the concrete construction of high-power fan foundation in alpine regions is carried out, and the environmental temperature is generally between -15°C and -30°C. The heat released by the hydration reaction inside the concrete is easily absorbed by the surrounding low-temperature environment, resulting in insufficient early strength of the concrete, and even freezing damage. Therefore, real-time concrete temperature monitoring using a distributed temperature sensor system is particularly critical. The system is usually composed of high-precision optical fiber sensing lines, demodulators, signal processing modules, and data transmission systems. The sensing optical fiber is laid along the key parts of the fan foundation structure, such as the center of the bottom plate, the middle and lower part of the side wall, and the surrounding of the anchor bolt, with a common layout interval of 0.5-1 meter and a depth control of 0.3-1.5 meters. The sampling frequency can be dynamically adjusted according to the construction stage, usually set to once every 5 minutes, and the temperature collection accuracy can reach ±0.2°C. The system has long-distance synchronous multi-point collection capability, can support high-density layout within hundreds of meters, and uploads data to the construction management platform in real time through wireless or wired methods, ensuring that construction management personnel can monitor the evolution trend of the internal temperature field of the concrete for 24 hours. The protection performance of anti-freezing, anti-pressure, and waterproof should also be considered during the operation of the system, especially during the early maintenance stage of the concrete in winter. Such sensor systems must have the ability to work stably at -40°C environment. This step provides the original data basis for subsequent temperature control adjustment and temperature trend analysis, and plays a key role that cannot be replaced. Due to the complex environment of the construction site, the sensor may be affected by electromagnetic interference, mechanical damage, temperature control equipment, or human operation errors, resulting in abnormal conditions such as sudden value, drift value, signal loss, etc. in the collected temperature data. If not processed directly for analysis, it is easy to mislead the judgment of the hydration heat behavior of the concrete. Therefore, it is necessary to identify and optimize the real-time temperature data collected. In this step, a multiple detection mechanism based on statistical methods is used to screen the temperature data one by one, including sliding window mean method (setting window length to 11 points and 21 points), median deviation method (MAD, setting threshold to 2 times standard deviation), and Z-score standardization (setting threshold to ±3). For the data of the sensor nodes that are continuously lost for more than 3 times (15 minutes), linear interpolation or local spline fitting is used for data completion. For the sampling data that deviates from the adjacent nodes by more than 5°C, it is marked as "abnormal mutation" and corrected by trend fitting. In actual engineering, a project monitored a number of sensor points with instantaneous drop of more than 8°C during the night when the temperature difference changed dramatically. After analysis, it was found that the battery power supply of the acquisition instrument was unstable. After processing, the optimized data is more stable and can accurately reflect the real temperature change trend. The final "abnormal optimized temperature monitoring parameter" data set provides a reliable data basis for subsequent time trend analysis and spatial evolution modeling.

[0055] To achieve spatial visualization analysis of the internal temperature distribution of concrete structures, each temperature sensor must be accurately positioned in space, and its position model in the three-dimensional coordinate system must be established. Before construction, the theoretical layout path of the sensor is usually preset in the BIM (Building Information Modeling) platform, and the coordinate positioning point method is used for calibration. During actual operation on the construction site, the total station or high-precision RTK GPS equipment is used to measure the sensing optical fiber path point by point, especially in the key thermal control area (such as the anchor bolt area, the center of the bottom plate, etc.), a space node is recorded every 0.5-1 meter, and its spatial coordinates (X, Y, Z) are assigned. To further improve the accuracy, after the concrete pouring is completed, a laser scanner or a structured light scanning device can be used to model the point cloud of the foundation surface, and the spatial deviation is corrected by model fitting and sensing path comparison to ensure that the positioning error is controlled within ±5 mm. In addition, the curved layout form of the optical fiber sensing line should also be considered, especially around the corners of the structure and the columns, and the path should be restored through the fitting curve and three-dimensional path matching algorithm. Finally, a high-precision sensor coordinate database is obtained, which records the spatial position of each sampling point and the corresponding sensor number. This database will serve as the core spatial index support for three-dimensional interpolation and thermal field reconstruction of time series temperature data, achieving accurate spatial mapping of data from the acquisition end to the analysis end. After obtaining the optimized temperature data, time series analysis is needed to identify the main stages and key inflection points of the concrete hydration heat process. The temperature change during the hardening of concrete can be roughly divided into three stages: temperature rise period, platform period, and temperature drop period. To extract the characteristics of these stages, wavelet transform combined with weighted moving average method is used to denoise and smooth the temperature sequence to reduce the random disturbance caused by environmental fluctuations. Each sensor point draws a temperature change curve according to its time series, forming a "time series temperature discrete trend curve". In practical applications, such as the curve collected by the bottom plate center sensor in a certain wind power project, the temperature rises rapidly in the first 6 hours after concrete pouring, with an average temperature rise rate of 3.2℃ / h; the temperature reaches a peak of about 41.7℃ at the 18th hour; and the temperature drops to 28.5℃ at the 36th hour and tends to be stable. By comparing the curve characteristics of multiple sensing points, it can be determined whether the concrete hydration heat reaction at different positions is synchronized and whether there are abnormal areas (such as temperature rise lag, heat accumulation). In addition, the first and second derivatives of time can be calculated to extract the temperature change rate and acceleration indicators for further analysis of the response efficiency of the temperature control measures and the rationality of the temperature control strategy. The time series temperature curve provides an important basis for concrete quality assessment and intelligent temperature control, and is also a prerequisite for subsequent dynamic analysis of the spatial temperature field.

[0056] The spatial position coordinates of each sensor are combined with the corresponding time-series temperature trend data to construct a three-dimensional temperature fluctuation evolution graph of the concrete structure throughout the curing period through interpolation and thermal field reconstruction algorithms. In this step, the Kriging interpolation method is selected for spatial temperature field reconstruction. The Kriging method can consider the covariance and distance relationship between spatial positions, making it suitable for modeling the heterogeneous temperature distribution within concrete. The interpolation process is performed in frames at each time unit, resulting in a four-dimensional temperature distribution graph with time axis evolution capability. The image can be displayed in the form of isothermal surfaces or color heat zones in the three-dimensional model, clearly showing the distribution of high temperature zones, cooling zones, and abnormal areas. For example, in a certain high-cold wind power project, the constructed temperature fluctuation evolution graph reveals that the temperature in the peripheral area of the bottom plate is more than 10°C lower than that in the core area for a long time, and the heat spreads slowly upwards, prompting the need to strengthen the insulation measures. Through the graph, the thermal field evolution path and its corresponding relationship with external temperature and construction time can also be analyzed. The graphical results can be uploaded to a remote construction control platform, combined with an AI intelligent analysis system to determine whether to intervene in measures such as electric heating, infrared insulation, or air cooling. The temperature fluctuation distribution evolution graph not only improves the accuracy of temperature control and regulation, but also provides long-term data support for post-concrete structure health assessment, and is an important pillar tool for realizing the intelligentization and digitization of concrete construction.

[0057] In the embodiment, the specific steps of filtering and processing the real-time concrete temperature monitoring parameters to obtain abnormal optimized temperature monitoring parameters are as follows:

[0058] A fixed-length sliding time window is defined;

[0059] The real-time temperature monitoring parameters are analyzed based on the sliding time window fitting analysis, and the temperature monitoring parameters of multiple time windows are extracted;

[0060] The fitting residual, temperature slope, and temperature change rate of the temperature monitoring parameters are calculated;

[0061] Adjacent time window temperature jump detection is performed based on the temperature slope and temperature change rate, and abnormal temperature jump points are marked;

[0062] According to the fitting residual, the slope change rate is analyzed, and the slope gradually deviates from the identification, and the abnormal temperature drift points are marked;

[0063] The abnormal temperature jump points and abnormal temperature drift points are determined as abnormal temperature monitoring points;

[0064] The error analysis of the abnormal temperature monitoring points is performed, and the error monitoring points and abnormal outlier monitoring points are extracted;

[0065] The multi-point average temperature monitoring parameters of the real-time concrete temperature monitoring parameters are calculated;

[0066] According to the multi-point average temperature monitoring parameter, the mean value interpolation replacement is performed on the error monitoring points, and the outlier filtering processing is performed on the abnormal outlier monitoring points, to obtain an abnormal optimized temperature monitoring parameter.

[0067] In this embodiment, in the construction of high-power fan foundation concrete in high-cold regions, the temperature change is affected by environmental temperature fluctuation, concrete hydration heat release process and heat preservation measures, and the change has obvious time sequence characteristics and stages. Therefore, in order to realize dynamic tracking and analysis of the temperature change trend, a sliding time window mechanism needs to be introduced. The sliding time window refers to a way of rolling analysis of data within a fixed time length, which can be defined as a fixed length time period of 5 hours, 6 hours or 8 hours in this scene. When selecting the length of the time window, the heat release peak duration of the concrete, the sensor sampling frequency (such as once every 5 minutes) and the temperature change rate need to be considered to set comprehensively. Taking 5 hours as an example, 60 temperature sampling points are included in one window, which can capture the stage changes of concrete heating, peak value and cooling, and avoid noise interference caused by too much detail. The sliding step can be set to 30 minutes or 1 hour to ensure good continuity and overlap on the time axis. Through such window division, clear time structure support can be provided for subsequent local temperature trend fitting, abnormal fluctuation identification and other operations, realizing accurate analysis and control in different time periods, which is the prerequisite for fine management of concrete temperature control. After completing the division of the sliding time window, the temperature data in each time window needs to be fitted and analyzed to extract its trend change characteristics. The core purpose of fitting analysis is to establish a mathematical expression model of temperature change in each time period, which usually adopts a linear regression model or a local polynomial fitting model (such as a second or third order polynomial fitting) for processing. In the high-cold environment, the concrete temperature often shows a trend of continuous rise or slow decline, so the linear model fitting has high explanatory and applicability. Taking a 5-hour window as an example, the least square method is applied to linear fitting of each 60 data points to obtain the temperature change slope, intercept and fitting residual parameters of the time period; at the same time, the deviation of each point between the fitted value and the measured value is recorded to evaluate the fitting accuracy. In the fitting process, the external interference factors specific to high-cold construction (such as temporary heat preservation interruption, sudden start of electric heating, etc.) also need to be considered, so that in some windows, a non-linear trend will be presented, and a third-order fitting model can be appropriately switched to correct it.

[0068] After the completion of the sliding window fitting, further extraction of each time window is required to represent the key numerical characteristics of the thermal behavior of concrete, namely the fitting residual (Residual), temperature slope (Slope), and temperature change rate (ΔT / Δt). The fitting residual is an important indicator for evaluating the accuracy of the fitting model. The calculation method is to subtract the fitting value from the actual temperature value of each point. If the residual fluctuates sharply or is abnormally distributed, it usually means that there may be external disturbances or sensor abnormalities in the window. The temperature slope represents the heating or cooling speed per unit time, and its positive or negative value can determine whether the current concrete is in the heating, plateau, or cooling stage. In experimental measurements, the slope is usually higher than 0.8°C / h in the early pouring stage, the peak plateau tends to be close to 0°C, and the cooling period is a negative slope of about -0.3°C / h. The temperature change rate further refines the change rate of the slope between consecutive windows and is the core indicator for dynamic monitoring of temperature change sensitivity. Through joint analysis of these three parameters, the internal thermal field fluctuation state of the concrete can be comprehensively mastered, and possible abnormal points such as slope mutation or residual surge can be preliminarily identified, providing direct numerical basis for subsequent jump and drift judgment. Temperature jump refers to the sharp change of temperature in adjacent time periods, which is often caused by external intervention, heating out of control, or sensor signal abnormalities. In practical applications, by comparing whether there is a large mutation in the temperature slope and change rate of adjacent sliding windows, potential temperature jump points can be identified. The specific method is to set the temperature slope jump threshold (such as 0.6°C / h) and the change rate threshold (such as 0.8°C / h 2 ), when the slope of two adjacent windows changes by more than this threshold, it is marked as a jump candidate point. In the first night of wind power foundation concrete pouring, the peripheral concrete area will experience instantaneous cooling due to external temperature drop, and the temperature jump is obvious, with the slope changing from positive to negative (such as from +0.5°C / h to -0.4°C / h). Jump detection can effectively identify the time and position of these discontinuous changes and automatically mark them, avoiding misjudgment of these sharp changes as normal trends in subsequent analysis, thereby improving the sensitivity and stability of the temperature control system.

[0069] In addition to temperature jumps, a more subtle anomaly, temperature drift, needs to be identified. Drift refers to the phenomenon that the temperature data collected by the sensor slowly but continuously deviates from the true value in multiple time windows, often caused by sensor aging, poor contact, or local heat preservation failure. To detect drift trends, slope change rate analysis can be based on fitting residuals, i.e., calculating the change direction and amplitude of the slope of multiple consecutive windows. If the slope of multiple consecutive windows (such as more than 5) shows one-way growth or decrease, and the fitting residual continues to expand (the mean value of the residual increases by more than 1.5°C), it can be preliminarily judged as a temperature drift point. For example, in a certain engineering project, a sensor on the outer edge of the concrete has been showing a slow rise in temperature since the 24th hour, but other sensors at the same location have stabilized, with a slope of 0.1°C / h continuously rising, and a residual expanding from 0.4°C to 2.1°C, eventually identified as an abnormal drift point. Marking the drift point can effectively eliminate misleading data and prevent it from having a negative impact on temperature control strategies or concrete quality judgments. The temperature jump points and temperature drift points identified in the first two steps are classified as "abnormal temperature monitoring points" for subsequent data cleaning and correction. This classification is based on a logical judgment model to ensure that all temperature anomaly time points and location nodes can be accurately located and distinguished. Jump points are mostly sudden anomalies, requiring high sensitivity to the system, while drift points are trend deviations that require some data accumulation to identify. The common feature of both types of abnormal points is that they deviate from the normal temperature evolution pattern of hydration heat release. If not removed, it will cause the average temperature trend to be pulled up or down, misleading the judgment of early concrete curing or the implementation of control measures. To achieve comprehensive coverage, the system also sets an abnormality identification confidence index to evaluate factors such as the number of identification time periods and the size of the change, and to remove interfering false positives. This step forms a complete set of abnormal points, which is the direct input for subsequent error analysis and data repair.

[0070] After identifying the abnormal monitoring points, further analysis is needed to determine the cause, distinguishing whether it is caused by sensor hardware error, environmental interference or data processing problem. By comparing the abnormal points with the adjacent sensing points in space (within 0.5 meters), calculate whether the temperature difference exceeds 3℃; at the same time, combined with the historical stability analysis of the sensing point (the standard deviation of fluctuation exceeds 2 times the mean value), the error monitoring point can be identified. If a point shows isolated abnormality in space and time dimensions, and has no continuous trend support, it is judged as an outlier point. For example, in the actual data, the temperature collected by a sensing point at the 32nd hour is 47℃, while the adjacent points are 36-38℃, combined with the previous 24 hours without similar temperature records, it is finally marked as an outlier point. This step builds an abnormal structure classification system to provide classification basis for subsequent processing, ensuring that useful information is not excessively excluded and key errors are not missed. To further improve the rationality and accuracy of data repair, the average temperature of multiple normal points near the abnormal point is calculated as the reference. The multi-point average temperature parameter not only reflects the overall temperature level of the local area, but also effectively balances the deviation caused by individual abnormalities. In operation, usually 4-6 normal sensing points within 1 meter of the abnormal point are selected, and the average temperature of the same time is calculated as the reference. It is found in the experiment that this method has strong adaptability to local temperature fluctuations, especially in the corner or edge area, effectively avoiding the influence of single-point error on overall judgment. The average temperature can also be used to fill in the missing data of the abnormal point, ensuring continuity and accuracy.

[0071] For error monitoring points, multi-point average temperature is used for interpolation replacement to ensure that interpolation is reasonable in space and time. The interpolation process can use weighted average method to assign values to multiple adjacent points according to distance weight, and take the weighted average value as the replacement result. For outlier monitoring points, since they are usually single-point anomalies and have no continuity, interpolation correction is not suitable, so direct exclusion processing is performed, i.e. shielding the point data in the analysis. After the above processing, the final optimized temperature monitoring parameter set obtained will not be disturbed by mutation, drift or outlier value, and is more consistent with the actual thermal field change of concrete. This data set is of key significance as input for subsequent intelligent temperature control strategy development and construction control model, which can significantly improve the temperature control accuracy and concrete quality assurance level of wind power foundation construction in cold regions.

[0072] In this embodiment, referring to Figure 3 , the specific steps of extracting the concrete surface environment parameters, processing the heat exchange simulation of the temperature fluctuation distribution evolution diagram, and performing multi-element coupling correlation analysis to build the temperature-environment quantitative relationship model are as follows:

[0073] Based on the temperature fluctuation distribution evolution diagram, the internal temperature distribution pattern of concrete is extracted.

[0074] define a time period, and perform a plurality of period temperature change logical calculations on the temperature fluctuation distribution evolution diagram to generate a temperature change rule;

[0075] based on the internal temperature distribution pattern and the temperature change rule, perform numerical real-time simulation to generate a real-time temperature distribution field;

[0076] adaptively collect frequency parameters of the fan foundation construction area, and extract concrete surface environmental parameters;

[0077] based on the concrete surface environmental parameters, perform heat exchange simulation processing on the real-time temperature distribution field to generate environmental-internal temperature heat exchange simulation data;

[0078] perform multivariate coupling correlation analysis on the environmental-internal temperature heat exchange simulation data, and quantize the temperature change response to construct a temperature-environment quantization relationship model.

[0079] In this embodiment, during the construction of wind power foundation in alpine regions, the concrete will experience strong spatial and temporal temperature gradient during hardening. In order to master the distribution characteristics of its internal temperature field, it is necessary to deeply explore the regularity information from the existing temperature fluctuation distribution evolution graph. The temperature fluctuation distribution evolution graph is usually based on three-dimensional space, and presents four-dimensional thermal evolution dynamics by integrating time dimension. When constructing the graph, the time series temperature data of each sensor has been mapped to the structure coordinate system. In this step, through image processing and thermal field modeling algorithm, the temperature distribution graph is clustered and pattern recognized, and typical temperature distribution areas are identified, such as central heat accumulation area, edge heat dissipation area, structure connection high gradient area, etc. Using spatial K-means clustering (k value is set to 3-6) or Gaussian mixture model (GMM), the temperature distribution graph can be divided into several representative area patterns. In actual cases, a stable existing temperature plateau area is observed in the middle of the wind power tower base plate, which has a significantly longer heat accumulation duration than other areas, and presents an ellipsoidal shape, which indicates that this area may have concentrated heat due to excessive heat preservation measures or excessive heat release. After extracting these patterns, the spatial position, maintenance time, temperature difference gradient and other parameters can be labeled and classified, and finally an "internal temperature distribution pattern library" is formed, which provides a structural template reference for subsequent rule calculation and intelligent control model. The temperature change during the hardening process of concrete has periodic and phased characteristics, especially in alpine regions where the environmental temperature fluctuates frequently, the temperature response capacity of concrete at different times is significantly different. Therefore, after obtaining the temperature fluctuation evolution graph and distribution pattern, the time axis needs to be divided into cycles based on the actual construction period and thermal dynamics characteristics, and the thermal change rule is extracted in each cycle. The time cycle definition can be segmented according to the pouring start time, such as dividing into early heating period (0-12 hours), medium platform period (12-36 hours) and late cooling period (36-72 hours), or according to the natural day-night change for 24-hour cycle decomposition. Within the cycle, the temperature fluctuation evolution graph is analyzed and calculated by time frame difference, and the average temperature rise rate, temperature drop rate, thermal balance stable time and other key parameters of different positions are calculated, and trend regression analysis (such as using moving average or exponential smoothing method) is carried out. For example, in a certain project, the average temperature rise rate of the middle of the base plate within 72 hours is 0.43℃ / h, and the platform period maintenance time is 13 hours; while the edge position temperature maintains the platform period for less than 6 hours, showing a rapid cooling trend. These analyses can reveal the temperature response mode of concrete structure at different positions and time periods, and finally generate a set of temperature change rules for subsequent numerical simulation and control model calling.

[0080] To realize the prediction and intervention ability of the temperature regulation system on the concrete thermal field, the extracted internal temperature distribution pattern and temperature variation law need to be numeratized and embedded in the real-time simulation module, so as to establish a dynamically updated "real-time temperature distribution field" model. The model discretizes the three-dimensional structure of the fan foundation into a finite element grid (such as 0.2m in length), and calculates the temperature value of each grid node in real time. In the simulation calculation, the temperature change rate, thermal diffusion coefficient (generally taken as 1.0×10 -6 m 2 / s) and time period variation coefficient are introduced, and the sensor data is updated in real time as the boundary condition input. The simulation algorithm can use finite difference method (FDM) or finite element heat conduction model, combined with GPU parallel processing to ensure real-time calculation. The model output is the three-dimensional spatial distribution state of the internal temperature of the entire wind power foundation concrete structure at each time, which can be visualized by heat map or isotherm surface map. In the actual test, the error of the model in predicting the temperature distribution at 36 hours is controlled within ±1.2℃, which shows that it has good dynamic response ability and spatial simulation accuracy. The real-time temperature distribution field provides a basis for environmental intervention simulation, intelligent heating control and structure thermal stress analysis. The internal temperature field of concrete is not only affected by material heat release, but also highly dependent on surface environmental factors such as wind speed, air temperature, humidity and radiation heat. To realize heat exchange modeling, a surface environmental parameter acquisition system needs to be built. The system should have adaptive frequency control ability, and adjust the sampling frequency according to different construction stages, day and night changes or sudden weather conditions. Usually the wind speed changes frequently during the day, and the sampling period is set to 10 minutes; at night it can be extended to 30 minutes or 60 minutes. The sensor layout includes infrared surface thermometer, anemometer, hygrometer and radiation thermometer, which are installed at the periphery of the foundation at a height of 1.5 meters and on the tower foundation surface. In the actual test, during the construction of a highland wind farm foundation, the surface temperature at night was as low as-25℃, and the diurnal temperature difference reached 18℃; the maximum instantaneous wind speed reached 10.2m / s, which significantly disturbed the heat flux density on the concrete surface. The acquisition system supports edge computing and anomaly identification to ensure timely response in the event of strong cooling or strong wind, and to improve the real-time and accuracy of the input of the heat exchange model. The extracted environmental parameters will be used as the boundary conditions of the heat flux on the outer surface of the concrete, providing external input support for heat exchange simulation.

[0081] After the surface environmental parameter extraction, a heat exchange simulation model between the environment and the internal temperature needs to be constructed to quantify the energy transfer process between the two. There are mainly three mechanisms between the concrete structure surface and the environment: convective heat transfer, radiative heat transfer, and thermal conduction. The mathematical modeling relies on the steady-state and transient heat conduction equations. In the simulation process, the environmental temperature, wind speed, and radiation heat data are used to apply dynamic boundary conditions to the surface nodes, and the Newton cooling law (Q = hAΔT) is used to calculate the heat flux per unit time; the convective heat transfer coefficient h will be dynamically adjusted with the wind speed (e.g., wind speed 0-10 m / s corresponds to h value range of 5-50 W / m 2 ·K). The simulation can be performed using multi-physics software such as COMSOL or Python self-built model, and embedded into the real-time temperature control platform. In a sudden wind speed increase event during the night in actual engineering, the simulation data shows that the heat flux of the tower foundation edge area accumulates to 8500 J / m 2 in 4 hours, causing the local concrete temperature to drop by more than 3.5℃. The simulation data reveals the direct impact of environmental changes on the internal temperature field of the concrete, providing quantitative basis for intelligent insulation decisions (such as local heating or thermal film covering), and laying the foundation for the next step of building the environment-internal relationship model

[0082] In this embodiment, the specific steps for collecting the adaptive frequency parameters of the wind turbine foundation construction area and extracting the concrete surface environmental parameters are as follows:

[0083] Topological analysis of the wind turbine foundation construction area is performed to extract the topological structure characteristics of the construction area.

[0084] According to the topological structure characteristics of the construction area, key equipment nodes and redundant areas are identified to extract core equipment areas and redundant areas.

[0085] Based on the core equipment areas and redundant areas, a multi-layer environment architecture is modeled to construct a three-layer environment monitoring framework, including a core temperature monitoring layer, a gradient change perception layer, and a boundary environment monitoring layer.

[0086] Based on the three-layer environment monitoring framework, adaptive sampling frequency adjustment is performed, and multi-dimensional surface environmental parameter collection is performed to extract the concrete surface environmental parameters.

[0087] In this embodiment, during the foundation construction process of high-power wind turbines in cold regions, due to the large scale of concrete structures, complex component distribution, and significant differences in heat conduction paths, it is necessary to first conduct regional topology analysis of the entire construction area to comprehensively identify its structural spatial characteristics and heat conduction relationships. The core of topology analysis is to abstract the concrete structure from the physical layer to a node-edge model, identifying the relative spatial position, contact relationship, heat propagation path, and construction level of each component (such as the bottom plate, pile cap, anchoring cage, and edge thickening zone). In specific practice, BIM models (Building Information Modeling) and site construction drawings are often combined, supplemented by laser scanning measurement and coordinate conversion, to construct a three-dimensional topology structure atlas with centimeter-level precision. Taking a 6.5MW wind turbine as an example, its foundation bottom plate has a diameter of 22 meters and a thickness of more than 2.8 meters, with anchor cages arranged within a 4-meter radius. Through topology analysis, five heat-affected structural units are identified, among which the anchoring area becomes the heat accumulation center due to the dense steel reinforcement and large heat capacity, while the outer edge area becomes the heat flow dissipation end due to its proximity to the air-soil interface, short heat conduction path, and rapid cooling. These structural differences will have a significant impact on subsequent temperature control strategies, and topology structure extraction is therefore a fundamental work for heat distribution modeling and environmental monitoring level construction. After completing the topology structure analysis, it is necessary to identify the construction area based on thermal response characteristics and functional importance to extract core equipment areas and redundant areas. This process combines structural position, thermal coupling strength, construction sensitivity, and post-operation requirements to make judgments. Key equipment nodes usually refer to locations that are in the thermal center, functionally dense, and have extremely high requirements for temperature control accuracy, such as the anchoring bolt arrangement area, the area around the main pressure reinforcement, and the center of large-volume pouring under the pile cap. These areas are prone to early cracking or strength decline problems when temperature control is unbalanced. Redundant areas are usually located at the edges of the concrete or non-critical heat paths, such as the four corners of the bottom plate, the surrounding of the ventilation channel, and non-load-bearing areas of the structure. Although they are coupled with the overall thermal field, their temperature fluctuations have limited impact on structural safety. In actual projects, through analysis of the 72-hour average temperature rise rate and temperature peak value distribution of each area of the concrete, it is found that the temperature rise rate of the core area can reach 0.86°C / h, which is much higher than the 0.35°C / h of the edge area, with a thermal response time difference of more than 9 hours. Combined with the structure diagram and thermal response results, the boundaries of various areas can be accurately determined, providing spatial basis for the next step of multi-layer monitoring architecture division. The results of this area identification enable precise placement of monitoring resources, improve data collection efficiency, and avoid redundant point placement and excessive monitoring problems.

[0088] After the thermal response differences of each region of the structure are identified, a layered environmental monitoring framework can be constructed accordingly to achieve differentiated collection in different regions and multi-scale thermal information fusion. The three-layer environmental monitoring framework proposed in this step includes a core temperature monitoring layer, a gradient change perception layer, and a boundary environmental monitoring layer. The core temperature monitoring layer is equipped with high-precision and high-frequency sampling thermocouples or optical fiber thermometers in the key equipment area to capture the central heat release rate, temperature peak appearance time, and local thermal imbalance risk. The sampling frequency is recommended to be 5 minutes per time. The gradient change perception layer is distributed in the transition area between the core and the edge, mainly used to monitor the thermal gradient change trend and predict the temperature field diffusion direction. It uses medium-precision Pt100 or thermistor elements, with a spacing of 1-1.5 meters and a sampling frequency of 10-15 minutes per time. The boundary environmental monitoring layer is placed at the contact position of the concrete outer edge, the formwork outer wall, the surface insulation layer, and the surrounding air, equipped with infrared temperature measurement points, anemometers, radiometers, etc., to obtain the heat exchange boundary data of the concrete and the environment. In a certain construction project, 72 sensing points are distributed in the three-layer structure, accounting for about 40%, 35%, and 25%, respectively, and the point distribution is dynamically adjusted according to the feedback of the structure's thermal response. This three-layer architecture not only enhances the spatial analysis capability of the internal thermal state of the structure, but also enhances the dynamic response performance under external environmental disturbances, and is the basic framework for intelligent temperature control and thermal field prediction. After the three-layer environmental monitoring framework is built, the system needs to further introduce an adaptive sampling frequency adjustment mechanism to adapt to the rapidly changing environmental conditions in high-cold regions and achieve multi-dimensional collection of factors affecting the heat exchange of the concrete surface. Adaptive frequency adjustment relies on real-time sensing data variation amplitude and trend calculation. For example, when the external temperature drops by more than 0.5°C within 24 minutes or the wind speed exceeds 8 m / s instantaneously, the system automatically increases the sampling frequency of the core area from 10 minutes per time to 3 minutes per time, and the sampling frequency of the boundary layer is increased to 5 minutes per time, ensuring the real-time and continuity of the data. This mechanism uses edge computing modules to judge and schedule fluctuations, avoiding excessive load on the central server. At the same time, in multi-dimensional surface environmental parameter collection, the system is equipped with an infrared non-contact thermometer for surface temperature acquisition, an anemometer for convective heat exchange monitoring, a radiometer for solar heat flux estimation, and humidity and air pressure monitoring points for evaporation heat exchange parameter estimation. In a high-cold wind field application, the minimum temperature reaches -28.6°C, and the daytime temperature difference exceeds 16°C. The system dynamically responds to severe climate changes through adaptive sampling, and the error of the surface environmental temperature data is controlled within ±0.7°C. The final concrete surface environmental parameter data will be used as input for the heat exchange model to dynamically simulate the energy coupling behavior of the concrete and the external thermal field, which is the prerequisite for active adjustment of the temperature control strategy.

[0089] In this embodiment, reference is made to Figure 4The specific steps of obtaining the historical meteorological log of the construction area and the meteorological environment data of the construction area, performing similar meteorological condition matching calculation, and performing short-term meteorological trend prediction to generate short-term meteorological trend prediction characteristics are as follows:

[0090] Obtain the historical meteorological log of the construction area; integrate meteorological radar, infrared thermal imaging, and wind speed and direction sensors to obtain the meteorological environment data of the construction area;

[0091] Perform historical meteorological change analysis on the historical meteorological log of the construction area to extract historical meteorological change condition information;

[0092] Perform time-series meteorological change analysis based on the meteorological environment data of the construction area to obtain time-series meteorological change characteristics;

[0093] Perform similarity calculation and most similar event matching on the historical meteorological change condition information based on the time-series meteorological change characteristics to obtain the most similar historical sample of the current meteorological environment;

[0094] Perform short-term meteorological trend prediction for the construction area according to the historical sample to generate short-term meteorological trend prediction characteristics.

[0095] In this embodiment, historical meteorological logs of the construction area need to be obtained. The historical meteorological logs usually contain multi-dimensional meteorological parameters such as temperature, humidity, wind speed, wind direction, air pressure, precipitation, and solar radiation intensity, and the time span generally covers more than 5 years to meet the needs of seasonal and annual climate change analysis. Data sources include the public database of the National Meteorological Bureau, local meteorological stations, and special environmental monitoring equipment installed during the construction of the wind farm. The collected historical meteorological data are processed in time series, such as outlier removal, missing value interpolation, and uniform timestamp standardization, to ensure the accuracy of subsequent analysis. Taking a certain alpine wind farm as an example, the annual average temperature of the construction area is between -15°C and 5°C, and the lowest temperature in winter once reached -38°C, and the maximum wind speed exceeded 20 m / s. The historical logs show that these extreme weather events have a significant impact on the concrete temperature field. By constructing a historical meteorological database, basic data support is provided for subsequent meteorological trend analysis and temperature regulation during construction. Based on the multi-sensor integration scheme, the construction site is arranged with ground-based radar, infrared thermal imaging instrument, and wind speed and direction sensor to form a multi-source data fusion system covering the area. The weather radar can remotely monitor cloud movement, precipitation intensity, and range, providing spatial dynamic information for temperature change warning. The infrared thermal imaging technology captures the temperature distribution of the ground and the concrete surface in real time, helping to judge the influence of external heat and cold sources. The wind speed and direction sensor is in the form of ultrasonic or mechanical equipment, arranged at key wind ports and open sites, collecting high-resolution wind speed (0-50 m / s, accuracy ±0.1 m / s) and wind direction (360°, accuracy ±2°) data. These data are real-time aggregated to the central monitoring platform through a wireless transmission network, combined with a time synchronization mechanism to ensure data consistency. Field experiments show that the combination of radar data and ground temperature sensors improves the timeliness and spatial resolution of meteorological change response, providing accurate environmental input parameters for the intelligent temperature control system.

[0096] Based on the complete historical meteorological log, time series statistics and pattern recognition techniques are used to analyze historical meteorological changes. First, the long-term trend, seasonal fluctuations and residual terms are extracted by time series decomposition methods such as seasonal-trend decomposition STL to identify the periodic characteristics and abnormal events of the construction area. Combined with clustering analysis such as K-means and DBSCAN, the meteorological state is classified into several typical meteorological categories such as routine, cold wave, storm, and frost. Taking a high-cold wind field as an example, it is found that the frequency of frost events in winter is about 25 times per year, and the duration is 12 hours on average. The cold wave event with wind speed exceeding 10 m / s occurs 3 times a year on average. Further, the temperature gradient, wind speed fluctuation amplitude and humidity change rate are calculated by statistical methods to form the meteorological change information set. This information not only reflects the intensity and frequency of meteorological changes, but also reveals the potential influence of meteorological changes on the concrete thermal environment, providing historical reference samples for similarity matching and prediction models. Combined with real-time acquisition of multi-source meteorological environmental data, high-resolution time series meteorological change analysis is carried out. Through sliding time window method, temperature, wind speed, radiation intensity and other key parameters are smoothed and fitted to extract the instantaneous change trend and periodic fluctuation characteristics. For example, using a 10-minute sliding window to calculate the temperature change rate, wind speed acceleration and other indicators, meteorological mutations or slow evolution processes are identified. Using autocorrelation function (ACF) and power spectrum analysis methods, the time correlation and frequency spectrum characteristics of meteorological variables are revealed. In the measured data, it is found that the wind speed peaks between 9:00 and 15:00, the daily temperature difference fluctuation amplitude reaches 12℃, and the night temperature decreases exponentially. In addition, through multivariate time series analysis model such as Vector Autoregression (VAR), the mutual influence relationship between different meteorological elements is analyzed, which provides a basis for dynamic prediction and correlation modeling. This time series feature description helps to capture the real-time challenges of environmental fluctuations on concrete temperature control.

[0097] To improve the accuracy of weather trend prediction, the similarity calculation method is used to compare the current time series weather change characteristics with the historical weather change condition information, and the most similar historical weather event sample is selected. Common similarity measures include dynamic time warping (DTW) and Euclidean distance. DTW can adapt to nonlinear alignment on the time axis and is suitable for comparison of weather data rhythm misalignment. By constructing a multi-dimensional weather feature vector (including temperature change rate, wind speed and direction pattern, humidity change, etc.) and weighting each dimension, the matching priority of key weather factors is improved. Taking a certain construction day data as an example, two high-cold cold wave events in the past three years are matched as the most similar samples, and the temperature change trend and wind speed fluctuation pattern are consistent with more than 87%. The matching result not only provides historical weather reference for the current construction environment, but also provides training set for short-term prediction model, which helps to accurately capture the impact of potential extreme weather on concrete temperature. Using the matched most similar historical sample as the prior condition, combined with real-time weather data, time series prediction algorithm is used to predict the future short-term weather trend in the construction area. Common methods include deep learning models based on recurrent neural network (RNN) and long short-term memory network (LSTM), which are suitable for weather prediction in high-cold extreme climate conditions due to their good modeling ability for nonlinear complex time series data. The training process integrates historical weather data and real-time monitoring data, and the model outputs the temperature, wind speed and humidity change curve in the next 6 to 72 hours. The prediction result is verified by statistics, with an error control within ±1.2℃ temperature and ±1.5m / s wind speed range, which can early warning possible cold wave, frost or gale event. By accurately grasping the short-term weather trend, the system can dynamically adjust the concrete temperature control strategy, reasonably arrange heating, insulation and ventilation measures, and ensure the structural safety and construction quality of concrete under extreme weather conditions.

[0098] In this embodiment, the temperature-environment quantitative relationship model based on short-term weather trend prediction characteristics is used to predict the short-term multi-region temperature trend and fit the regional temperature change distribution, and the specific steps of constructing the natural temperature change prediction distribution field are as follows:

[0099] Based on the short-term weather trend prediction characteristics, the temperature-environment quantitative relationship model is used for deep convolution learning, and the meteorological natural temperature evolution dynamics analysis is carried out, and the construction area temperature evolution twin model is constructed;

[0100] Based on the construction area temperature evolution twin model, the short-term multi-region temperature trend is predicted, and the short-term temperature trend prediction values of different regions are generated;

[0101] The temperature change amplitude and range distribution of the short-term temperature trend prediction value are calculated;

[0102] Based on the temperature change amplitude and range distribution, a regional temperature change distribution fitting is performed to construct a natural temperature change prediction distribution field.

[0103] In this embodiment, short-term meteorological trend prediction features (including temperature, wind speed, humidity, and other multi-dimensional time series data) and environmental temperature data of the concrete construction area are input into a pre-established temperature-environment quantitative relationship model. A multi-layer convolution layer is used to extract spatial-temporal features of the input data, capture complex nonlinear temperature-environment correlation features, and improve the expression ability of the model to environmental temperature fluctuations. The convolution learning process focuses on the natural temperature evolution dynamics under meteorological conditions, extracts local spatial temperature gradients and time evolution rules through convolution kernels, and realizes deep understanding of dynamic temperature fields. Based on this training, a temperature evolution twin model of the construction area is constructed, which simulates the change process of the real concrete temperature under different meteorological conditions and accurately reflects the influence of environmental changes on the concrete thermal field. In the experiment, the model is verified under a typical high-cold construction environment (temperature -30℃ to 5℃, wind speed 0-15m / s), and the prediction error is controlled within ±0.8℃, which reflects the high adaptability and accuracy of the model to temperature evolution under extreme climate conditions. The construction area is divided into multiple temperature monitoring sub-areas, and the meteorological environment parameters and historical temperature data of the corresponding areas are input into the twin model. The model predicts the internal and surface temperature change trend of each area within 6 to 72 hours. In this process, a division granularity of about 5 meters is used to ensure fine-grained temperature dynamic capture. The model outputs the temperature trend prediction value of each sub-area, reflecting the internal temperature change trend and possible local thermal stress concentration. Experimental data shows that the average temperature error of the twin model in different sub-areas is maintained at ±0.7℃, effectively supporting the accurate implementation of local temperature control measures during construction. This prediction result provides a multi-dimensional temperature trend view for construction management personnel, facilitating the development of differentiated intelligent heating and insulation strategies, and especially showing significant application value in high-cold environments with high wind speed and sudden temperature drop.

[0104] The temperature variation amplitude refers to the maximum fluctuation of the temperature within the prediction time window, usually quantified in degrees Celsius, calculated as the highest predicted temperature minus the lowest predicted temperature in the region. The range distribution is determined by statistical analysis methods to determine the spatial coverage of the temperature fluctuations reaching a certain threshold (such as ±3℃, ±5℃, etc.). In specific implementation, the sliding window method is used to extract the local maximum and minimum values of the time series temperature data of each sub-region, and the temperature difference in the time interval is calculated. At the same time, through the spatial interpolation algorithm (such as Kriging interpolation) combined with the temperature variation data, the distribution form of the temperature fluctuation in space is depicted. Experimental parameters show that during the prediction period of a typical winter cold wave event, the temperature variation amplitude in the core region can reach 8℃, and in the edge region it is about 5℃. The temperature variation range distribution is relatively concentrated, mainly concentrated in the active construction area and the tuyere area. The calculation results provide a quantitative basis for the dynamic response of the construction temperature control system, help to identify high-risk temperature difference areas, and achieve local precise temperature control.

[0105] By mathematical fitting and physical modeling methods, the natural temperature variation prediction distribution field of the construction area is constructed. The fitting process uses a combination of polynomial regression and Gaussian process regression to smooth the fitting of the spatial temperature variation field, ensuring that the temperature variation field can reflect both local details and global coherence. At the same time, a temperature diffusion model is introduced, combined with the thermal conductivity characteristics (thermal conductivity of about 1.7 W / (m·K)) of concrete materials and environmental boundary conditions, to simulate the diffusion process of heat in the concrete structure. Through iterative calculation, a continuous spatial temperature prediction field is generated, which is represented as a distribution map of temperature prediction values at each location in the construction area in the future time period. Experimental verification shows that the prediction accuracy of this distribution field under multiple cold weather events is better than that of the traditional linear interpolation method, with an average error reduction of about 15%. This prediction distribution field not only provides comprehensive spatial temperature dynamic reference for the construction temperature control system, but also supports the development of intelligent temperature regulation strategies, achieving temperature safety protection for concrete construction in cold regions.

[0106] In this embodiment, the specific steps for generating regional differentiated temperature control instructions based on the natural temperature variation prediction distribution field and conducting differentiated regional heating power demand analysis and preventive temperature regulation are as follows:

[0107] Identify the array of industrial-grade air heaters; calculate the position coordinates of each module in the array of industrial-grade air heaters, and match them based on the natural temperature variation prediction distribution field to obtain matching information;

[0108] According to the matching information, conduct differentiated regional heating power demand analysis to generate heating power demand values for different heating modules;

[0109] Based on the heating power demand values, calculate the heating temperature rise time and perform optimal heating time point calculation to obtain the optimal heating time point;

[0110] Preventive temperature regulation is performed based on the heating power requirement value and the optimal heating time point, to generate a region-differentiated temperature regulation instruction.

[0111] In this embodiment, the number and distribution state of all heating modules in the field are identified and confirmed through the device management system and the sensor network. Radio frequency identification (RFID), wireless sensor network (WSN), or positioning system (such as UWB positioning technology) is used to spatially locate each heating module, accurately calculate its three-dimensional position coordinates, and control the positioning error within ±0.1 meters. After completing the spatial coordinate collection, the positions of the modules are mapped to the predicted distribution field of natural temperature variation in the construction area, and the temperature variation characteristics of the position where each module is located are analyzed through a spatial matching algorithm (such as nearest neighbor matching, spatial interpolation method). This matching process helps to identify the temperature variation requirements of the area where the heating module is located, and forms the matching information of the heating module and the temperature prediction field. In the experiment, the module array layout covers an area of about 500 square meters, and the spatial matching processing time is less than 30 seconds, ensuring real-time response capability. The heating power requirement of each heating module is calculated using the temperature variation amplitude, variation rate, and historical temperature data, combined with the heat capacity and heat conduction characteristics of the concrete material. Specifically, a thermodynamic energy balance model is used, combined with the regional temperature compensation coefficient and heat loss parameters, to quantitatively analyze the energy supplement requirements of different modules in future temperature fluctuations. For example, for areas with large temperature prediction fluctuations, the power requirement value will significantly increase. In this process, the module power adjustment range (such as 0-5 kW) and the coordination of power distribution between modules are considered to ensure balanced load of the overall heating system. Experimental parameters show that in a winter night low temperature environment (-25℃), the peak heating power requirement of the core area can reach 4.5 kW, while the edge area only needs about 1.2 kW. This differentiated analysis supports subsequent precise temperature control and avoids energy waste.

[0112] After determining the heating power requirement, the temperature rise time of each module from starting heating to reaching the predetermined temperature (e.g., concrete surface temperature ≥ 5℃) is further calculated. By combining the concrete heat conduction equation and the module heat power characteristics, the temperature variation dynamics of the heating process are simulated using numerical simulation methods (e.g., finite difference method) to estimate the time required for heating. This calculation takes into account environmental heat dissipation conditions (wind speed, air temperature, etc.) and the response delay of the heating module. Subsequently, based on the temperature rise time and the short-term temperature prediction model, the optimal heating timing algorithm is executed to determine the optimal time point for each module to start heating, in order to achieve the predetermined temperature while reducing invalid heating time and energy consumption. It is found in experiments that, in typical high-cold nights, starting the heating about 30 to 45 minutes in advance can effectively prevent the concrete temperature from dropping sharply. This calculation process realizes the time optimization control of the heating system, improving the overall heating efficiency and construction safety. Combined with the heating power requirement and the optimal starting time obtained from the previous steps, the system generates specific preventive temperature regulation instructions. The regulation instructions include the power setting, start / stop time points, and adjustment strategies of the heating module, supporting dynamic control of the module in different time periods and power in the region. Through industrial control protocols (such as Modbus, CAN bus), the instructions are sent to each heating module on site to realize precise temperature regulation. Preventive regulation is based on temperature prediction, starting heating in advance to avoid temperature drop and reduce the risk of freezing damage; at the same time, it dynamically adjusts according to environmental parameters to prevent overheating and waste of resources. In practical applications, the system response time is less than 5 seconds, supporting minute-level dynamic adjustment. The instruction generation strategy ensures that different regions are tailored to local conditions and flexibly adapt to environmental changes, maximizing the uniformity and safety of concrete construction temperature.

[0113] In this embodiment, the warm air temperature control is executed based on the regional differentiated temperature regulation instructions, and iterative regulation learning is performed to construct a warm air temperature control optimization model. The specific steps are as follows:

[0114] The warm air temperature control is executed based on the regional differentiated temperature regulation instructions, and the regional temperature regulation feedback information is collected.

[0115] The regional temperature regulation feedback information is analyzed for each regional temperature regulation response, and the response delay is calculated to obtain a plurality of regional regulation delay values.

[0116] The specified temperature range is analyzed according to the specified temperature range of the regional differentiated temperature regulation instructions.

[0117] The temperature regulation deviation of the specified temperature range is calculated based on the regional temperature regulation feedback information to obtain a real-time temperature regulation deviation curve.

[0118] According to the multi-zone regulation delay value and real-time temperature regulation deviation curve, intelligent heating parameter optimization is carried out, and iterative regulation learning is carried out to construct a warm air heater temperature control optimization model.

[0119] In this embodiment, the control system sends instructions to each warm air heater heating module through an industrial communication protocol. The module adjusts the heating power and start-stop time according to the instructions to complete multi-point and multi-level temperature control in the construction area. At the same time, the temperature sensors deployed in the construction area collect concrete and surface temperature data in real time, forming a complete feedback information flow. The feedback information covers the temperature changes, heating response state and environmental parameter changes of each sub-area, and is uploaded to the central monitoring system in real time. To ensure data accuracy, the collection frequency is set to once per minute, and the sensor accuracy requirement is within ±0.2℃. During the experiment, the real-time and accuracy of temperature feedback directly affect the subsequent regulation and optimization effect. The system response delay is controlled within 5 seconds, ensuring the continuity and effectiveness of real-time control. For the collected temperature regulation feedback information, the system analyzes the temperature response effect of each region in detail. The specific method is to compare the time of issuing the heating instruction with the time of actual temperature change in the corresponding region, and calculate the response delay value, that is, the time difference between the implementation of the regulation instruction and the temperature feedback change. Time series analysis methods such as cross-correlation function (Cross-Correlation Function) are used to calculate the time lag of the regulation signal and temperature change. In addition, the response amplitude of each region is compared with the expected target to evaluate the regulation effect. In the experiment, the wind speed changes greatly in the high-cold environment, resulting in a longer response delay in some edge areas, with a maximum delay of 15 minutes, while the response delay in the core heating area generally remains at 3-5 minutes. Through this response delay analysis, the differences in regulation effect of each region are clear, providing an important basis for subsequent temperature control parameter optimization.

[0120] Based on the regional difference regulation instruction, the specified temperature control range of each construction sub-region is analyzed and determined. The specified temperature range is usually the safe temperature interval specified by the construction process, for example, the concrete surface temperature is controlled between 3°C and 8°C to ensure the normal progress of the concrete hydration process and avoid freezing and cracking. In the analysis process, the historical temperature control instruction data and the actual environmental temperature are combined, and the statistical method is used to calculate the reasonable interval of the upper and lower limits of the temperature, to ensure that the temperature control instruction can cover the variable climate conditions. The tolerance analysis based on interval estimation is used to dynamically adjust the specified temperature range to adapt to the temperature fluctuations during construction. Experimental data show that the specified temperature range is moderately increased at night in high-cold areas (such as 5°C to 10°C) to enhance the frost resistance of concrete. Through reasonable analysis of the temperature control range, the balance between safety and energy saving of construction temperature control is achieved. Combined with the temperature monitoring data and the specified temperature control range of the foregoing feedback, the system calculates the temperature control deviation in real time, i.e. the deviation of the actual measured temperature from the target temperature range. By recording the deviation value at each time, the real-time temperature regulation deviation curve of each region is constructed. The deviation calculation uses error functions (such as absolute error, mean square error, etc.) to reflect the accuracy and stability of temperature control. The temperature control deviation curve helps to identify temperature overshoot, under-regulation and fluctuation problems, and analyzes the timeliness and effectiveness of concrete temperature control. In the experiment, under the typical-20°C low temperature environment, the deviation curve shows that there is a 0.5-1.2°C deviation fluctuation in some edge areas, reflecting the lack of local regulation. This data provides an intuitive basis for subsequent intelligent optimization and regulation, ensuring that the temperature control system can be adjusted in time to improve the overall temperature control level.

[0121] Based on the obtained regional regulation delay value and temperature control deviation curve, machine learning methods, especially reinforcement learning and recurrent neural network (RNN), are used to realize dynamic optimization of intelligent heating parameters. The system uses historical regulation effects as training samples to establish a mapping relationship between regulation response and parameter adjustment, and gradually reduces the response delay and temperature control deviation through iterative learning. The model can predict future temperature trends based on the current environmental state and historical regulation data, and actively adjust the heating power, start time and adjustment frequency to realize pre-control. The warm air heater temperature control optimization model can reduce the temperature control deviation by more than 30% in actual operation, and the response delay is shortened to 1-2 minutes, significantly improving the accuracy and real-time performance of concrete temperature control during construction. Experimental verification shows that the model adapts to complex meteorological fluctuations in high-cold areas and ensures a safe temperature environment for concrete construction.

[0122] In this embodiment, an intelligent temperature control device for wind turbine foundation construction in high-cold areas is provided for performing the intelligent temperature control method for wind turbine foundation construction in high-cold areas as described above, comprising:

[0123] A temperature fluctuation distribution module is configured to collect real-time concrete temperature monitoring parameters based on a distributed temperature sensor, perform time-series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution, and construct a temperature fluctuation distribution evolution diagram;

[0124] A coupling correlation module is configured to extract concrete surface environment parameters, perform heat exchange simulation processing on the temperature fluctuation distribution evolution diagram, and perform multi-element coupling correlation analysis to construct a temperature-environment quantitative relationship model;

[0125] A meteorological trend prediction module is configured to obtain historical meteorological logs of a construction area and meteorological environment data of the construction area, perform similar meteorological condition matching calculation, and perform short-term meteorological trend prediction to generate short-term meteorological trend prediction features;

[0126] A temperature trend prediction module is configured to perform short-term multi-region temperature trend prediction and regional temperature change distribution fitting on the temperature-environment quantitative relationship model based on the short-term meteorological trend prediction features, and construct a natural temperature change prediction distribution field;

[0127] A differential temperature regulation module is configured to perform differential regional heating power demand analysis based on the natural temperature change prediction distribution field, and perform preventive temperature regulation to generate regional differential temperature regulation instructions;

[0128] An intelligent temperature control optimization module is configured to perform temperature control execution of a warm air blower based on the regional differential temperature regulation instructions, and perform iterative regulation learning to construct a warm air blower temperature control optimization model.

[0129] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the present application being defined by the appended claims and not by the above description, therefore all variations falling within the meaning and scope of the equivalent elements of the application file are intended to be included in the present application.

[0130] The above description is merely that of specific embodiments of the application, enabling a person skilled in the art to understand or implement the application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application shall not be limited to these embodiments shown herein, but shall conform to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions, characterized in that, Includes the following steps: Based on the real-time concrete temperature monitoring parameters collected by distributed temperature sensors, time-series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution are performed to construct a temperature fluctuation distribution evolution map. Environmental parameters of the concrete surface were extracted, and the heat exchange simulation was performed on the temperature fluctuation distribution evolution diagram. Multivariate coupling correlation analysis was conducted to construct a quantitative relationship model between temperature and environment. Historical meteorological logs and meteorological environment data of the construction area are obtained, similar meteorological conditions are matched and calculated, and short-term meteorological trend prediction is performed to generate short-term meteorological trend prediction features. Based on the short-term meteorological trend prediction characteristics, the temperature-environment quantitative relationship model is used to predict the short-term multi-regional temperature situation and fit the regional temperature change distribution, and to construct a natural temperature change prediction distribution field. Based on the predicted distribution field of natural temperature changes, we conduct differentiated regional heating power demand analysis, carry out preventive temperature regulation, and generate regional differentiated temperature regulation instructions. The temperature control of the heater is executed based on regionally differentiated temperature control commands, and iterative control learning is performed to build an optimized temperature control model for the heater.

2. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for collecting real-time concrete temperature monitoring parameters based on distributed temperature sensors, performing time-series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution, and constructing the temperature fluctuation distribution evolution are as follows: Real-time concrete temperature monitoring parameters in the wind turbine foundation construction area are collected using distributed temperature sensors. Abnormal parameter filtering is performed on the real-time concrete temperature monitoring parameters to obtain optimized abnormal temperature monitoring parameters. Perform individual sensor spatial positioning calculations on the distributed temperature sensors to extract the spatial position coordinates of multiple sensors; Perform time-series temperature dispersion trend analysis on abnormal optimized temperature monitoring parameters to generate time-series temperature dispersion trend curves; Based on the spatial location coordinates of multiple sensors, the spatial temperature fluctuation distribution evolution of the discrete trend curve of time-series temperature is carried out, and a temperature fluctuation distribution evolution map is constructed.

3. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 2, characterized in that, The specific steps for filtering out abnormal parameters from real-time concrete temperature monitoring parameters to obtain optimized temperature monitoring parameters are as follows: Define a sliding time window of fixed length; Based on the sliding time window, a sliding window fitting analysis is performed on the real-time temperature monitoring parameters to extract temperature monitoring parameters from multiple time windows. Calculate the fitting residuals, temperature slope, and temperature change rate of the temperature monitoring parameters; Temperature jumps between adjacent time windows are detected based on temperature slope and temperature change rate, and abnormal temperature jump points are marked. Based on the fitted residuals, slope change rate analysis is performed, and slope deviation is gradually identified to mark abnormal temperature drift points. Abnormal temperature jump points and abnormal temperature drift points are identified as abnormal temperature monitoring points. Perform sensor monitoring error analysis on abnormal temperature monitoring points, and extract error monitoring points and abnormal outlier monitoring points; Calculate the multi-point average temperature monitoring parameters of the real-time concrete temperature monitoring parameters; Based on the multi-point average temperature monitoring parameters, the error monitoring points are replaced by mean interpolation, and outlier monitoring points are filtered out to obtain abnormal optimized temperature monitoring parameters.

4. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for extracting concrete surface environmental parameters, simulating the heat exchange of temperature fluctuation distribution evolution diagrams, performing multivariate coupled correlation analysis, and constructing a temperature-environment quantitative relationship model are as follows: Based on the temperature fluctuation distribution evolution map, the internal temperature distribution of concrete is mined and the internal temperature distribution pattern is extracted. Define a time period, perform logical calculations on the temperature fluctuation distribution evolution diagram for multiple periods of temperature change, and generate temperature change patterns; Numerical real-time simulation is performed based on the internal temperature distribution pattern and temperature change law to generate a real-time temperature distribution field; Adaptive frequency parameters are collected in the construction area of ​​the wind turbine foundation, and environmental parameters of the concrete surface are extracted. Based on the environmental parameters of the concrete surface, heat exchange simulation processing of the real-time temperature distribution field is performed to generate simulation data of environmental-internal temperature heat exchange. Multivariate coupling correlation analysis was performed on the simulation data of environmental-internal temperature heat exchange, and the temperature change response was quantified to construct a quantitative relationship model between temperature and environment.

5. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 4, characterized in that, The specific steps for acquiring adaptive frequency parameters and extracting concrete surface environmental parameters in the wind turbine foundation construction area are as follows: A regional topology analysis was performed on the wind turbine foundation construction area to extract the topological features of the construction area. Based on the topological characteristics of the construction area, key equipment nodes and redundant areas are identified, and core equipment areas and redundant areas are extracted. Based on the core equipment area and the redundant area, a multi-layer environmental architecture model is constructed to build a three-layer environmental monitoring framework, which includes a core temperature monitoring layer, a gradient change sensing layer and a boundary environment monitoring layer. Based on a three-layer environmental monitoring framework, adaptive sampling frequency adjustment is performed, and multi-dimensional surface environmental parameters are collected to extract concrete surface environmental parameters.

6. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for obtaining historical meteorological logs and meteorological environment data of the construction area, performing similar meteorological condition matching calculations, and generating short-term meteorological trend prediction features are as follows: Acquire historical weather logs for the construction area; integrate weather radar, infrared thermal imaging, and wind speed and direction sensors to acquire meteorological environmental data for the construction area; Historical meteorological changes were analyzed from historical meteorological logs of the construction area to extract information on historical meteorological changes. Based on meteorological environmental data of the construction area, a time-series meteorological change analysis was conducted to obtain the characteristics of time-series meteorological changes. Based on the characteristics of time-series meteorological changes, similarity calculations and most similar event matching are performed on historical meteorological change information to obtain the most similar historical samples for the current meteorological environment. Based on the historical samples, short-term weather trend predictions for the construction area are generated, resulting in short-term weather trend prediction features.

7. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for constructing a natural temperature change prediction distribution field by using a temperature-environment quantitative relationship model based on short-term meteorological trend prediction characteristics to predict short-term multi-regional temperature trends and fit regional temperature change distribution are as follows: Based on the short-term meteorological trend prediction characteristics, a deep convolutional learning model of the temperature-environment quantitative relationship is performed, and a dynamic analysis of the evolution of meteorological natural temperature is conducted to construct a twin model of temperature evolution in the construction area. Short-term multi-regional temperature trend prediction is performed based on the twin model of temperature evolution in the construction area, generating short-term temperature trend prediction values ​​for different regions. Calculate the temperature change amplitude and range distribution of the short-term temperature trend prediction values; Based on the temperature change amplitude and range distribution, a regional temperature change distribution is fitted to construct a natural temperature change prediction distribution field.

8. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for analyzing differentiated regional heating power demand based on the predicted distribution field of natural temperature changes, performing preventative temperature control, and generating regional differentiated temperature control commands are as follows: Identify the industrial-grade heater module array; calculate the position coordinates of each module in the industrial-grade heater module array, and match them based on the distribution field predicted by natural temperature changes to obtain matching information; Based on the matching information, perform differentiated regional heating power demand analysis to generate heating power demand values ​​for different heating modules; The heating time is calculated based on the heating power requirement value, and the optimal heating timing is calculated to obtain the optimal heating time point. Based on the heating power demand and the optimal heating time, preventative temperature control is performed to generate regionally differentiated temperature control commands.

9. The intelligent temperature control method for wind turbine foundation construction in high-altitude and cold regions according to claim 1, characterized in that, The specific steps for executing the temperature control of the heater based on regionally differentiated temperature control commands, and for iteratively learning and constructing an optimized temperature control model for the heater are as follows: The temperature control of the heater is executed based on the regionally differentiated temperature control command, and regional temperature control feedback information is collected. The regional temperature control feedback information is analyzed on a regional basis, and the response delay is calculated to obtain multiple regional control delay values. Based on the regionally differentiated temperature control instructions, an analysis of the specified temperature range is performed to obtain the specified temperature range. Based on the regional temperature control feedback information, the temperature control deviation is calculated for a specified temperature range to obtain a real-time temperature control deviation curve. Intelligent heating parameters are optimized based on multiple regional control delay values ​​and real-time temperature control deviation curves, and iterative control learning is performed to build a temperature control optimization model for the heater.

10. An intelligent temperature control device for wind turbine foundation construction in high-altitude and cold regions, characterized in that, The intelligent temperature control method for wind turbine foundation construction in cold regions as described in claim 1 includes: The temperature fluctuation distribution module is used to collect real-time concrete temperature monitoring parameters based on distributed temperature sensors, perform time-series temperature discrete trend analysis and spatial temperature fluctuation distribution evolution, and construct a temperature fluctuation distribution evolution map. The coupling and correlation module is used to extract environmental parameters of concrete surface, perform heat exchange simulation processing on temperature fluctuation distribution evolution diagram, and conduct multivariate coupling and correlation analysis to construct a quantitative relationship model between temperature and environment. The meteorological trend prediction module is used to obtain historical meteorological logs and meteorological environment data of the construction area, perform similar meteorological condition matching calculations, and perform short-term meteorological trend prediction to generate short-term meteorological trend prediction features. The temperature trend prediction module is used to perform short-term multi-regional temperature trend prediction and regional temperature change distribution fitting based on the temperature-environment quantitative relationship model according to the short-term meteorological trend prediction characteristics, and to construct a natural temperature change prediction distribution field. The differentiated temperature control module is used to perform differentiated regional heating power demand analysis based on the predicted distribution field of natural temperature changes, and to perform preventive temperature control, generating regional differentiated temperature control commands. The intelligent temperature control optimization module is used to execute the temperature control of the heater based on regionally differentiated temperature control commands, and to perform iterative control learning to build a temperature control optimization model for the heater.

Images