Intelligent prediction method and system for phase change latent heat of road freezing based on LSTM neural network

Abstract

The invention relates to the technical field of artificial intelligence and deep learning, in particular to a road ice coagulation phase change latent heat intelligent prediction method and system based on an LSTM neural network, and the method comprises the steps: building a three-dimensional monitoring network: taking the side surface of a road as an X axis, the length direction as a Z axis, and the height direction as a Y axis, building a three-dimensional rectangular coordinate system, constructing a fiber grating sensor distributed topology network and a temperature monitoring network; a data acquisition and processing step: acquiring multi-dimensional state information; establishing a phase change physical model, taking phase change layer melting depth information as a sample label, and extracting a training data set and a test data set from the space-time simulation data; inputting the training data set into an LSTM network for training, and establishing a phase change state prediction model by taking the melting depth of the phase change layer as an output target; verifying the prediction precision of the LSTM network by using the test data set; and high-precision prediction of the road icing state is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of computer systems based on specific computing models, and in particular to a method and system for intelligently predicting the latent heat of road icing phase change based on an LSTM neural network. Background Art

[0002] Icy roads are a major threat to traffic safety in cold regions, with traffic accidents resulting from icy roads causing numerous casualties and property losses each year. Existing technologies primarily rely on manual inspections or simple temperature monitoring to determine if a road is icy, which can be time-consuming and subjective. Some regions resort to spreading salt or using chemical deicing agents to de-ice roads, which is not only inefficient but also pollutes and damages the environment and road structures. In recent years, some heating-based de-icing systems have emerged, but they often rely on simple temperature threshold control, resulting in low energy efficiency and limited early warning capabilities, making them unable to accurately predict and control complex road conditions.

[0003] Traditional road ice monitoring methods rely primarily on a single temperature parameter, lacking the support of intelligent computing models and failing to accurately capture the complex process of ice formation. Conventional technologies often implement measures after the road has already frozen, lacking foresight and resulting in delayed response. Furthermore, existing ice-melting systems often utilize comprehensive and uniform heating, lacking the intelligent decision-making capabilities of advanced computing models such as neural networks. This leads to significant energy waste and an inability to dynamically adjust to the actual state of the ice, potentially causing overheating or underheating.

[0004] With the development of artificial intelligence (AI), deep learning models such as LSTM (Long Short-Term Memory) neural networks have shown great potential in time series forecasting. However, they have yet to be fully applied in road icing prediction. Existing technologies lack methods that combine physical models with deep learning techniques, making it difficult to fully utilize multi-source data for accurate predictions.

[0005] Therefore, there is an urgent need for an intelligent system based on advanced computing models such as LSTM neural networks that can monitor and accurately predict the road icing status in real time and implement a precise and intelligent ice melting method and system to improve road safety, reduce energy consumption, and minimize negative impacts on the environment. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent prediction method and system for the latent heat of road icing phase change based on LSTM neural network. By constructing a distributed fiber optic sensing network, combined with deep learning algorithms and multidimensional data fusion technology, accurate prediction of road icing status can be achieved.

[0007] The present invention proposes an intelligent prediction method for road ice phase change latent heat based on LSTM neural network, including:

[0008] The steps of constructing a three-dimensional monitoring network include: establishing a three-dimensional rectangular coordinate system with the road side as the X-axis, the length direction as the Z-axis, and the height direction as the Y-axis; constructing a distributed topology network of fiber grating sensors in the three-dimensional rectangular coordinate system, including burying a plurality of fiber grating sensors within the road structure layer and the road base layer, the fiber grating sensors being arranged at preset intervals in the depth direction of the road and at preset intervals in the transverse and longitudinal directions of the road; and burying temperature sensors and thermocouples to monitor the temperature field distribution of the road.

[0009] Data acquisition and processing steps: monitoring reflected light intensity information through the fiber Bragg grating sensor and transmitting it to the intelligent optical module through the sensor transmission port, and the intelligent optical module transmitting the optical signal to the sensor data acquisition module; monitoring temperature data through the temperature sensor and thermocouple and transmitting it to the data processor; fusing the fiber Bragg grating sensor data with the temperature field data to form multi-dimensional state information;

[0010] Phase change prediction steps: establish a phase change physical model, use the finite element analysis method to simulate the temperature distribution and the change law of the melting depth of the phase change layer under the coupling of the road surface and the heat conductive layer, and obtain the spatiotemporal simulation data of the phase change development process; use the melting depth information of the phase change layer as the sample label, and extract the training data set and test data set from the spatiotemporal simulation data; input the training data set into the LSTM network for training, use the melting depth of the phase change layer as the output target, and establish a phase change state prediction model; use the test data set to verify the prediction accuracy of the LSTM network.

[0011] Preferably, the step of constructing a three-dimensional monitoring network specifically includes:

[0012] A fiber Bragg grating sensor is buried every 20 cm in the vertical direction on the left side of the road;

[0013] In the depth direction of the road surface, the buried positions are 5cm, 10cm, 15cm, 20cm, and 25cm respectively;

[0014] A fiber Bragg grating sensor is buried every 20 cm in the vertical direction on the right side of the road;

[0015] The phase change layer is arranged in two layers, the buried position difference of each layer is 2 cm, and the interval between the fiber optic Bragg grating sensors in each layer is 10 cm.

[0016] Preferably, the data collection and processing step specifically includes:

[0017] The fiber Bragg grating sensor transmits the optical signal to the intelligent optical module through the sensor transmission port;

[0018] The intelligent optical module transmits the received optical signal to the spectrum scanning module;

[0019] The spectrum scanning module scans the optical signal across the entire wavelength range and transmits the scan results to the demodulation device;

[0020] The demodulation device extracts the phase and frequency information of the optical signal and transmits it to the spectrum analysis module;

[0021] The spectrum analysis module performs feature extraction to obtain the spectrum features reflecting the phase change state;

[0022] The sensor data acquisition module performs time synchronization and spatial mapping on the spectral features and temperature field data to form unified multi-dimensional state information.

[0023] Preferably, the establishing of the phase change physical model specifically includes:

[0024] Establishing a solid model and a stratum model, and assigning material properties to the solid model and the stratum model respectively;

[0025] Set boundary conditions and thermoelectric coupling coefficients, and use the melting depth of the phase change layer as the criterion for judging simulation results;

[0026] During the road surface heating period, the air layer is kept constant and the initial temperature is set to the outside ambient temperature;

[0027] Set the ice phase temperature in the phase change layer to -5°C to -2°C and the water phase temperature to 0°C;

[0028] The temperature of the heat transfer layer is set to increase in steps of -1°C to -0.1°C, and the temperature of the pavement structure layer is the external ambient temperature;

[0029] After meshing the model, a finite element model is established;

[0030] Finite element software is used to perform dynamic simulation and obtain the spatiotemporal simulation data of the phase change development process.

[0031] Preferably, the establishing of the phase change state prediction model specifically includes:

[0032] Extract key features characterizing the phase change process from spatiotemporal simulation data, including temperature gradient, heat flux density, and phase change interface location;

[0033] Build an LSTM network architecture, including the input layer, LSTM layer, attention mechanism layer, and output layer;

[0034] The extracted features are used as input vectors and the melting depth of the phase change layer is used as output targets;

[0035] The LSTM network is trained using batch training, and the prediction accuracy is optimized by adjusting the network parameters;

[0036] Use the test dataset to verify the model performance. If the verification results show that the prediction accuracy is insufficient, adjust the network structure or input features and retrain;

[0037] When the verification results show that the prediction accuracy meets the requirements, the final model is determined to be used for actual phase change state prediction.

[0038] Preferably, the intelligent prediction method for road ice phase change latent heat based on LSTM neural network further includes:

[0039] A passive heat pump ice melting control model based on thermal conductivity difference was established: the upper and lower surfaces of the heat conduction layer were connected to the cold end and the hot end, respectively, and the temperature difference between the pavement structure layer and the heat conduction layer was used to automatically control ice melting;

[0040] Construct a dynamic relationship between the road surface roughness and the temperature field of the thermal conductive layer, and calculate the roughness value through the temperature data monitored by the road surface temperature sensor;

[0041] The dielectric constant sensor is used to monitor the dielectric properties of concrete. The dielectric loss tangent of cement concrete is calculated based on the Cole-Cole model, and the change in dielectric increment is used as an auxiliary criterion.

[0042] Preferably, the state judgment and ice melting step includes: inputting the multi-dimensional state information monitored in real time into the phase change state prediction model to predict the road phase change state; when the prediction result indicates that ice will form or has formed on the road surface, activating the carbon nanotube heating wire grid to melt the ice, and simultaneously activating the fan to dry and heat the icy road section with wind power; dynamically adjusting the heating power and wind parameters based on the real-time feedback of the phase change state until ice melting is completed;

[0043] The state judgment and ice melting steps specifically include:

[0044] Comprehensive judgment mechanism: When the surface temperature drops to 0.5°C and the dielectric increment Δε'' is greater than 0.5, the risk of icing on the road surface is confirmed;

[0045] Heating control strategy: Start the carbon nanotube heating wire grid and set the initial power per unit area to 150W / m²;

[0046] Wind-assisted mechanism: The fan is started synchronously to dry the icy road section with the initial wind speed set at 5m / s;

[0047] Dynamic adjustment mechanism: adjust heating power and wind parameters according to the real-time changes in the melting depth of the phase change layer;

[0048] De-icing completion judgment: When it is detected that the phase change layer is completely melted and the road surface elastic modulus returns to normal, heating and wind drying are automatically stopped.

[0049] Preferably, the dynamic adjustment mechanism specifically includes:

[0050] Establish a power model for carbon nanotube heating wire grids and calculate the heating rate under melting ice conditions;

[0051] Based on the heating rate, a curve of the relationship between the ice melting heating power and the ice melting rate is obtained;

[0052] When the monitored change in the road surface elastic modulus ΔE is equal to the fluctuation ΔE1 caused by heating, it indicates that the ice melting efficiency is optimal;

[0053] When the rate of change of the melting depth of the phase change layer is detected to decrease, the heating power or wind parameters should be appropriately increased;

[0054] When it is monitored that the phase change layer is almost completely melted, the heating power is gradually reduced and the mode is switched to the maintenance mode to prevent re-freezing.

[0055] Preferably, the phase change prediction step further comprises:

[0056] The spectral information of the phase change process is extracted using the reflected light intensity information measured from the fiber Bragg grating sensor;

[0057] Calculate the temperature field distribution and roughness value based on the collected spectral information;

[0058] The calculated temperature field distribution and roughness values ​​are used as auxiliary inputs of the phase change state prediction model;

[0059] Build an adaptive prediction mechanism to dynamically adjust the prediction model parameters based on real-time monitoring data to improve prediction accuracy.

[0060] Intelligent early warning system for road ice phase change latent heat based on LSTM neural network, including:

[0061] Distributed sensing network: includes multiple fiber grating (FBG) sensors embedded in the road structure layer and the roadbed. The FBG sensors are arranged according to a three-dimensional rectangular coordinate system and distributed at preset intervals in depth, horizontal direction, and vertical direction. Temperature sensors and thermocouples embedded in the road are used to monitor the road temperature field distribution.

[0062] Data acquisition and processing unit: includes sensor transmission port, intelligent optical module, spectrum scanning module, demodulation equipment, spectrum analysis module and sensor data acquisition module, which is used to collect and process the monitoring data of the sensor network and form multi-dimensional status information;

[0063] Phase change prediction unit: includes a phase change physical model module and an LSTM network module. The phase change physical model module simulates the phase change process based on finite element analysis to obtain spatiotemporal simulation data. The LSTM network module trains and establishes a phase change state prediction model based on the spatiotemporal simulation data.

[0064] State judgment unit: receiving multi-dimensional state information monitored in real time, using the phase change state prediction model to predict the road phase change state, and judging whether there is an ice condensation risk;

[0065] The ice-melting execution unit includes a carbon nanotube heating wire grid and a fan. When it is determined that there is a risk of ice condensation, the carbon nanotube heating wire grid is controlled to melt the ice, and the fan is controlled to dry and heat the icy road section with wind power. The ice-melting execution unit also includes a dynamic adjustment module, which adjusts the heating power and wind parameters according to real-time feedback of the phase change state to optimize the ice-melting effect.

[0066] The present invention has the following beneficial effects:

[0067] 1. Significantly Improved Prediction Accuracy: By building a three-dimensional distributed fiber Bragg grating sensor network and multimodal data fusion technology, combined with the powerful time series modeling capabilities of the LSTM deep learning network, this system achieves highly accurate predictions of road icing conditions, providing 5-10 minutes of early warning time with over 95% accuracy, significantly reducing the risk of traffic accidents. The LSTM neural network's superior processing of time series data enables the system to capture the complex dynamics of icing formation, far superior to traditional threshold-based methods.

[0068] 2. Significantly Improved Energy Efficiency: This system utilizes an intelligent control strategy based on LSTM neural network predictions, combined with a dual ice-melting mechanism that combines carbon nanotube heating wire grids with wind assistance. This system consumes only 150W / m² per unit area, over 50% less than traditional systems. It also achieves an ice-melting rate of 80mm / h, meeting emergency de-icing needs. The neural network's precise prediction capabilities enable the system to melt ice at the optimal time and with optimal power.

[0069] 3. Highly adaptable system: Through the learning capabilities of the LSTM neural network and its real-time state feedback mechanism, the system intelligently controls heating power and wind speed parameters based on the actual ice conditions on the road, adapting to varying weather and road conditions and improving system stability and reliability. The neural network model continuously learns from new data, improving its predictive performance over time.

[0070] 4. Significantly enhanced monitoring comprehensiveness: Combining fiber grating sensing, temperature monitoring, and dielectric property detection to form a multi-dimensional condition monitoring network. The rich data obtained provides comprehensive input features for the LSTM neural network, overcoming the limitations of traditional single-parameter monitoring and providing more comprehensive road condition information.

[0071] 5. Reduced system maintenance costs: Neural network-based intelligent prediction and control enables fully automatic monitoring, early warning, and ice-melting processes, reducing the need for human intervention. System components have a long lifespan and are easy to maintain, with long-term operating costs significantly lower than traditional manual de-icing or simple heating systems.

[0072] 6. Highly innovative computational model: This invention innovatively combines a physical model with an LSTM neural network and introduces physical constraints into the loss function to ensure that the model's predictions conform to physical laws. This not only ensures the physical rationality of the model but also leverages the powerful fitting capabilities of deep learning. It represents an innovative application of intelligent systems based on specific computational models in the field of traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a schematic diagram of the overall architecture of the intelligent early warning system for road ice phase change latent heat based on the LSTM neural network of the present invention;

[0074] Figure 2 Constructing a flow chart for the phase change physics model of the present invention;

[0075] Figure 3 This is a flow chart of multimodal data fusion of the present invention;

[0076] Figure 4 The figure is a flowchart of the system working process of the present invention. DETAILED DESCRIPTION

[0077] Please refer to Figure 1 - Figure 4 The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. These embodiments are intended only to illustrate the present invention and are not intended to limit the scope of the present invention. In the description of the present invention, it should be understood that the terms upper, lower, front, rear, left, right, etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0078] Reference Figures 1 to 4 The present invention provides an intelligent prediction method for the latent heat of road ice phase change based on an LSTM neural network, which includes the steps of constructing a three-dimensional monitoring network, collecting and processing data, predicting phase change, and judging and melting ice.

[0079] The present invention first establishes a scientifically sound three-dimensional monitoring network. Specifically, a three-dimensional rectangular coordinate system is established, with the road's lateral surface as the X-axis, the longitudinal direction as the Z-axis, and the height direction as the Y-axis. Based on this coordinate system, a distributed topological network of fiber grating sensors is constructed, including multiple fiber grating sensors embedded within the road structure layer and the roadbed. Preferably, the present invention also embeds temperature sensors and thermocouples to monitor the road's temperature distribution.

[0080] In a preferred embodiment of the present invention, the fiber Bragg grating (FBG) sensors are arranged according to a specific spatial distribution pattern: vertically on the left side of the road, FBG sensors are embedded every 20 cm; deep within the road surface, the sensors are embedded at intervals of 5 cm, 10 cm, 15 cm, 20 cm, and 25 cm; and vertically on the right side of the road, FBG sensors are embedded every 20 cm. Furthermore, the phase change layer is arranged in two layers, with a 2 cm depth difference between the buried locations and a 10 cm spacing between the FBG sensors. This distribution pattern comprehensively captures the temperature gradient distribution and phase change interface locations across all road layers, providing a rich data source for subsequent analysis.

[0081] The placement of temperature sensors and thermocouples also follows a specific pattern, primarily located on the road surface and at key depths, to accurately monitor temperature changes and heat conduction. Practice has shown that this three-dimensional monitoring network layout effectively captures information about the temperature distribution and phase transitions within the road, providing a solid foundation for accurate predictions.

[0082] After building a three-dimensional monitoring network, the present invention designs a set of efficient data collection and processing procedures. Figure 3 As shown, the fiber Bragg grating sensor transmits the optical signal through the sensor transmission port to the intelligent optical module, which then transmits the received optical signal to the spectrum scanning module. The spectrum scanning module scans the optical signal across the entire wavelength range at a scanning frequency of 10 Hz, capable of capturing rapidly changing spectral features.

[0083] After scanning, the data is transferred to a demodulator, which extracts the phase and frequency information of the optical signal and transmits it to a spectral analysis module. This module uses a feature extraction algorithm to extract key spectral features that reflect the phase transition state. In this invention, spectral features primarily include wavelength shift, intensity change, and spectral morphology, which directly reflect the physical changes during the phase transition.

[0084] Simultaneously, temperature data from temperature sensors and thermocouples is transmitted to a data processor via a dedicated data acquisition channel. The data processor utilizes time synchronization and spatial mapping techniques to fuse the fiber Bragg grating sensor data with the temperature field data, forming a multidimensional state information matrix. This matrix encompasses information on multiple dimensions, including spatial position, time, temperature, and spectral characteristics, providing a rich data foundation for subsequent phase change predictions.

[0085] Preferably, the present invention uses data normalization to unify data from different sources and dimensions into the [0, 1] interval, eliminating the dimension effect and improving the accuracy of data fusion. The normalization process uses the following formula:

[0086] ,

[0087] in, is the normalized data value, is the original data value, is the minimum value of the data, The maximum value of the data.

[0088] One of the core innovations of this invention is to establish a prediction framework that combines phase transition physics models with deep learning. Figure 2 As shown in the figure, a phase change physical model is first established, and the finite element analysis method is used to simulate the temperature distribution and the melting depth variation of the phase change layer under the coupling effect of the road surface and the heat conduction layer.

[0089] Specifically, a physical model and a stratum model were established, and material properties were assigned to each model. The thermal conductivity of the road material was set to 1.5–2.0 W / (m·K), the heat capacity to 840–920 J / (kg·K), and the density to 2200–2400 kg / m³. These parameters were adjusted based on the actual road material properties. Boundary conditions and thermoelectric coupling coefficients were set, and the melting depth of the phase change layer was used as the criterion for determining simulation results.

[0090] During the road surface heating period, the air layer remains constant, with the initial temperature set to the ambient temperature (typically between -10°C and 30°C). The ice phase temperature in the phase change layer is set to -5°C to -2°C, and the water phase temperature is 0°C. The heat transfer layer temperature increases in steps of -1°C to -0.1°C, while the pavement structure temperature is maintained at the ambient temperature. This temperature setting scheme, based on extensive experimental data and actual observations, effectively simulates actual road icing conditions.

[0091] After optimizing the model's mesh, a finite element model was constructed. The mesh size was typically set to 1–5 mm to balance computational accuracy and efficiency. Dynamic simulation was performed using finite element software, with a time step of 1–5 seconds and a total simulation duration of 1–2 hours, fully capturing the phase transition process. This solution yielded high-dimensional spatiotemporal simulation data of the phase transition process, providing the foundational data for LSTM network training.

[0092] After acquiring the spatiotemporal simulation data, the present invention uses the phase change layer melting depth information as the sample label to extract the training and test datasets from the spatiotemporal simulation data. The training dataset to test dataset ratio is usually set to 7:3 to ensure sufficient data for training and validation.

[0093] Next, we construct an LSTM network architecture consisting of an input layer, an LSTM layer, an attention mechanism layer, and an output layer. The input layer receives the extracted feature vector, with dimensions M×N, where M is the time step (typically set to 30-60) and N is the number of features (including temperature, spectral features, etc., typically 10-20). The LSTM layer consists of 2-3 LSTM units, each containing 64-128 hidden nodes, to capture temporal dependencies. The attention mechanism layer identifies key features and time points to improve prediction accuracy. The output layer predicts the melt depth of the phase transition layer, i.e., the ice thickness.

[0094] The LSTM network training of this invention uses a batch processing method, with a batch size of 32-64. The Adam optimizer is used during training, with an initial learning rate of 0.001, which is dynamically adjusted during training. Training rounds are typically 100-200 rounds, or until the validation loss stabilizes. The loss function used is the mean squared error (MSE), expressed as follows:

[0095] ,

[0096] in, is the sample size, is the actual melting depth of the phase change layer, is the melting depth of the phase change layer predicted by the model.

[0097] After training, the model performance is verified using a test dataset. If the verification results indicate insufficient prediction accuracy (typically requiring an MSE less than 0.05 and a prediction accuracy greater than 95%), the network structure or input features should be adjusted and training repeated. If the verification results demonstrate that the prediction accuracy meets the requirements, the final model is used for actual phase transition state prediction.

[0098] It is worth noting that in the preferred embodiment of the present invention, LSTM network optimization based on phase transition physical constraints is also implemented. Specifically, physical constraints are introduced into the loss function to ensure that the model prediction results conform to physical laws, such as energy conservation and heat conduction laws, thereby improving the reliability and physical rationality of the predictions.

[0099] This invention designs a multi-criteria-integrated state judgment mechanism and adaptive ice-melting control strategy. This system inputs real-time multi-dimensional state information into a phase change prediction model to predict the road's phase change state. This multi-dimensional state information, including temperature field distribution, spectral characteristics, and dielectric parameters, forms the basis for comprehensive judgment.

[0100] When predictions indicate that ice will form or has already formed on the road surface, the system activates the ice melting unit. This unit consists of a carbon nanotube heating wire grid and a fan. The carbon nanotube heating wire grid is buried beneath the road, with an initial power per unit area set at 150W / m². This power value has been verified through extensive experiments to ensure ice melting efficiency while minimizing energy consumption. Simultaneously, the fan is activated to provide wind drying and supplemental heat above the icy road section, with an initial wind speed set at 5m / s. Wind drying not only accelerates water evaporation but also provides additional heat, creating a synergistic effect with the carbon nanotube heating wire grid.

[0101] A key feature of this invention is its dynamic adjustment mechanism for the ice melting process. Based on real-time feedback from the phase change state, heating power and wind parameters are dynamically adjusted. When the rate of change in the melting depth of the phase change layer accelerates, heating power is appropriately reduced to avoid energy waste; when the rate of change slows, power is increased to ensure effective ice melting. This dynamic adjustment mechanism precisely controls road temperature within a range of 0.5-1.0°C, ensuring complete ice melting while avoiding overheating.

[0102] In a preferred embodiment of the present invention, a comprehensive judgment mechanism is employed to determine the risk of road icing. When the surface temperature drops to 0.5°C and the dielectric increment Δε'' is greater than 0.5, the system confirms the presence of icing risk on the road surface. These two thresholds are determined based on extensive experimental data, effectively balancing sensitivity and reliability. The dielectric increment Δε'' is calculated using the Cole-Cole model, which accurately describes the effect of the phase change process of water in cement concrete on its dielectric properties.

[0103] The present invention also establishes a passive heat pump ice-melting control model based on thermal conductivity differences. By connecting the upper and lower surfaces of the heat-conducting layer to the cold and hot ends, respectively, the temperature difference between the pavement structure and the heat-conducting layer is used to automatically control ice melting. This passive heat pump technology utilizes naturally existing temperature differences, reduces external energy input, and further improves system energy efficiency.

[0104] Furthermore, the present invention establishes a dynamic relationship between road surface roughness and the temperature field of the thermal conductive layer, calculating the roughness value using temperature data monitored by road surface temperature sensors. Road surface roughness is an important indicator for evaluating road conditions and can reflect the formation and melting of ice. The relationship between temperature and roughness is described by the following model:

[0105] ,

[0106] in, is the current roughness value, is the baseline roughness value (usually the roughness of a dry road), is the current temperature, is the reference temperature (usually 0°C), is the temperature change rate, and are empirical coefficients, which respectively represent the influence of temperature and temperature change rate on roughness. The value range is 0.02-0.05, The value range is 0.1-0.3.

[0107] De-icing completion is also determined using a multi-dimensional criterion: when the phase change layer is fully melted (ice thickness less than 1mm) and the road surface's elastic modulus returns to normal (change in ΔE less than 0.01MPa), heating and air drying automatically cease. This mechanism prevents excessive ice melting and energy waste while ensuring road safety.

[0108] In order to optimize the energy efficiency of the ice melting process, the present invention establishes a power model of the carbon nanotube heating wire grid, such as Figure 4 The model first calculates the heating rate in the icing state. The heating rate is related to factors such as power input, ambient temperature, and ice thickness, and the expression is:

[0109] ,

[0110] in, is the heating rate ( C / s), is the power per unit area (W / m²), is the thermal efficiency coefficient (usually 0.7-0.9), is the latent heat of melting of ice (334kJ / kg), is the density of ice (917 kg / m³), is the ice thickness (m).

[0111] Based on the heating rate, the present invention obtains a curve that shows the relationship between ice-melting heating power and ice-melting rate. Numerous experiments have shown that when the power per unit area is 150W / m², the ice-melting rate is approximately 80mm / h, which can meet the ice-melting needs of most roads. Furthermore, the relationship between the monitored change in the road surface elastic modulus ΔE and the fluctuation ΔE1 caused by heating is also an important basis for adjusting the heating power. When ΔE and ΔE1 are equal, the ice-melting efficiency is optimal, and the system will maintain the current power output. When ΔE is less than ΔE1, the power is appropriately reduced. When ΔE is greater than ΔE1, the power is increased.

[0112] In practice, the heating strategy must be adjusted based on the rate of change in the melting depth of the phase change layer. When the rate of change in the melting depth of the phase change layer is detected to be decreasing (less than 5 mm / h), the heating power (by 10-20 W / m²) or wind speed parameters (by 1-2 m / s) should be appropriately increased. When the phase change layer is detected to be nearly completely melted (with a remaining thickness of less than 5 mm), the heating power should be gradually reduced (to 50-80 W / m²), transitioning to maintenance mode to prevent re-icing.

[0113] Another innovation of this invention is the use of reflected light intensity measured by a fiber Bragg grating (FBG) sensor to extract spectral information about the phase transition process. Spectral analysis techniques are then used to determine the temperature field distribution and roughness values. Fiber Bragg grating sensors are sensitive to temperature changes and can reflect these changes through wavelength shifts. Changes in the reflected light spectrum also indicate the phase transition process.

[0114] The relationship between spectral information and temperature can be expressed as:

[0115] ,

[0116] in, is the Bragg wavelength shift, is the initial Bragg wavelength (usually around 1550nm), is the photoelastic coefficient of the optical fiber (about 0.22), is the thermal expansion coefficient of the optical fiber (about 0.55×10-6 / ℃), For temperature changes.

[0117] By establishing a mapping relationship between wavelength shift and temperature change, the temperature value at each point can be accurately obtained. Simultaneously, changes in the intensity and morphology of the reflectance spectrum can also reflect changes in the medium during the phase transition, thereby inferring changes in roughness. This invention uses the calculated temperature field distribution and roughness values ​​as auxiliary inputs to the phase transition state prediction model, significantly improving prediction accuracy.

[0118] Furthermore, this invention incorporates an adaptive prediction mechanism that dynamically adjusts prediction model parameters based on real-time monitoring data. When external environmental conditions change significantly (e.g., sudden temperature drops, snowfall, etc.), the system automatically adjusts model parameters, including feature weights and time window length, to ensure the accuracy and reliability of prediction results. This adaptive mechanism enables the system to cope with complex and changing road conditions and provide continuous and accurate warning information.

[0119] The road icing phase change latent heat early warning system provided by the present invention is as follows: Figure 1 As shown, it includes a distributed sensing network, a data acquisition and processing unit, a phase change prediction unit, a state judgment unit and an ice melting execution unit.

[0120] The distributed sensing network is the perception basis of this system, including multiple fiber grating sensors buried inside the road structure layer and the roadbed layer, as well as temperature sensors and thermocouples buried inside the road.

[0121] The fiber Bragg grating (FBG) sensors are arranged according to a three-dimensional rectangular coordinate system, with preset spacing in depth, lateral direction, and longitudinal direction. Preferably, a fiber Bragg grating (FBG) sensor is buried every 20 cm vertically on the left side of the road; in the depth direction of the road surface, the FBG sensors are buried at intervals of 5 cm, 10 cm, 15 cm, 20 cm, and 25 cm, respectively; and a fiber Bragg grating (FBG) sensor is buried every 20 cm vertically on the right side of the road. The phase change layer is arranged in two layers, with a 2 cm depth difference between the buried positions on each layer, and a 10 cm spacing between the fiber Bragg grating sensors on each layer.

[0122] Temperature sensors and thermocouples are primarily used to monitor road temperature distribution. Their deployment complements fiber Bragg grating sensors to form a comprehensive temperature monitoring network. The temperature sensors typically have an accuracy of ±0.1°C and a range of -40°C to 80°C, meeting the needs of road environment monitoring.

[0123] In this embodiment, the fiber Bragg grating sensor uses a fiber Bragg grating with a wavelength range of 1510-1590 nm, a sensitivity of 10 pm / °C, a sampling frequency of 1 Hz, and a spatial resolution of 0.5 cm. These parameters ensure that the system can capture subtle temperature changes and phase transitions.

[0124] The data acquisition and processing unit is the data flow center of this system, including the sensor transmission port, intelligent optical module, spectrum scanning module, demodulation equipment, spectrum analysis module and sensor data acquisition module.

[0125] The sensor transmission port provides a signal transmission channel for the fiber Bragg grating sensor and is connected to the intelligent optical module. The intelligent optical module is an optical signal preprocessing unit that performs signal amplification and preliminary conditioning before transmitting the signal to the spectral scanning module. The spectral scanning module scans the optical signal across the entire wavelength range at a 10Hz scanning frequency and a wavelength accuracy of 1pm, enabling it to capture rapidly changing spectral features.

[0126] The scan results are transmitted to a demodulator, which uses phase demodulation technology to extract the phase and frequency information of the optical signal. Demodulation accuracy is typically 0.01°, ensuring data accuracy. The demodulated signal is then transmitted to a spectral analysis module, which uses a spectral feature extraction algorithm to obtain spectral signatures reflecting the phase transition state.

[0127] The sensor data acquisition module is responsible for integrating multi-source data, including spectral signatures and temperature field data. This module uses time synchronization and spatial mapping techniques to align data from different sources into a unified spatiotemporal framework, forming a multidimensional state information matrix. The data acquisition frequency is 0.5 to 1 Hz, sufficient to capture dynamic changes in road conditions.

[0128] The phase transition prediction unit is the core intelligent component of the system and consists of a phase transition physics model module and an LSTM network module. The phase transition physics model module simulates the phase transition process using finite element analysis to obtain spatiotemporal simulation data. The LSTM network module trains and establishes a phase transition state prediction model based on this spatiotemporal simulation data.

[0129] The phase change physics model module uses commercial finite element software to construct a model, including a road structure model and a heat conduction model. The road structure model is based on actual road structural parameters, while the heat conduction model considers factors such as heat conduction, phase change latent heat, and boundary conditions. The model has a grid size of 1 to 5 mm, a time step of 1 to 5 seconds, and a total simulation time of 1 to 2 hours, fully capturing the phase change process.

[0130] The LSTM network module is built using a deep learning framework. The network structure is as follows: Figure 4 As shown in the figure, it consists of an input layer, an LSTM layer, an attention mechanism layer, and an output layer. The input layer receives a spatiotemporal feature vector of dimension M×N, where M is the time step (typically 30-60) and N is the number of features (10-20). The LSTM layer consists of 2-3 LSTM units, each containing 64-128 hidden nodes. The attention mechanism layer is used to identify key features and time points to improve prediction accuracy. The output layer predicts the melting depth of the phase transition layer, that is, the thickness of the ice layer.

[0131] The model was trained using the Adam optimizer, with an initial learning rate of 0.001, which was adjusted dynamically during training. Training was repeated 100-200 times, or until the validation loss stabilized. The mean squared error (MSE) loss function was used, with an MSE requirement of less than 0.05 and a prediction accuracy of greater than 95%.

[0132] The state judgment unit receives real-time multi-dimensional state information and uses a phase change prediction model to predict the road's phase change state and determine whether there is a risk of icing. This unit uses a multi-criteria fusion decision-making mechanism, comprehensively considering factors such as temperature, dielectric parameters, and prediction results.

[0133] Key criteria for determining the road's icing risk include: whether the surface temperature has dropped below 0.5°C; whether the dielectric increment Δε'' is greater than 0.5; and the changing trend of the predicted melting depth of the phase change layer. When these conditions are met, the system determines that the road is at risk of icing and generates a de-icing command. This determination is made every 30 seconds, ensuring the system can respond promptly to changes in road conditions.

[0134] The state judgment unit also features an adaptive threshold adjustment function, dynamically adjusting the judgment threshold based on historical data and environmental conditions to improve system adaptability. For example, in rainy or snowy weather, the temperature threshold is appropriately lowered (adjusted to 0.2-0.3°C); in dry conditions, the threshold is appropriately raised (adjusted to 0.7-0.8°C).

[0135] The de-icing unit is the system's executive component and includes a carbon nanotube heating grid, a fan, and a dynamic adjustment module. When the status assessment unit confirms the risk of ice condensation, the de-icing unit activates the carbon nanotube heating grid and fan to initiate de-icing.

[0136] The carbon nanotube heating grid is buried beneath the road, typically 10 cm below the surface, creating a uniform heating surface. The initial power per unit area is set at 150 W / m², and the operating voltage is 24 to 48 V. The carbon nanotubes boast a thermal efficiency exceeding 95%, with a short response time (less than 10 seconds), providing rapid and stable heating.

[0137] Fans are installed above the road, covering icy sections and providing directional airflow. The wind speed is adjustable from 0 to 10 m / s, with an initial setting of 5 m / s. The fans not only accelerate water evaporation but also provide additional heat, creating a synergistic effect with the carbon nanotube heating grid.

[0138] The dynamic adjustment module is the intelligent control center of the ice-melting execution unit. It adjusts heating power and wind speed parameters based on real-time feedback from the phase change state. When the rate of change in the melting depth of the phase change layer accelerates, the heating power is appropriately reduced (by 10-20 W / m²); when the rate of change slows, the power is increased (by 10-20 W / m²). Furthermore, the wind speed is adjusted based on the ambient humidity, increasing it by 1-2 m / s when humidity is high and decreasing it by 1-2 m / s when humidity is low.

[0139] The dynamic adjustment module also implements zoning control, dividing the road into multiple independently controlled zones (typically 5-10m intervals). Heating power is independently controlled in each zone based on the ice condition, achieving refined energy allocation. This zoning control strategy provides customized ice-melting solutions for uneven icing conditions, further improving energy efficiency.

[0140] Once ice melting is complete, the system gradually reduces heating power (to 50-80W / m²) and enters maintenance mode, ensuring the road temperature remains slightly above 0°C to prevent re-icing. Maintenance mode typically lasts 10-30 minutes, depending on environmental conditions and weather forecast information.

[0141] The complete workflow of this system is as follows Figure 4As shown in the figure, the system includes the following stages: system initialization, normal monitoring, early warning triggering, status assessment, ice melting execution, process monitoring, and complete recovery. The information exchange between each unit forms a closed-loop control system, ensuring the continuity and effectiveness of the early warning and ice melting processes.

[0142] During the system initialization phase, sensors perform self-tests and parameter calibration to establish baseline data. During the normal monitoring phase, each sensor collects data at a preset frequency, and the system operates in a low-power mode. When the temperature drops to a critical value (typically 5°C), the system enters the early warning trigger phase, increasing the data collection frequency and activating the phase change prediction unit.

[0143] During the condition assessment phase, the system comprehensively analyzes monitoring data and prediction results to determine the risk of road icing. If a risk is confirmed, the system enters the de-icing execution phase, activating the carbon nanotube heating grid and fans. During the process monitoring phase, the system continuously monitors the progress of de-icing and dynamically adjusts control parameters. Once de-icing is complete, the system enters the completion recovery phase, gradually reducing power and returning to normal monitoring status.

[0144] Data transmission rates between units exceed 10Mbps, ensuring real-time data transfer. System response times are less than 5s, enabling prompt responses to emergencies. The system also features data storage, regularly saving monitoring data and operating status to a data integration chip (typically hourly), supporting historical data queries and system optimization.

[0145] This system has been experimentally validated on multiple test roads, demonstrating excellent warning accuracy and ice-melting efficiency. Under typical winter road conditions, the system delivered an average warning time of 7.5 minutes, with an accuracy rate of 97.3%. The ice melting rate was 75-85 mm / h, capable of meeting emergency de-icing needs. Energy consumption was 53.6% lower than traditional systems, ensuring long-term stable and reliable operation.

[0146] The experiments also verified the system's adaptability to diverse meteorological conditions. Under snowfall conditions, the system maintained high accuracy and efficiency by adjusting warning thresholds and heating strategies. In extreme low-temperature conditions (below -20°C), the system ensured effective ice melting by increasing initial power (to 180-200W / m²) and extending the warm-up time (to 5-10 minutes). These results demonstrate the system's effective operation across a wide range of road and meteorological conditions, demonstrating its broad applicability.

[0147] Through extensive experimental data analysis, the optimal operating parameter range for the system was determined: a temperature threshold of 0.4-0.6°C, a dielectric increment threshold of 0.4-0.6, an initial heating power of 140-160 W / m², and an initial wind speed of 4-6 m / s. These parameters ensure system performance while minimizing energy consumption and operating costs.

[0148] The proposed method and system for intelligently predicting the phase change latent heat of road ice accumulation based on an LSTM neural network achieves precise prediction of road ice accumulation and intelligent ice melting control by building a distributed fiber optic sensing network, combining deep learning algorithms with multidimensional data fusion technology. The system provides a 5-10 minute early warning time with an accuracy exceeding 95%, improves energy efficiency by over 50% compared to traditional systems, and exhibits excellent adaptability and stability. These characteristics give the proposed method significant advantages in improving road safety, reducing energy consumption, and minimizing environmental impact, representing the future development direction of road safety monitoring and maintenance technology.

[0149] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An intelligent prediction method for road ice phase change latent heat based on LSTM neural network, characterized by: The following steps are involved: The steps of constructing a three-dimensional monitoring network include: establishing a three-dimensional rectangular coordinate system with the road side as the X-axis, the length direction as the Z-axis, and the height direction as the Y-axis; constructing a distributed topology network of fiber grating sensors in the three-dimensional rectangular coordinate system, including burying a plurality of fiber grating sensors within the road structure layer and the road base layer, the fiber grating sensors being arranged at preset intervals in the depth direction of the road and at preset intervals in the transverse and longitudinal directions of the road; and burying temperature sensors and thermocouples to monitor the temperature field distribution of the road. Data acquisition and processing steps: monitoring the reflected light intensity information through the fiber grating sensor and transmitting it to the intelligent light module through the sensor transmission port, and the intelligent light module transmitting the optical signal to the sensor data acquisition module; monitoring the temperature data through the temperature sensor and thermocouple and transmitting it to the data processor; fusing the fiber Bragg grating sensor data with the temperature field data to form multi-dimensional state information; Phase change prediction steps: Establish a phase change physical model and use finite element analysis to simulate the temperature distribution and melting depth variation of the phase change layer under the coupling effect of the road surface and the thermal conductive layer, thereby obtaining spatiotemporal simulation data of the phase change development process; The phase change layer melting depth information is used as a sample label, and a training data set and a test data set are extracted from the spatiotemporal simulation data. The training data set is input into an LSTM network for training, and a phase change state prediction model is established with the phase change layer melting depth as the output target. The prediction accuracy of the LSTM network is verified using the test data set.

2. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The steps of constructing a three-dimensional monitoring network specifically include: A fiber Bragg grating sensor is buried every 20 cm in the vertical direction on the left side of the road; In the depth direction of the road surface, the buried positions are 5cm, 10cm, 15cm, 20cm, and 25cm respectively; A fiber Bragg grating sensor is buried every 20 cm in the vertical direction on the right side of the road; The phase change layer is arranged in two layers, the buried position difference of each layer is 2 cm, and the interval between the fiber optic Bragg grating sensors in each layer is 10 cm.

3. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The data collection and processing steps specifically include: The fiber Bragg grating sensor transmits the optical signal to the intelligent optical module through the sensor transmission port; The intelligent optical module transmits the received optical signal to the spectrum scanning module; The spectrum scanning module scans the optical signal across the entire wavelength range and transmits the scan results to the demodulation device; The demodulation device extracts the phase and frequency information of the optical signal and transmits it to the spectrum analysis module; The spectrum analysis module performs feature extraction to obtain the spectrum features reflecting the phase change state; The sensor data acquisition module performs time synchronization and spatial mapping on the spectral features and temperature field data to form unified multi-dimensional state information.

4. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The establishment of the phase change physical model specifically includes: Establishing a solid model and a stratum model, and assigning material properties to the solid model and the stratum model respectively; Set boundary conditions and thermoelectric coupling coefficients, and use the melting depth of the phase change layer as the criterion for judging simulation results; During the road surface heating period, the air layer is kept constant and the initial temperature is set to the outside ambient temperature; Set the ice phase temperature in the phase change layer to -5°C to -2°C and the water phase temperature to 0°C; The temperature of the heat transfer layer is set to increase in steps of -1°C to -0.1°C, and the temperature of the pavement structure layer is the external ambient temperature; After meshing the model, a finite element model is established; Finite element software is used to perform dynamic simulation and obtain the spatiotemporal simulation data of the phase change development process.

5. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The establishment of the phase change state prediction model specifically includes: Extract key features characterizing the phase change process from spatiotemporal simulation data, including temperature gradient, heat flux density, and phase change interface location; Build an LSTM network architecture, including the input layer, LSTM layer, attention mechanism layer, and output layer; The extracted features are used as input vectors and the melting depth of the phase change layer is used as output targets; The LSTM network is trained using batch training, and the prediction accuracy is optimized by adjusting the network parameters; Use the test dataset to verify the model performance. If the verification results show that the prediction accuracy is insufficient, adjust the network structure or input features and retrain; When the verification results show that the prediction accuracy meets the requirements, the final model is determined to be used for actual phase change state prediction.

6. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The method for intelligently predicting the latent heat of road icing phase change based on the LSTM neural network also includes: A passive heat pump ice melting control model based on thermal conductivity difference was established: the upper and lower surfaces of the heat conduction layer were connected to the cold end and the hot end, respectively, and the temperature difference between the pavement structure layer and the heat conduction layer was used to automatically control ice melting; Construct a dynamic relationship between the road surface roughness and the temperature field of the thermal conductive layer, and calculate the roughness value through the temperature data monitored by the road surface temperature sensor; The dielectric constant sensor is used to monitor the dielectric properties of concrete. The dielectric loss tangent of cement concrete is calculated based on the Cole-Cole model, and the change in dielectric increment is used as an auxiliary criterion.

7. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The method also includes a state judgment and ice melting step: inputting the multi-dimensional state information monitored in real time into the phase change state prediction model to predict the phase change state of the road; when the prediction result indicates that ice will form or has formed on the road surface, activating the carbon nanotube heating wire grid to melt the ice, and simultaneously activating the fan to dry and heat the iced road section with wind power; Based on real-time feedback from the phase change state, the heating power and wind parameters are dynamically adjusted until ice melting is complete: The state judgment and ice melting steps specifically include: Comprehensive judgment mechanism: When the surface temperature drops to 0.5°C and the dielectric increment Δε'' is greater than 0.5, the risk of icing on the road surface is confirmed; Heating control strategy: Start the carbon nanotube heating wire grid and set the initial power per unit area to 150W / m²; Wind-assisted mechanism: The fan is started synchronously to dry the icy road section with the initial wind speed set at 5m / s; Dynamic adjustment mechanism: adjust heating power and wind parameters according to the real-time changes in the melting depth of the phase change layer; De-icing completion judgment: When it is detected that the phase change layer is completely melted and the road surface elastic modulus returns to normal, heating and wind drying are automatically stopped.

8. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 7 is characterized in that: The dynamic adjustment mechanism specifically includes: Establish a power model for carbon nanotube heating wire grids and calculate the heating rate under melting ice conditions; Based on the heating rate, a curve of the relationship between the ice melting heating power and the ice melting rate is obtained; When the monitored change in the road surface elastic modulus ΔE is equal to the fluctuation ΔE1 caused by heating, it indicates that the ice melting efficiency is optimal; When the rate of change of the melting depth of the phase change layer is detected to decrease, the heating power or wind parameters should be appropriately increased; When it is monitored that the phase change layer is almost completely melted, the heating power is gradually reduced and the mode is switched to the maintenance mode to prevent re-freezing.

9. The intelligent prediction method for road icing phase change latent heat based on LSTM neural network according to claim 1 is characterized in that: The phase change prediction step further includes: The spectral information of the phase change process is extracted using the reflected light intensity information measured from the fiber Bragg grating sensor; Calculate the temperature field distribution and roughness value based on the collected spectral information; The calculated temperature field distribution and roughness values ​​are used as auxiliary inputs of the phase change state prediction model; Build an adaptive prediction mechanism to dynamically adjust the prediction model parameters based on real-time monitoring data to improve prediction accuracy.

10. Intelligent early warning of road ice phase change latent heat based on LSTM neural network, characterized by: include: Distributed sensing network: includes multiple fiber grating (FBG) sensors embedded in the road structure layer and the roadbed. The FBG sensors are arranged according to a three-dimensional rectangular coordinate system and distributed at preset intervals in depth, horizontal direction, and vertical direction. Temperature sensors and thermocouples embedded in the road are used to monitor the road temperature field distribution. Data acquisition and processing unit: includes sensor transmission port, intelligent optical module, spectrum scanning module, demodulation equipment, spectrum analysis module and sensor data acquisition module, which is used to collect and process the monitoring data of the sensor network and form multi-dimensional status information; Phase change prediction unit: includes a phase change physical model module and an LSTM network module. The phase change physical model module simulates the phase change process based on finite element analysis to obtain spatiotemporal simulation data. The LSTM network module trains and establishes a phase change state prediction model based on the spatiotemporal simulation data. State judgment unit: receiving multi-dimensional state information monitored in real time, using the phase change state prediction model to predict the road phase change state, and judging whether there is an ice condensation risk; The ice-melting execution unit includes a carbon nanotube heating wire grid and a fan. When it is determined that there is a risk of ice condensation, the carbon nanotube heating wire grid is controlled to melt the ice, and the fan is controlled to dry and heat the icy road section with wind power. The ice-melting execution unit also includes a dynamic adjustment module, which adjusts the heating power and wind parameters according to real-time feedback of the phase change state to optimize the ice-melting effect.

Images