Road ice melting implementation system and method

Abstract

The invention relates to the technical field of road ice melting, and discloses a road ice melting implementation system and method. The system comprises a meteorological monitoring platform, a snow-melting agent spraying platform and a management and control platform, the method comprises the following steps: firstly, collecting meteorological data and monitoring a road surface state to obtain an initial road ice melting data set, and then carrying out anomaly detection and filling missing data; establishing a road ice melting prediction model based on the neural network, predicting whether the road is iced or not, and outputting a road icing result; then ice melting work is carried out, an enhanced hawk optimization algorithm is introduced to optimize spraying parameters in the ice melting work, and a road ice melting implementation strategy is generated; and finally, adjusting a road ice melting implementation strategy, and establishing a snow melting environment coupling model and an alarm mechanism. By analyzing and processing the road ice melting data, the purpose of implementing road ice melting is achieved, and the method is objective and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of road ice melting, and in particular to a road ice melting implementation system and method. Background Art

[0002] Snow and ice on winter roads pose a global threat to traffic safety and efficiency. Statistics show that the number of traffic accidents caused by icy roads increases by 30%-50% compared to normal weather conditions, potentially leading to regional traffic jams and significant economic losses. In recent years, with the frequent occurrence of extreme weather, traditional passive de-icing methods have become unable to meet the demands of modern transportation networks for efficient, real-time, and sustainable ice melting. While new technologies such as carbon nanotube heating and conductive concrete are emerging, their high cost, complex construction, and lack of technological maturity limit their practical application. There is an urgent need to explore innovative ice-melting solutions that balance environmental friendliness, cost-effectiveness, and reliability.

[0003] Currently, traditional road ice melting methods can be divided into three categories: the first is mechanical de-icing, which uses snowplows, de-icing rollers and other equipment to physically remove ice and snow; the second is chemical de-icing, which mainly involves spreading chloride salt de-icing agents (such as sodium chloride and calcium chloride) and using the freezing point depression effect to accelerate the melting of ice and snow; the third is thermal de-icing, such as laying electric heating cables, ground source heat pump circulation systems or electrically heated asphalt roads, to increase road temperature through external energy input.

[0004] Traditional road ice melting methods generally rely on repeated mechanical de-icing and timed spraying of snow-melting agents. They lack intelligent control capabilities and are unable to dynamically adjust ice melting strategies based on meteorological conditions, slippery conditions of ice and snow on the road surface, etc., often resulting in energy waste and incomplete ice melting. Summary of the Invention

[0005] In response to the problems in the related art, the present invention provides a road ice melting implementation system and method to overcome the technical problems existing in the existing related art.

[0006] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a road de-icing implementation system, specifically comprising: meteorological monitoring, de-icing agent spraying and control platform; Meteorological monitoring, including a meteorological environment monitoring module and a road condition monitoring module, is used to collect meteorological data and monitor road conditions to obtain an initial road ice melting data set. Anomaly detection is performed on the initial road ice melting data set using an adaptive window-based data detection method, and missing data is filled to generate a processed road ice melting data set. Snowmelt spraying, including snowmelt pumping stations, snowmelt spraying facilities and snowmelt auxiliary equipment; A management and control platform for ice and snow monitoring and early warning, equipment condition monitoring, and solution spraying control; The ice and snow monitoring and early warning system includes establishing a road ice melting prediction model, predicting whether the road is icy based on the processed road ice melting data set, outputting the road icing result, and segmenting the road to obtain a set of segmented ice melting sections; The equipment operating condition monitoring includes monitoring the operation process of spraying the snow melting agent; The solution spraying control includes performing ice-melting work on ice-melting sections in a set of segmented ice-melting sections, introducing an enhanced Sky Eagle optimization algorithm to optimize the spraying parameters in the ice-melting work, generating a road ice-melting implementation strategy, adjusting the road ice-melting implementation strategy according to real-time meteorological data and the use of snow-melting agent materials, and establishing a snow-melting environment coupling model and an alarm mechanism.

[0007] Preferably, collecting meteorological data and monitoring road conditions to obtain an initial road ice melting data set includes: Meteorological data is collected to obtain a meteorological data set, road surface conditions are monitored to obtain a road surface condition data set, and road ice melting time series are recorded to obtain an initial road ice melting data set.

[0008] Preferably, the method of performing anomaly detection on the initial road ice melting data set using the adaptive window-based data detection method includes: Set a sliding window, dynamically and adaptively adjust the sliding window to generate an adaptive window, calculate the anomaly score of the road ice melting data in the adaptive window, and identify the abnormal data; Count the number of abnormal data in the current adaptive window, then calculate the ratio of the number of abnormal data to the current adaptive window size, and calculate the next adaptive window size; The current adaptive window size is updated according to the next adaptive window size, and the anomaly score of the road ice melting data in the next adaptive window is calculated until the initial road ice melting data set is traversed, all anomaly data are deleted, and the processed road ice melting data set is obtained.

[0009] Preferably, filling missing data includes: When the missing data is the first or last road ice melting data in the adaptive window, the mean of the road ice melting data in the adaptive window is used to fill the missing data; otherwise, piecewise linear interpolation is used to fill the missing data to generate a processed road ice melting data set.

[0010] Preferably, the establishing of a road ice melting prediction model, predicting whether a road is icy based on a processed road ice melting data set, and outputting a road icing result includes: Obtaining a current road ice melting data set from the processed road ice melting data set, then obtaining a road ice melting data sample set, setting a window step, dividing the data according to the window step, and performing standardization processing to obtain a plurality of road ice melting data sample subsets; The road ice melting prediction model is set to include a neural network model and a support vector machine. The neural network model adopts an encoder-decoder structure. The encoder includes two LSTM layers, the decoder includes one LSTM layer and a fully connected layer, and the activation function is the Tanh function. Dividing the road ice melting data sample subset into a sample training set and a sample test set, inputting the sets into a neural network model for training, outputting prediction results, and obtaining a final road ice melting prediction model; Setting a road icing rule, marking the road ice melting data that meets the road icing rule in the prediction result as 1, otherwise marking it as 0; The support vector machine is set to use a radial basis kernel function, the prediction results are divided according to the window step size, and normalized, and input into the support vector machine for training. The maximum number of training rounds is set. When the maximum number of training rounds is reached, the training is stopped to obtain the final support vector machine; The current road ice melting data set is divided according to the window step size and standardized, and then input into the final road ice melting prediction model to output the road ice melting data prediction value. The road ice melting data prediction value is marked according to the road icing rules and input into the final support vector machine. The output 1 indicates that the road is iced, and the output 0 indicates that the road is not iced, thus obtaining the road icing result.

[0011] Preferably, the segmenting of the road comprises: The road is segmented according to the road icing result, and the road sections corresponding to the road icing are found and marked as ice-melting sections. The road sections corresponding to the road not icing are found and marked as ice-melting sections, thereby obtaining a segmented ice-melting section set.

[0012] Preferably, the introduction of the enhanced Sky Eagle optimization algorithm to optimize the spraying parameters in the ice melting operation includes: Selecting an ice-melting section from the set of segmented ice-melting sections for ice-melting operation, controlling spraying parameters during the ice-melting operation, wherein the spraying parameters include a pipeline pressure of an ice-melting solution spraying device, an ice-melting agent concentration, and a spraying volume per unit area; setting a pipeline pressure range, an ice-melting agent concentration range, and a minimum spraying coverage rate, spraying the ice-melting agent solution, and then recording energy consumption of the ice-melting solution spraying device, ice melting time of the ice-melting section, and coverage uniformity of the ice-melting agent solution; Establish an objective function based on minimum energy consumption and maximum ice melting efficiency; The Skyhawk optimization algorithm is improved by integrating the hill climbing algorithm and the Harris hawk hunting behavior to obtain an enhanced Skyhawk optimization algorithm; the objective function is used as the fitness function, a search space is set, a Skyhawk population exists in the search space, the Skyhawk position in the Skyhawk population represents a set of spraying parameters, the Skyhawk position iteration process is regarded as a spraying parameter optimization process, and the optimal fitness function value is used to simulate the optimal objective function value; Introduce the hill climbing algorithm to update the position of the Sky Eagle; The Sky Eagle population has entered the high-altitude hunting and gliding hunting stages, and Levi's flight simulation Sky Eagle hunting has been introduced to update the Sky Eagle's position; The Harris hawk hunting behavior is used to replace the low-flying hunting and gliding hunting stages of the hawk population. The hawk position is updated again until the current number of iterations reaches the maximum number of iterations. The iteration is stopped to obtain the final hawk population. The hawk position corresponding to the best fitness function value in the final hawk population is found to obtain the optimized spraying parameters.

[0013] Preferably, the generating of the road ice melting implementation strategy includes: The optimized spraying parameters include the pipeline pressure, deicing agent concentration and spraying volume per unit area of the optimized deicing agent solution spraying equipment. An deicing section in the set of segmented deicing sections is selected, and the deicing agent solution spraying equipment is driven by the optimized spraying parameters to perform deicing work, thereby obtaining a road deicing implementation strategy.

[0014] Preferably, adjusting the road de-icing implementation strategy based on real-time meteorological data and de-icing material usage, and establishing a de-icing environment coupling model and an alarm mechanism include: Collect real-time meteorological data, set a change threshold and a thickness threshold, and when the change rate of the real-time meteorological data is greater than the change threshold, find the de-icing section corresponding to the real-time meteorological data and measure the ice thickness. When the ice thickness is greater than the ice threshold, adjust the de-icing strategy for the road and give priority to de-icing the corresponding de-icing section. Monitor the use of snow-melting agent materials, then establish a snow-melting environment coupling model to calculate the remaining amount in the storage tank; set the remaining amount threshold and the rated threshold. When the remaining amount in the storage tank is less than the remaining amount threshold, replenish the snow-melting agent solution in time. When the remaining amount in the storage tank is greater than the rated threshold, trigger the alarm mechanism and complete the road ice melting implementation.

[0015] The present invention also discloses a method for implementing road ice melting, which specifically includes: S1. Collect meteorological data and monitor road conditions to obtain an initial road ice melting data set, perform anomaly detection on the initial road ice melting data set using an adaptive window-based data detection method, and fill in missing data to generate a processed road ice melting data set; S2. Establishing a road ice melting prediction model based on a neural network, predicting whether the road is icy based on the processed road ice melting data set, outputting a road icing result, and segmenting the road to obtain a set of segmented ice melting road sections; S3. Performing ice-melting operations on the ice-melting sections in the set of segmented ice-melting sections, optimizing spraying parameters during the ice-melting operations using an enhanced Sky Eagle optimization algorithm, and generating a road ice-melting implementation strategy; S4. Adjust the road de-icing implementation strategy based on real-time meteorological data and the use of de-icing agent materials, establish a de-icing environment coupling model and an alarm mechanism, and complete the road de-icing implementation.

[0016] The present invention has the following beneficial effects: 1. This invention collects meteorological data and monitors road conditions, uses an adaptive window-based data detection method to detect anomalies and fill in missing data, and dynamically adjusts the window size. When the data anomaly ratio is high, the window is narrowed to improve detection sensitivity. When the data is relatively normal, the window is expanded to reduce computing overhead, avoiding resource waste caused by frequent adjustments. It strikes a balance between detection accuracy and computing efficiency, is suitable for anomaly cleaning and filling tasks of various meteorological indicators, and provides reliable input for subsequent icing predictions.

[0017] 2. This invention establishes a road ice melting prediction model, integrates LSTM neural networks and support vector machines, effectively combines physical rules with data-driven methods, predicts whether the road is icy, outputs road icing results, and reduces manual review costs. Compared with a single neural network model, it has higher accuracy and reliability and stronger adaptability to extreme environments, providing a flexible solution for subsequent road segmentation and ice melting work.

[0018] 3. This invention optimizes the spraying parameters in ice melting by introducing an enhanced Skyhawk optimization algorithm, integrating the hill climbing algorithm and the hunting behavior of the Harris Hawk. Compared with the traditional algorithm, it solves the problems of easy falling into local optimality, slow convergence speed and poor accuracy. By simulating the hunting behavior of the Skyhawk, the global optimal solution search for the spraying parameters is realized, and the spraying parameters suitable for the ice-melting sections are obtained, which significantly reduces energy waste and improves the thoroughness of ice melting.

[0019] 4. This invention adjusts the road ice melting implementation strategy, establishes a snow melting environment coupling model and alarm mechanism, integrates dynamic adaptive adjustment and alarm mechanism, and constructs a closed-loop response system of resources-environment-equipment, thereby improving the ice melting response speed and the intelligent level of emergency management in extreme weather conditions.

[0020] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The present invention provides an overall schematic diagram of a road ice melting implementation system; Figure 2 The present invention provides a flow chart of a method for implementing road ice melting; Figure 3 The present invention provides a schematic diagram of the module structure of a road ice melting implementation system. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] Traditional road ice melting methods generally rely on repeated mechanical de-icing and timed spraying of snow-melting agents. They lack intelligent control capabilities and are unable to dynamically adjust ice melting strategies based on meteorological conditions, slippery conditions of ice and snow on the road surface, etc., often resulting in energy waste and incomplete ice melting.

[0024] In order to solve the above technical problems, Figure 1 and Figure 3 As shown, an embodiment of the present invention provides a road ice melting implementation system, which specifically includes: meteorological monitoring, snow melting agent spraying and management and control platform; the meteorological monitoring includes a meteorological environment monitoring module and a road surface condition monitoring module, which are used to collect meteorological data and monitor the road surface condition, obtain an initial road ice melting data set, use a data detection method based on an adaptive window to perform anomaly detection on the initial road ice melting data set, and fill in missing data to generate a processed road ice melting data set; the snow melting agent spraying includes a snow melting agent pump station, snow melting agent spraying facilities and snow melting agent auxiliary equipment; the management and control platform is used for ice and snow monitoring and early warning, equipment condition monitoring and solution spraying management and control; the ice Snow monitoring and early warning include establishing a road ice melting prediction model, predicting whether the road is frozen based on the processed road ice melting data set, outputting the road icing results, and segmenting the road to obtain a set of segmented ice melting sections; the equipment operating condition monitoring includes monitoring the operation process of the snow melting agent spraying; the solution spraying control includes performing ice melting work on the ice melting sections in the set of segmented ice melting sections, introducing an enhanced Sky Eagle optimization algorithm to optimize the spraying parameters in the ice melting work, generating a road ice melting implementation strategy, adjusting the road ice melting implementation strategy based on real-time meteorological data and the use of snow melting agent materials, and establishing a snow melting environment coupling model and alarm mechanism.

[0025] A specific embodiment is to use meteorological environment sensors to automatically monitor comprehensive meteorological environment information such as temperature, humidity, pressure, and wind speed, and set up road condition sensors to collect road data such as road slipperiness, road humidity, and road water accumulation; the snow-melting agent solution spraying equipment is composed of an integrated intelligent device and liquid storage, intelligent spraying, and electrical system to control the automatic spraying of the snow-melting agent solution, providing real-time meteorological and road condition monitoring data for the embodiment of the present invention, helping statistical analysis and auxiliary decision-making.

[0026] In the specific implementation process of the above embodiment, first, by collecting meteorological data and monitoring the road surface conditions, an initial road ice melting data set is obtained, and anomaly detection is performed using a data detection method based on an adaptive window, and missing data is filled to obtain a processed road ice melting data set; this method dynamically adjusts the window size. When the data anomaly ratio is high, the window is reduced to improve the detection sensitivity. When the data is relatively normal, the window is expanded to reduce the computing overhead, avoiding the waste of resources caused by frequent adjustments, achieving a balance between detection accuracy and computing efficiency, and being suitable for anomaly cleaning and filling tasks of various meteorological indicators, providing reliable input for subsequent icing predictions; secondly, a road ice melting prediction model is established, and based on the processed road ice melting data set, whether the road is frozen is predicted, the road icing result is output, and the road is segmented; this method integrates LSTM neural network and support vector machine, effectively combines physical rules and data drive, reduces manual review costs, and is relatively safe. Compared with a single neural network model, it has higher accuracy and reliability and stronger adaptability to extreme environments. Segmented processing provides a flexible solution for subsequent ice melting work. Then, ice melting is carried out on segmented roads, and an enhanced Eagle optimization algorithm is introduced to optimize the spraying parameters in the ice melting work to generate a road ice melting implementation strategy. Compared with traditional algorithms, this algorithm integrates the hill climbing algorithm and the hunting behavior of the Harris hawk. It solves the problems of easy falling into local optimality, slow convergence and poor accuracy. By simulating the hunting behavior of the Eagle, the global optimal solution search for the spraying parameters is realized, and the spraying parameters suitable for the ice melting sections are obtained, which significantly reduces energy waste and improves the thoroughness of ice melting. Finally, the road ice melting implementation strategy is adjusted, and a snow melting environment coupling model and alarm mechanism are established. The dynamic adaptive adjustment and alarm mechanism are integrated to build a closed-loop response system of resources-environment-equipment, which improves the ice melting response speed and the intelligent level of emergency management in extreme weather conditions, and completes the implementation of road ice melting.

[0027] Further, in order to better introduce the technical solution of the embodiment of the present invention, based on the above-mentioned road ice melting implementation system, as shown in FIG. Figure 2 As shown, an embodiment of the present invention provides a method for implementing road ice melting, which specifically includes the following contents: S1. Collect meteorological data and monitor road conditions to obtain an initial road ice melting data set, perform anomaly detection on the initial road ice melting data set using an adaptive window-based data detection method, and fill in missing data to generate a processed road ice melting data set; Said S1 comprises the following steps: S11. Use a multi-factor meteorological environment sensor to collect meteorological data, including temperature, humidity, pressure, wind speed, etc., to obtain a meteorological data set; then monitor the road surface conditions, including road slipperiness, road humidity, road water accumulation, etc., to obtain a road surface condition data set; and record the time points of collecting meteorological data and road surface conditions to generate a road ice melting time series. Combine the road ice melting time series, meteorological data set, and road surface condition data set to form an initial road ice melting data set. ,in represents the mth time point of the road ice melting time series, represents the meteorological data collected at the mth time point, represents the road surface state collected at the mth time point; S12: Setting a sliding window, dynamically and adaptively adjusting the sliding window to generate an adaptive window, performing anomaly detection on the initial road ice melting data set using a data detection method based on the adaptive window, and deleting the abnormal data to obtain a processed road ice melting data set. The specific steps are as follows: S121, placing the adaptive window at the beginning of the initial road ice melting data set, calculating the mean and variance of the road ice melting data within the adaptive window, and then calculating the anomaly score of the nth road ice melting data ,in Indicates the nth road ice melting data, represents the average value of road ice melting data within the adaptive window, Represents the variance of the road ice melting data within the adaptive window; sets an abnormal threshold. When the abnormal score of the n-th road ice melting data is greater than the abnormal threshold, the n-th road ice melting data is considered as abnormal data; S122, set the current adaptive window size to w, count the number of abnormal data in the current adaptive window, and then calculate the ratio of the number of abnormal data to the current adaptive window size to obtain the current abnormal ratio; set the target abnormal ratio, and then calculate the next adaptive window size ,in Indicates the window adjustment coefficient, which is 0.1. represents the target abnormality ratio, Indicates the current abnormal ratio; S123: Move the current adaptive window and update the current adaptive window size according to the next adaptive window size. Calculate the anomaly score of the road ice melting data in the next adaptive window, mark the location of the abnormal data, and continue to update the adaptive window size until the initial road ice melting data set is traversed, delete all abnormal data, and obtain the processed road ice melting data set. S13. When the missing data is the first road ice melting data or the wth road ice melting data in the adaptive window, the missing data is filled using the mean of the road ice melting data in the adaptive window; otherwise, the missing data is filled using piecewise linear interpolation, and the road ice melting data before the missing data and the road ice melting data after the missing data are selected. In this case, the missing data filling value is ,in Indicates the road ice melting data before the missing data, Indicates road ice melting data after missing data, Indicates the time point corresponding to the road ice melting data before the missing data, Indicates the time point corresponding to the road ice melting data after the missing data, Indicates the time point corresponding to the missing data; fills the missing data in the processed road ice melting data set in sequence to generate a processed road ice melting data set; In this embodiment, by collecting meteorological data and monitoring the road surface conditions, an initial road ice melting data set is obtained, anomaly detection is performed using a data detection method based on an adaptive window, and missing data is filled to obtain a processed road ice melting data set; this method dynamically adjusts the window size. When the data anomaly ratio is high, the window is narrowed to improve detection sensitivity. When the data is relatively normal, the window is expanded to reduce computing overhead, avoiding resource waste caused by frequent adjustments, and achieving a balance between detection accuracy and computing efficiency. It is suitable for anomaly cleaning and filling tasks of various meteorological indicators, providing reliable input for subsequent icing predictions; specifically, for example, simplifying the data set and only recording time points , temperature and road wetness, {(t1, (5℃, 60%)), (t2, (20℃, 20%)), (t3, (4℃, 65%)}, set the window size to 3, the temperature anomaly score of t1 is 0, the temperature anomaly score of t2 is 1.16, the temperature anomaly score of t3 is -1.22, the anomaly threshold is 1.0, the anomaly ratio is 1 / 3, the target anomaly ratio is 10%, the window adjustment coefficient is 0.1, then adjust the window size to 3, delete the abnormal data t2; fill in the missing data, use piecewise linear interpolation, the time interval of the preceding data of t2 is 5 minutes, the time interval of the following data of t2 is 5 minutes, the fill-in temperature is 5℃, and fill in the data in sequence; S2. Establishing a road ice melting prediction model based on a neural network, predicting whether the road is icy based on the processed road ice melting data set, outputting a road icing result, and segmenting the road to obtain a set of segmented ice melting road sections; The S2 comprises the following steps: S21. Obtaining temperature, humidity, pressure, wind speed, road humidity, and road water accumulation from the processed road ice melting data set to form a current road ice melting data set; then obtaining meteorological data, road surface conditions, and collection time points from previous years to form a road ice melting data sample set; setting a window step size, dividing the collection time points in the road ice melting data sample set according to the window step size, and performing normalization processing to obtain a plurality of road ice melting data sample subsets; S22. Build a road ice melting prediction model based on the LSTM neural network and support vector machine to predict the probability of road icing, output the road icing probability, and determine whether the road is icy. The specific steps are as follows: S221. Assume that a road ice melting prediction model includes a neural network model and a support vector machine, wherein the neural network model adopts an encoder-decoder structure, the encoder includes two LSTM layers, the decoder includes one LSTM layer and a fully connected layer, and the activation function is a Tanh function; The road ice melting data sample subset is divided into a sample training set and a sample test set, and the sample training set is input into the input layer of the neural network model for training until the neural network model converges to obtain a trained neural network model; the sample test set is then input into the trained neural network model, a prediction result is output, and an accuracy threshold is set. When the accuracy of the prediction result is greater than the accuracy threshold, a final road ice melting prediction model is obtained; otherwise, the weight is adjusted until the accuracy of the prediction result is greater than the accuracy threshold; S323: Set a road humidity threshold and a road water volume threshold, and set a road icing rule; when the temperature in the prediction result is less than 0 degrees Celsius and the road humidity is greater than the road humidity threshold, determine that the road is icy; when the road water volume in the prediction result is greater than the road water volume threshold and the temperature is less than 0 degrees Celsius, determine that the road is icy; mark the road ice melting data in the prediction result that meets the road icing rule as 1, otherwise mark it as 0; S33, setting the support vector machine to use a radial basis kernel function, dividing the prediction results according to the window step size, and normalizing them, and inputting them into the support vector machine for training, setting a maximum number of training rounds, and stopping training when the maximum number of training rounds is reached, to obtain the final support vector machine; The current road ice melting data set is divided according to the window step size, standardized, and input into the final road ice melting prediction model to output the road ice melting data prediction value. The road ice melting data prediction value is then marked according to the road icing rule and input into the final support vector machine to determine whether the road is icy. The output is 1 if the road is icy and 0 if the road is not icy, thereby obtaining the road icing result. S23. Segment the road according to the road icing result, find the road sections corresponding to the icing and mark them as ice-melting sections, find the road sections corresponding to the non-icing and mark them as non-ice-melting sections, and obtain a segmented ice-melting section set; In this embodiment, a road ice melting prediction model is established. Based on the processed road ice melting data set, it is predicted whether the road is frozen, the road icing result is output, and the road is segmented. This method integrates LSTM neural network and support vector machine, effectively combines physical rules with data-driven, reduces the cost of manual review, and has higher accuracy and reliability and stronger adaptability to extreme environments than a single neural network model. The segmented processing provides a flexible solution for subsequent ice melting work. Specifically, for example, with a window step of every 2 hours, 6 consecutive hours of data are used as a sample subset, and Z-score standardization is performed on features such as temperature (range -25℃-10℃) and humidity (0-100%) to make the mean 0. , with a standard deviation of 1; Encoder: 2-layer LSTM, 64 neurons per layer, processing the input sequence (6 hours × 6 features); Decoder: 1-layer LSTM (32 neurons) + fully connected layer (outputting 6-feature predictions), with the Tanh activation function; Icing rule settings: Condition 1: Temperature ≤ 0°C and road humidity ≥ 85%; Condition 2: Water accumulation ≥ 3mm and temperature ≤ 0°C. If either condition is met, the road is marked as ice (label 1); otherwise, the label is 0; SVM classifier: Uses the RBF kernel function and the predicted values output by the LSTM as features; Combined with GIS maps, icy sections (label 1) and normal sections (label 0) are divided into 500-meter intervals, and the prediction results are updated to dynamically adjust the segment set to improve deicing efficiency. S3. Performing ice-melting operations on the ice-melting sections in the set of segmented ice-melting sections, optimizing spraying parameters during the ice-melting operations using an enhanced Sky Eagle optimization algorithm, and generating a road ice-melting implementation strategy; The S3 includes the following steps: S31, selecting an ice-melting section from the set of segmented ice-melting sections for ice-melting operation, controlling spraying parameters during the ice-melting operation, wherein the spraying parameters include the pipeline pressure of the deicing solution spraying equipment, the deicing agent concentration, and the spraying volume per unit area; setting the pipeline pressure range, the deicing agent concentration range, and the minimum spraying coverage rate, spraying the deicing solution, and then recording the energy consumption of the deicing solution spraying equipment, the ice melting time of the ice-melting section, and the coverage uniformity of the deicing solution; S32. Establish an objective function based on minimum energy consumption and maximum ice melting efficiency ,in 、 and represents the weight coefficient, Indicates the energy consumption of snow melting solution spraying equipment, Indicates the time it takes for ice to melt on the ice-melting road section. Indicates the coverage uniformity of the deicing solution; The Sky Eagle Optimization Algorithm is improved by integrating the hill climbing algorithm and the Harris Hawk hunting behavior to obtain the enhanced Sky Eagle Optimization Algorithm. The enhanced Sky Eagle Optimization Algorithm is used to optimize the spraying parameters to obtain the optimized spraying parameters. The specific steps are as follows: S321. The objective function is used as the fitness function, and a search space is set. There is a population of eagles in the search space. The position of the eagles in the eagle population represents a set of spraying parameters. The iterative process of the eagle positions is regarded as a process of optimizing the spraying parameters. The optimal fitness function value is used to simulate the optimal objective function value. The number of eagle populations is set to p, the dimension of the eagle population is set to q, the eagle population is initialized, the current number of iterations is t, the maximum number of iterations is T, the hill climbing algorithm is introduced, and the position of the i-th eagle at the t-th iteration is set to , distance position Recent Location ,Location To location The probability of , Represents a random number between the interval [0, 1]; when hour, , otherwise the position constant; S322, the eagle population enters the high-altitude hunting and gliding hunting stages, and the average position of the eagle population at the tth iteration is set to , the optimal position is , now calculate the position of the i-th eagle at the t+1th iteration ; Introduce Levi flight simulation to simulate eagle hunting, set Levi flight coefficient to , the Gaussian distribution coefficient is and , for position Update and get ; S323, use Harris Hawk hunting behavior to replace the low-flying hunting and gliding hunting stages of the Skyhawk population, set represents a random number between the interval [0, 1], 、 、 and represents a random number between the interval [0, q], when When the jth eagle is randomly selected from the eagle population, the position , again for the position Update and get ;when When , the upper and lower bounds of the search space are set to and , again for the position Update and get At this time, all stages of the t-th iteration are completed and the next iteration is entered until the current number of iterations reaches the maximum number of iterations. The iteration is stopped and the final eagle population is obtained. The eagle position corresponding to the best fitness function value in the final eagle population is found to obtain the optimized spraying parameters. S33, the optimized spraying parameters include the optimized pipeline pressure, deicing agent concentration, and spraying volume per unit area of the deicing agent solution spraying equipment, selecting an deicing section from the set of segmented deicing sections, and driving the deicing agent solution spraying equipment to perform deicing using the optimized spraying parameters, thereby obtaining a road deicing implementation strategy; In this embodiment, ice melting is performed on segmented roads, and an enhanced Eagle optimization algorithm is introduced to optimize the spraying parameters in the ice melting work and generate a road ice melting implementation strategy. The algorithm integrates the hill climbing algorithm and the hunting behavior of the Harris hawk. Compared with the traditional algorithm, it solves the problems of easy falling into local optimality, slow convergence speed and poor accuracy. By simulating the hunting behavior of the Eagle, the global optimal solution search of the spraying parameters is realized, and the spraying parameters suitable for the ice melting section are obtained. Specifically, for example, the pipeline pressure range is set to [0.5, 2.5] MPa, the deicing agent concentration range is [20%, 40%], the minimum spraying coverage rate is 90%, and the Eagle algorithm parameters are initialized: the population size is 50, the dimension is 3 (corresponding to 3 optimization parameters), the maximum number of iterations is 100, the objective function weight coefficients are 0.4 (energy consumption), 0.3 (melting time), 0.3 (coverage); 50 sets of initial parameter combinations were randomly generated, and a hill climbing algorithm was used for local search. The position of the Skyhawk was updated during the high-altitude gliding phase. Levy flight was then introduced to enhance the global search capability, resulting in jump-like parameter adjustments. The position was further updated using the Harris Hawk hunting mechanism. After 100 iterations, the algorithm converged to the optimal parameter combination, resulting in a pipeline pressure of 1.8 MPa (a 20% reduction in energy consumption compared to the initial value), a deicing agent concentration of 30% (the minimum effective concentration to meet antifreeze requirements, reducing costs), and a spray volume per unit area of 0.12 L / m² (coverage increased to 95%, improving ice melting efficiency). The optimization algorithm was used to search for the global optimal solution for the spraying parameters, significantly reducing energy waste and improving ice melting thoroughness. The optimized parameters were input into the automated spraying control system to achieve intelligent and precise ice melting operations. S4. Adjust the road de-icing implementation strategy based on real-time meteorological data and de-icing agent material usage, establish a de-icing environment coupling model and an alarm mechanism, and complete the road de-icing implementation; The S4 comprises the following steps: S41. Collect real-time meteorological data, set a change threshold and a thickness threshold, and when the change rate of the real-time meteorological data is greater than the change threshold, find the de-icing section corresponding to the real-time meteorological data and measure the ice thickness. When the ice thickness is greater than the ice threshold, adjust the de-icing strategy for the road, giving priority to de-icing the de-icing section corresponding to the real-time meteorological data. S42: Monitor the usage of deicing agent materials, including deicing agent concentration and consumption per unit area, and establish a deicing environment coupling model to calculate the remaining amount in the liquid storage tank. , where U represents the initial volume of the liquid storage tank, k represents the concentration correction coefficient, represents the area of the e-th ice-melting road section in the set of segmented ice-melting road sections, represents the unit area consumption of the e-th ice-melting road section, s represents the number of segmented ice-melting road sections, Set a remaining threshold. When the remaining amount in the storage tank is less than the remaining threshold, the snow-melting agent solution is replenished in time. When the remaining amount in the storage tank is greater than the rated threshold, the alarm mechanism is triggered to complete the road ice melting implementation. In this embodiment, the road ice melting implementation strategy is adjusted, a snow melting environment coupling model and an alarm mechanism are established, dynamic adaptive adjustment and alarm mechanisms are integrated, and a closed-loop response system of resources, environment, and equipment is constructed. Specifically, for example, the meteorological change threshold is set to 20% / hour, and the ice thickness threshold is set to 5mm. The system monitors that the temperature in a certain area drops sharply from -2°C to -8°C within 1 hour. The total span of the reference temperature range is 10°C. At this time, the change rate is 6°C / 10°C = 60% / hour. The corresponding road section is located: K12-K15 section of the highway (the road section areas are 800m², 1000m², and 120m² respectively, and the unit consumption is 20%. The measured ice thickness was 6.2 mm (exceeding the 5 mm threshold), and the system automatically upgraded the road section to a priority level. The concentration correction coefficient k was 1.1 (due to low temperatures, the concentration needed to be increased based on standard 1). The initial liquid storage volume was 5000 L, and the calculated remaining volume in the storage tank was 440 L (less than the remaining volume threshold of 500 L). The snow-melting agent material was replenished in time, and the remaining volume of the snow-melting agent after replenishment was 4000 L, which was higher than the rated threshold of 2000 L. This improved the ice-melting response speed in extreme weather conditions and the intelligent level of emergency management, and completed the implementation of road ice melting.

[0028] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0029] The preferred embodiments of the invention disclosed above are intended only to help illustrate the invention. These preferred embodiments do not exhaust all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A road ice melting implementation system, characterized in that: include: Meteorological monitoring, including a meteorological environment monitoring module and a road condition monitoring module, is used to collect meteorological data and monitor road conditions to obtain an initial road ice melting data set. Anomaly detection is performed on the initial road ice melting data set using an adaptive window-based data detection method, and missing data is filled to generate a processed road ice melting data set. Snowmelt spraying, including snowmelt pumping stations, snowmelt spraying facilities and snowmelt auxiliary equipment; A management and control platform for ice and snow monitoring and early warning, equipment condition monitoring, and solution spraying control; The ice and snow monitoring and early warning system includes establishing a road ice melting prediction model, predicting whether the road is icy based on the processed road ice melting data set, outputting the road icing result, and segmenting the road to obtain a set of segmented ice melting sections; The equipment operating condition monitoring includes monitoring the operation process of spraying the snow melting agent; The solution spraying control includes performing ice-melting work on ice-melting sections in a set of segmented ice-melting sections, introducing an enhanced Sky Eagle optimization algorithm to optimize the spraying parameters in the ice-melting work, generating a road ice-melting implementation strategy, adjusting the road ice-melting implementation strategy according to real-time meteorological data and the use of snow-melting agent materials, and establishing a snow-melting environment coupling model and an alarm mechanism.

2. A road ice melting implementation system according to claim 1, characterized in that: The collecting of meteorological data and monitoring of road conditions to obtain an initial road ice melting data set includes: Meteorological data is collected to obtain a meteorological data set, road surface conditions are monitored to obtain a road surface condition data set, and road ice melting time series are recorded to obtain an initial road ice melting data set.

3. A road ice melting implementation system according to claim 2, characterized in that: The method of using the adaptive window-based data detection method to perform anomaly detection on the initial road ice melting data set includes: Set a sliding window, dynamically and adaptively adjust the sliding window to generate an adaptive window, calculate the anomaly score of the road ice melting data in the adaptive window, and identify the abnormal data; Count the number of abnormal data in the current adaptive window, then calculate the ratio of the number of abnormal data to the current adaptive window size, and calculate the next adaptive window size; The current adaptive window size is updated according to the next adaptive window size, and the anomaly score of the road ice melting data in the next adaptive window is calculated until the initial road ice melting data set is traversed, all anomaly data are deleted, and the processed road ice melting data set is obtained.

4. A road ice melting implementation system according to claim 3, characterized in that: The missing data described and filled in include: When the missing data is the first or last road ice melting data in the adaptive window, the mean of the road ice melting data in the adaptive window is used to fill the missing data; otherwise, piecewise linear interpolation is used to fill the missing data to generate a processed road ice melting data set.

5. A road ice melting implementation system according to claim 4, characterized in that: The road ice melting prediction model is established to predict whether the road is icy based on the processed road ice melting data set, and the output of the road icing result includes: Obtaining a current road ice melting data set from the processed road ice melting data set, then obtaining a road ice melting data sample set, setting a window step, dividing the data according to the window step, and performing standardization processing to obtain a plurality of road ice melting data sample subsets; The road ice melting prediction model is set to include a neural network model and a support vector machine. The neural network model adopts an encoder-decoder structure. The encoder includes two LSTM layers, the decoder includes one LSTM layer and a fully connected layer, and the activation function is the Tanh function. Dividing the road ice melting data sample subset into a sample training set and a sample test set, inputting the sets into a neural network model for training, outputting prediction results, and obtaining a final road ice melting prediction model; Setting a road icing rule, marking the road ice melting data that meets the road icing rule in the prediction result as 1, otherwise marking it as 0; The support vector machine is set to use a radial basis kernel function, the prediction results are divided according to the window step size, and normalized, and input into the support vector machine for training. The maximum number of training rounds is set. When the maximum number of training rounds is reached, the training is stopped to obtain the final support vector machine; The current road ice melting data set is divided according to the window step size and standardized, and then input into the final road ice melting prediction model to output the road ice melting data prediction value. The road ice melting data prediction value is marked according to the road icing rules and input into the final support vector machine. The output 1 indicates that the road is iced, and the output 0 indicates that the road is not iced, thus obtaining the road icing result.

6. A road ice melting implementation system according to claim 5, characterized in that: The segmentation process of the road includes: The road is segmented according to the road icing result, and the road sections corresponding to the road icing are found and marked as ice-melting sections. The road sections corresponding to the road not icing are found and marked as ice-melting sections, thereby obtaining a segmented ice-melting section set.

7. A road ice melting implementation system according to claim 6, characterized in that: The introduction of the enhanced Sky Eagle optimization algorithm to optimize the spraying parameters in ice melting work includes: Selecting an ice-melting section from the set of segmented ice-melting sections for ice-melting operation, controlling spraying parameters during the ice-melting operation, wherein the spraying parameters include a pipeline pressure of an ice-melting solution spraying device, an ice-melting agent concentration, and a spraying volume per unit area; setting a pipeline pressure range, an ice-melting agent concentration range, and a minimum spraying coverage rate, spraying the ice-melting agent solution, and then recording energy consumption of the ice-melting solution spraying device, ice melting time of the ice-melting section, and coverage uniformity of the ice-melting agent solution; Establish an objective function based on minimum energy consumption and maximum ice melting efficiency; The Skyhawk optimization algorithm is improved by integrating the hill climbing algorithm and the Harris hawk hunting behavior to obtain an enhanced Skyhawk optimization algorithm; the objective function is used as the fitness function, a search space is set, a Skyhawk population exists in the search space, the Skyhawk position in the Skyhawk population represents a set of spraying parameters, the Skyhawk position iteration process is regarded as a spraying parameter optimization process, and the optimal fitness function value is used to simulate the optimal objective function value; Introduce the hill climbing algorithm to update the position of the Sky Eagle; The Sky Eagle population has entered the high-altitude hunting and gliding hunting stages, and Levi's flight simulation Sky Eagle hunting has been introduced to update the Sky Eagle's position; The Harris hawk hunting behavior is used to replace the low-flying hunting and gliding hunting stages of the hawk population. The hawk position is updated again until the current number of iterations reaches the maximum number of iterations. The iteration is stopped to obtain the final hawk population. The hawk position corresponding to the best fitness function value in the final hawk population is found to obtain the optimized spraying parameters.

8. A road ice melting implementation system according to claim 7, characterized in that: The generated road ice melting implementation strategy includes: The optimized spraying parameters include the pipeline pressure, deicing agent concentration and spraying volume per unit area of the optimized deicing agent solution spraying equipment. An deicing section in the set of segmented deicing sections is selected, and the deicing agent solution spraying equipment is driven by the optimized spraying parameters to perform deicing work, thereby obtaining a road deicing implementation strategy.

9. A road ice melting implementation system according to claim 8, characterized in that: The adjustment of the road de-icing implementation strategy based on real-time meteorological data and de-icing material usage, and the establishment of a de-icing environment coupling model and an alarm mechanism include: Collect real-time meteorological data, set a change threshold and a thickness threshold, and when the change rate of the real-time meteorological data is greater than the change threshold, find the de-icing section corresponding to the real-time meteorological data and measure the ice thickness. When the ice thickness is greater than the ice threshold, adjust the de-icing strategy for the road and give priority to de-icing the corresponding de-icing section. Monitor the use of snow-melting agent materials, then establish a snow-melting environment coupling model to calculate the remaining amount in the storage tank; set the remaining amount threshold and the rated threshold. When the remaining amount in the storage tank is less than the remaining amount threshold, replenish the snow-melting agent solution in time. When the remaining amount in the storage tank is greater than the rated threshold, trigger the alarm mechanism and complete the road ice melting implementation.

10. A method for implementing road ice melting, characterized in that: The road de-icing implementation system according to any one of claims 1 to 9 specifically comprises: S1. Collect meteorological data and monitor road conditions to obtain an initial road ice melting data set, perform anomaly detection on the initial road ice melting data set using an adaptive window-based data detection method, and fill in missing data to generate a processed road ice melting data set; S2. Establishing a road ice melting prediction model based on a neural network, predicting whether the road is icy based on the processed road ice melting data set, outputting a road icing result, and segmenting the road to obtain a set of segmented ice melting road sections; S3. Performing ice-melting operations on the ice-melting sections in the set of segmented ice-melting sections, optimizing spraying parameters during the ice-melting operations using an enhanced Sky Eagle optimization algorithm, and generating a road ice-melting implementation strategy; S4. Adjust the road de-icing implementation strategy based on real-time meteorological data and the use of de-icing agent materials, establish a de-icing environment coupling model and an alarm mechanism, and complete the road de-icing implementation.

Images