Highway pavement ice condensation monitoring system

Abstract

The invention, which relates to the technical field of highway traffic safety monitoring, discloses an expressway pavement ice condensation monitoring system comprising a data acquisition module for acquiring environmental data and pavement icing state information on an expressway pavement; and the self-calibration module is connected with the data acquisition module, performs self-calibration on the data acquisition module according to the environment data acquired in real time and the road surface icing state information, and corrects sensor errors caused by external environment factors. According to the highway pavement ice condensation monitoring system, a self-calibration function is added in monitoring equipment and an intelligent algorithm is introduced, so that the monitoring system can automatically correct measurement errors caused by external environment changes in real time, and a machine learning model is combined to predict pavement conditions more accurately; the working stability of the system in severe weather can be improved, and the risk of icing of the road surface can be found earlier, so that more accurate early warning information is provided for a traffic management department, and the probability of traffic accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of highway traffic safety monitoring, and particularly to a monitoring system for icing on expressway road surfaces. Background Art

[0002] According to the existing technological development, many monitoring systems for icing on expressway road surfaces have adopted various sensors and technical means to detect road icing conditions, including temperature and humidity sensors, infrared sensors, weather stations, and other data acquisition devices; these systems usually conduct icing risk warnings by real-time monitoring of road surface temperature, humidity, and meteorological data; however, the existing technical solutions still have certain limitations; although many sensors can detect the basic information of road surface temperature and humidity, in severe weather conditions, such as snowstorms, strong winds, or low-temperature environments, the sensors will be affected by snow and ice accumulation, moisture, or icing, resulting in sensor failure or inaccurate data. For this problem, some technical solutions have adopted waterproof and antifreeze designs, or heating devices to ensure the normal operation of the sensors under low-temperature conditions, but these solutions usually do not solve the long-term reliability problems that may occur in extreme weather. Summary of the Invention

[0003] (I) Technical Problems to be Solved

[0004] In view of the deficiencies of the prior art, the present invention provides a monitoring system for icing on expressway road surfaces, which solves the long-term reliability problems that may occur to sensors in extreme weather.

[0005] (II) Technical Solutions

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A monitoring system for icing on expressway road surfaces, comprising:

[0007] A data acquisition module, which acquires environmental data and road surface icing state information on the expressway road surface;

[0008] A self-calibration module, connected to the data acquisition module, self-calibrates the data acquisition module according to the environmental data and road surface icing state information collected in real time, and corrects the sensor errors caused by external environmental factors, where the external environmental factors include snow and ice accumulation, moisture;

[0009] A data processing module, connected to the self-calibration module, processes the collected data, analyzes and predicts the road surface icing situation according to the corrected data; also classifies the road surface icing degree through standard comparison, and the degrees include mild icing, moderate icing, and severe icing, and determines the icing risk level of the current section based on the actual situation of data acquisition and comparison with the preset standard data;

[0010] A prediction module, connected to the data processing module, predicts the road icing situation through a machine learning algorithm based on the real-time corrected data and generates an icing risk assessment report;

[0011] A user interface module provides real-time data of icing risk information, weather warnings, and road condition monitoring to traffic management personnel through a display screen or a mobile device, presenting the road icing prediction results and risk assessment information to users, facilitating real-time decision-making by traffic management personnel and real-time adjustment of traffic control measures;

[0012] Among them, the prediction module adopts multiple regression analysis and time series prediction algorithms, quantitatively predicts the possibility of road icing by analyzing historical data and real-time collected data, and generates an icing warning report.

[0013] Preferably, the data acquisition module includes high-precision temperature and humidity sensors, infrared sensors, meteorological sensors, and heating devices. The heating devices are used to prevent the sensors from being affected by ice, snow, or moisture under harsh weather conditions, ensuring the long-term stable operation of the sensors; the data acquisition module is installed on both sides of the highway pavement or along the street lamp crossbeam and on the bridge, ensuring that the sensors can cover key areas on the road surface and minimizing external environmental interference to obtain real-time road surface environment data, including: regularly collecting the temperature and humidity data of the current air by the temperature and humidity sensors, the infrared sensor collecting the road surface temperature in real time, and the meteorological sensor obtaining the current meteorological data, including wind speed, air pressure, and precipitation. These data help predict meteorological conditions that may cause icing, including cold snaps, snowfall, or moisture; the data acquisition module also continuously monitors the road surface temperature through the infrared sensor, monitors the road icing state, and obtains road icing state information.

[0014] Preferably, the self-calibration module includes:

[0015] A sensor error detection unit is responsible for monitoring in real time the deviation between the data output by the data acquisition module and the preset standard value, and real-time detecting the sensor output deviation caused by external environmental factors (including ice and snow accumulation, moisture, temperature change); the process includes: obtaining real-time data from each sensor from the data acquisition module, including temperature, humidity, and infrared reflectivity information, comparing the real-time collected sensor data with the preset standard data, and the preset standard value is derived from the factory calibration value of the device, historical data, or external environmental standard data, including normal humidity and temperature ranges. If the sensor output data deviates from the predetermined standard, the system will mark the data as abnormal. When the sensor output data exceeds the allowable error range, the error detection unit will alarm in real time and record the abnormal data to form feedback information for subsequent calibration and correction;

[0016] Correction algorithm unit, based on the feedback information provided by the sensor error detection unit, automatically adjusts the readings of sensor data, eliminates the errors caused by environmental changes, ensures the accuracy of sensor data, and the correction algorithm adjusts the sensor output data according to historical data, current environmental data, and known calibration standards; the process includes: receiving the feedback from the sensor error detection unit, analyzing the error sources, and the error sources include ice and snow accumulation, moisture influence. According to the preset correction algorithm, the sensor errors are adjusted according to the temperature correction and moisture compensation rules based on the physical model, and the data is dynamically corrected to make it more conform to the actual road surface conditions. Among them, the preset correction algorithm is based on linear regression, Kalman filtering, or machine learning model;

[0017] Feedback mechanism unit, dynamically adjusts the working parameters of the data acquisition module according to the corrected data to ensure that the entire system can maintain a high-precision working state. This mechanism can automatically adjust the working mode of the acquisition module, including the acquisition frequency and the sensor calibration coefficient, to adapt to the changes in the external environment; the process includes: after correcting the data, the feedback mechanism unit will adjust the parameters of the data acquisition module according to the corrected information, including increasing the acquisition frequency of the sensor in snowy and icy weather to better capture the subtle changes in road icing; in an environment with heavy moisture, adjusting the sensitivity of the moisture sensor. When the external environment changes (including sudden temperature drop, heavy snowfall), the feedback mechanism will adjust the parameters of the data acquisition module in real time by automatically adjusting the calibration coefficient or the acquisition method to ensure that the system can work continuously and stably. The feedback mechanism enables the data acquisition module to cope with the continuous changes in the external environment by automatically adjusting the calibration coefficient or the acquisition method.

[0018] Preferably, the process of the correction algorithm unit analyzing the error source and dynamically correcting the data according to the preset correction algorithm includes: receiving the feedback information from the sensor error detection unit, where the feedback content includes the deviation between the sensor output data and the preset standard data, specifically including the deviation magnitude of the data and the error type. The error type includes temperature deviation and humidity deviation. This feedback information is the basis for subsequent error analysis. The correction algorithm unit conducts a preliminary analysis on the received feedback data to identify the source of the error. Among them, for temperature error analysis, by checking the output value of the temperature sensor, it is judged whether the temperature sensor error is caused by the external environment. The external environment includes ice and snow accumulation and sudden drop in temperature. Among them, for humidity error analysis, the output value of the humidity sensor is checked to analyze whether the error is caused by environmental humidity change or precipitation. For example, in humid weather, humidity may affect the accuracy of the humidity sensor. By analyzing the error source through a physical model, the analysis result is obtained. The correction algorithm unit applies the physical model to deeply analyze the error source. Based on the physical model, temperature error analysis is carried out. When the temperature sensor data is low, it may be due to the error caused by ice and snow accumulation or frost. The correction algorithm calculates the actual temperature value by applying the physical principles of the temperature change model and the heat conduction model, combined with environmental factors, and compares it with the output of the sensor to confirm the source of the error. Among them, environmental factors include temperature, humidity, and wind speed. Based on the humidity compensation rule, humidity error analysis is carried out. The error of the humidity sensor is usually caused by too high humidity or meteorological changes. The correction algorithm compares the current environmental humidity with the sensor output value through the humidity compensation model to judge whether the humidity sensor is affected by humidity change and makes appropriate corrections; The correction algorithm confirms the error source according to the analysis result. For temperature error confirmation, the correction algorithm confirms whether ice and snow accumulation or frost is the main source of the temperature sensor error through the temperature model. If it is determined that the error is caused by ice and snow accumulation, the correction algorithm will generate a correction strategy to adjust the sensor data. Among them, the temperature model includes the temperature change model and the heat conduction model. For humidity error confirmation, through the humidity compensation model, the correction algorithm confirms whether the humidity change has caused an error to the humidity sensor. If it is determined as a humidity error, the correction algorithm will correct it according to the actual environmental data and the compensation rule;

[0019] Once the error sources are identified, the correction algorithm unit formulates specific correction strategies and dynamically adjusts the sensor data for temperature correction. If the error is due to ice and snow accumulation or frost, the correction algorithm calculates the true temperature value based on the environmental data and dynamically adjusts the output of the temperature sensor through a physical model. For moisture correction, for the error of the moisture sensor, the correction algorithm uses moisture compensation rules to adjust the output of the moisture sensor to ensure its consistency with the actual humidity value. As the system operates in the long term, the correction algorithm self-optimizes based on the continuously accumulating historical data. The correction algorithm unit finally outputs the adjusted sensor data and transmits this data to the data acquisition module to replace the original incorrect data. These corrected data provide accurate data support for subsequent data processing, icing risk analysis, and prediction.

[0020] Preferably, the process by which the correction algorithm unit calculates the true temperature value based on the environmental data and dynamically adjusts the output of the temperature sensor includes:

[0021] Obtain the original output data of the temperature sensor from the temperature and humidity sensor and the infrared sensor. This data may be biased due to ice and snow accumulation or frost. At the same time, collect the surrounding environmental parameter data, including air temperature, humidity, and wind speed, as the reference basis for temperature correction. Filter, smooth, and denoise the collected environmental data and temperature sensor data to remove noise and ensure the stability and reliability of the data. Integrate the temperature data collected by each sensor with the environmental parameter data to form a complete environmental data set for subsequent processing;

[0022] Apply a physical model to calculate the true temperature. Select a physical model suitable for temperature correction, such as a mathematical model based on heat conduction or temperature decay, and determine the key parameters in the model. The key parameters include the ice and snow accumulation influence coefficient and the environmental temperature compensation coefficient. Use the integrated environmental data, that is, the environmental data set as the input, and calculate the true temperature value that the temperature sensor might have been before being affected by ice and snow and frost factors according to the physical model. The model automatically calculates the correction factor by comparing the environmental temperature with the sensor reading, and obtains the true temperature value based on the correction factor;

[0023] According to the difference between the calculated true temperature value and the original data of the temperature sensor, calculate the required dynamic adjustment amount. Using the preset adjustment rules, through linear or non-linear mapping, dynamically adjust the output of the temperature sensor, and update the original data to the corrected true temperature value. The adjustment process is continuously executed in the real-time data stream to ensure that when the environment changes (including sudden temperature drops, ice and snow accumulation changes), the sensor output can continuously reflect the corrected temperature information. Feed the temperature data (true temperature value) corrected by the physical model back to the data acquisition module to replace the originally error-prone data for subsequent data processing and icing risk prediction. Store the data before and after correction, correction factors, and model parameter information in the database for long-term optimization and further correction of the model.

[0024] Preferably, the process of the correction algorithm unit calculating the true temperature value based on the environmental data and dynamically adjusting the output of the temperature sensor through the physical model includes: The correction algorithm unit first receives the feedback data of the humidity sensor from the sensor error detection unit. The feedback data includes the deviation information between the output of the humidity sensor and the preset standard humidity value. The deviation information involves the specific values and their fluctuation ranges of the data being too high or too low. Analyze the feedback data to determine whether the abnormal output of the humidity sensor is caused by external environmental humidity factors (such as high humidity environment, rainfall, dew or condensation). This process is determined by comparing the sensor data with the factory calibration value of the device, historical data or external environmental standard humidity data. Synchronously collect the environmental parameter data related to humidity measurement. The environmental parameter data includes air temperature and air pressure, and filter, smooth and integrate these data to form a complete environmental data set, providing a necessary reference for subsequent humidity compensation. According to the preset humidity compensation rules, use the integrated environmental data to calculate the compensation factor for the humidity sensor data. The compensation rules consider the influence of environmental temperature and air pressure factors on the humidity sensor readings, and determine the compensation coefficient through a linear or non-linear mapping relationship, so as to estimate the deviation of the humidity sensor caused by humidity influence. Use the calculated compensation factor to dynamically correct the original humidity data, and the adjusted data can more accurately reflect the actual environmental humidity.

[0025] Preferably, the prediction module uses multiple regression analysis and time series prediction algorithms to predict the possibility of road icing by analyzing historical data and real-time collected data, and generates an icing warning report. The process includes: extracting historical environmental data, sensor data, and previous road icing records from the database to form the basis for model training, obtaining real-time temperature, humidity, infrared sensor data, and meteorological parameters (including wind speed, air pressure, and precipitation) after self-calibration processing through the data acquisition module, performing missing value processing, filtering, smoothing, and normalization on historical and real-time data to ensure data consistency and comparability, using a multiple regression model (linear or non-linear), with various environmental parameters and sensor data as independent variables and the road icing state or icing degree as the dependent variable, establishing a prediction model, training the model with historical data, determining the regression coefficients of each independent variable, capturing the relationship between each factor and the icing risk, using cross-validation and residual analysis to test the accuracy of the model, adjusting the model structure and parameters if necessary, obtaining the multiple regression analysis result, for the dynamic characteristics of real-time data, using ARIMA and LSTM time series prediction algorithms to analyze the trends, periodic changes, and short-term fluctuations of the data, combining historical data to extract long-term trends, seasonal changes, and the impact of emergencies, providing a time series reference for subsequent predictions, predicting the probability or risk value of road icing within a certain period in the future based on the current data and historical trends, obtaining the time series prediction result, weighting and fusing the multiple regression analysis result and the time series prediction result to form a comprehensive icing risk index, setting a warning threshold based on the comprehensive risk index, dividing the road icing risk into mild, moderate, and severe levels for intuitive judgment, organizing the prediction results, risk grading, and trend analysis information, generating a detailed icing warning report, the content including the current risk assessment, future risk trends, and recommended traffic management measures, visually displaying the prediction data through charts and curves for traffic management personnel to quickly understand the risk situation, and transmitting the warning report to the traffic management department in real time through the user interface module, display screen, or mobile terminal to ensure timely response.

[0026] Preferably, the process of weighting and fusing the multiple regression analysis result and the time series prediction result to form a comprehensive icing risk index is as follows: using historical data and real-time environmental data, establishing the relationship between each environmental parameter such as temperature, humidity, wind speed, and air pressure and the road icing risk through a multiple regression model, and generating the multiple regression prediction result R reg , which reflects the icing risk level under the current environmental conditions. Using time series prediction algorithms, ARIMA and LSTM, to model the time dynamic changes of real-time data and obtaining the time series prediction result R time , which reflects the trend change of the icing risk in a future period. To ensure the consistency of the numerical ranges of the outputs of different models, for R reg and R timeNormalization is performed separately to map the data to the range of 0 to 1 for subsequent weighted fusion calculations. According to the prediction accuracy of each model in historical data and real-time environmental feedback, the relative performance of the multiple regression model and the time series prediction model is evaluated to determine the weighting coefficients α and β, where α + β = 1. The prediction results of the two models are combined according to the weighting coefficients to obtain a unified index that can reflect the current and future road icing risks: the comprehensive icing risk index;

[0027] According to the comprehensive icing risk index R total In the numerical range of, the risk level division standard is preset, 0 ≤ R total <T1: Low icing risk, T1 ≤ R total <T2: Moderate icing risk, R total ≥ T2: High icing risk. The thresholds T1 and T2 are adjusted according to historical data statistics and actual application requirements to ensure accurate and effective risk classification. According to the comprehensive risk index R total and its corresponding risk level, a detailed icing warning report is generated. The report content includes current risk assessment, future trend prediction, impact analysis of each environmental factor, and recommended traffic management measures. Through the user interface module, the warning report is timely conveyed to the traffic management department in an intuitive form such as charts and curves;

[0028] Among them, T1: The demarcation threshold between low icing risk and moderate icing risk, T2: The demarcation threshold between moderate icing risk and high icing risk.

[0029] Preferably, the data processing module includes the following steps:

[0030] S1: Compare the temperature, humidity, and infrared sensor data collected in real time with the preset standard temperature, humidity, and infrared data. By comparing, determine whether there is an icing risk on the road surface and preliminarily classify it into low icing, moderate icing, or high icing levels;

[0031] S2: Evaluate the moderately icy sections according to the meteorological data collected in real time, and combine the historical icing data to correct the preliminary classification results. Among them, the meteorological data includes wind speed and air pressure;

[0032] S3: Finally confirm the icing levels of all sections, generate an icing risk assessment report, and feedback it to the traffic management personnel through the user interface module.

[0033] Preferably, when the data processing module corrects the moderately icy sections, real-time traffic data such as vehicle detour rate and vehicle deceleration gradient are used to perform secondary correction on the icing levels, and the corrected results can more accurately reflect the actual situation of road icing;

[0034] When the data processing module corrects moderately frozen road sections, the process of secondary correction of the icing level using real-time traffic data such as vehicle detour rate and vehicle deceleration gradient is as follows:

[0035] The data processing module first compares the data from temperature, humidity, and infrared sensors with preset standards, and preliminarily classifies the icing risks of each road section into mild, moderate, and severe; for road sections initially determined to be "moderately frozen", it is considered that there is a need for further refined evaluation in these areas to more accurately reflect the actual road surface conditions;

[0036] Through cameras or vehicle detection devices installed on the road surface, the proportion of vehicles choosing to detour when passing through this road section is monitored in real time; this data reflects the intuitive reaction of drivers to the road icing condition; using high-speed cameras or sensor systems, the deceleration of vehicles when passing through this road section is recorded in real time (such as the average acceleration of vehicle deceleration) to reflect the impact of road anomalies on driving behavior;

[0037] The system presets standard vehicle detour rates and standard vehicle deceleration gradient values, and these standard values can be determined based on historical data, actual measurements and statistics, or relevant traffic safety specifications; the data processing module compares the real-time collected vehicle detour rate and deceleration gradient with the corresponding standard values respectively: if the actual vehicle detour rate is significantly higher than the standard value, it indicates that drivers on this road section generally take detour measures due to icing, suggesting that the risk may be higher than the preliminary assessment; if the vehicle deceleration gradient increases significantly, it indicates that vehicles need to decelerate sharply on this road section, further corroborating that the road icing degree may be relatively high, and obtaining the comparison result; according to the comparison result, the system performs secondary correction on the initial moderately frozen level through a preset correction formula; when the calculation result shows that the comprehensive risk index increases, the system adjusts the moderately risky road section to a severe icing risk; conversely, if the risk index decreases, it may be adjusted to a mild icing risk; after secondary correction, the data processing module generates the final comprehensive icing risk index, which fully reflects the correlation between road icing conditions and real-time traffic reactions; according to the comprehensive icing risk index, the system further classifies the road section risks and updates the icing warning report to ensure that traffic management personnel obtain accurate risk assessment information.

[0038] (III) Beneficial effects

[0039] The present invention provides a highway pavement icing monitoring system. It has the following beneficial effects:

[0040] The ice condensation monitoring system for highway pavements improves the working stability of the system in bad weather and can detect the risk of road icing earlier by adding a self - calibration function to the monitoring equipment, especially when detecting the influence of humidity and temperature in environmental factors on the performance of sensors, introducing intelligent algorithms to enable the monitoring system to automatically correct measurement errors caused by external environmental changes in real - time, and combining machine - learning models to make more accurate predictions of pavement conditions. This can provide more accurate early warning information for traffic management departments and reduce the probability of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic framework diagram of an ice condensation monitoring system for highway pavements according to the present invention;

[0042] Figure 2 It is a schematic flow diagram of the prediction module according to the present invention;

[0043] Figure 3 It is a schematic flow diagram of the data processing module and the secondary correction of the data processing module according to the present invention;

[0044] Figure 4 It is a schematic flow diagram of the self - calibration module and the correction algorithm unit according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] Please refer to Figures 1 to 4 , the present invention provides a technical solution: an ice condensation monitoring system for highway pavements, including:

[0047] A data acquisition module that collects environmental data and road icing status information on the highway pavement;

[0048] A self - calibration module, connected to the data acquisition module, which self - calibrates the data acquisition module according to the real - time collected environmental data and road icing status information, and corrects the sensor errors caused by external environmental factors. The external environmental factors include ice and snow accumulation and moisture;

[0049] A data processing module, connected to the self-calibration module, processes the collected data, analyzes and predicts the road icing situation based on the calibrated data; it also classifies the road icing degree through standard comparison. The levels include light icing, moderate icing, and heavy icing, and it compares the actual situation of data collection with the preset standard data to determine the icing risk level of the current road section;

[0050] A prediction module, connected to the data processing module, predicts the road icing situation based on the real-time calibrated data through machine learning algorithms and generates an icing risk assessment report;

[0051] A user interface module provides real-time data of icing risk information, weather warnings, and road condition monitoring to traffic management personnel through a display screen or a mobile device, presenting the road icing prediction results and risk assessment information to users, facilitating real-time decision-making by traffic management personnel and real-time adjustment of traffic control measures;

[0052] Among them, the prediction module adopts multiple regression analysis and time series prediction algorithms. By analyzing historical data and real-time collected data, it quantitatively predicts the possibility of road icing and generates an icing warning report;

[0053] When the data processing module corrects the moderately-iced road sections, it uses real-time traffic data such as vehicle detour rate and vehicle deceleration gradient to perform secondary correction on the icing level, and the corrected result more accurately reflects the actual situation of road icing.

[0054] The data acquisition module includes a high-precision temperature and humidity sensor, an infrared sensor, a meteorological sensor, and a heating device. The heating device is used to prevent the sensors from being affected by ice, snow, or moisture under adverse weather conditions, ensuring the long-term stable operation of the sensors. The data acquisition module is installed on both sides of the highway pavement, along the street lamp crossbeam, or on the bridge, ensuring that the sensors can cover key areas on the road surface and minimizing external environmental interference to obtain real-time road surface environment data, including: regularly collecting the temperature and humidity data of the current air by the temperature and humidity sensor. Especially in cold weather and environments with large humidity changes, these data are crucial for judging whether there is a potential risk of road icing. Especially when the temperature is close to the freezing point, the humidity change also affects the icing situation of the road surface. The infrared sensor collects the road surface temperature in real time. When the road surface temperature drops below the freezing point, the infrared sensor can detect obvious temperature difference changes, thus providing important icing state information. The infrared sensor is installed on the road surface or at a slightly higher position to ensure comprehensive monitoring of the road surface state and real-time perception of road surface temperature changes. Especially when icing occurs, the infrared sensor can identify whether the road surface has iced. The meteorological sensor obtains the current meteorological data, including wind speed, air pressure, and precipitation. These data help predict meteorological conditions that may cause icing, including cold snaps, snowfall, or moisture. The data acquisition module also continuously monitors the road surface temperature through the infrared sensor, monitors the road icing state, and obtains road icing state information.

[0055] The self-calibration module includes:

[0056] The sensor error detection unit is responsible for real-time monitoring of the deviation between the data output by the data acquisition module and the preset standard value, and real-time detection of sensor output deviations caused by external environmental factors, including ice and snow accumulation, moisture, and temperature changes. The process includes: obtaining real-time data from each sensor from the data acquisition module, including temperature, humidity, and infrared reflectivity information, comparing the real-time collected sensor data with the preset standard data. The preset standard value is derived from the factory calibration value of the device, historical data, or external environmental standard data, including normal humidity and temperature ranges. If the sensor output data deviates from the predetermined standard, the system will mark the data as abnormal. When the sensor output data exceeds the allowable error range, the error detection unit will alarm in real time and record the abnormal data to form feedback information for subsequent correction and modification;

[0057] Correction algorithm unit, based on the feedback information provided by the sensor error detection unit, automatically adjusts the readings of sensor data, eliminates errors caused by environmental changes, ensures the accuracy of sensor data, and the correction algorithm adjusts the sensor output data according to historical data, current environmental data, and known calibration standards; the process includes: receiving the feedback from the sensor error detection unit, analyzing the error sources, and the error sources include ice and snow accumulation and moisture influence. According to the preset correction algorithm, the sensor errors are adjusted according to the temperature correction and moisture compensation rules based on the physical model, and the data is dynamically corrected to make it more in line with the actual road surface conditions. Among them, the preset correction algorithm is based on linear regression, Kalman filtering, or machine learning models. Among them, for ice and snow accumulation correction, if the temperature sensor data is low due to ice and snow accumulation, the correction algorithm calculates the actual temperature value through the temperature change model and makes adjustments; for moisture correction, the moisture affects the accuracy of the moisture sensor, and the correction algorithm combines the actual environmental humidity data and the standard humidity data to correct the sensor error; the corrected data is transmitted to the data acquisition module to replace the incorrect data value;

[0058] Feedback mechanism unit, dynamically adjusts the working parameters of the data acquisition module according to the corrected data to ensure that the entire system can maintain a high-precision working state. This mechanism can automatically adjust the working mode of the acquisition module, including the acquisition frequency and sensor calibration coefficient, to adapt to the changes in the external environment; the process includes: after correcting the data, the feedback mechanism unit adjusts the parameters of the data acquisition module according to the corrected information, including increasing the acquisition frequency of the sensor in snowy weather to better capture the subtle changes in road icing; in an environment with heavy moisture, adjusting the sensitivity of the moisture sensor. When the external environment changes, including sudden temperature drops and heavy snowfall, the feedback mechanism will adjust the parameters of the data acquisition module in real time by automatically adjusting the calibration coefficient or acquisition method to ensure that the system can work continuously and stably. The feedback mechanism enables the data acquisition module to cope with the continuous changes in the external environment by automatically adjusting the calibration coefficient or acquisition method; as the system runs for a long time, the feedback mechanism unit also continuously optimizes the adjustment strategy through the accumulation of historical data. Based on the long-term calibration data, the feedback mechanism can self-optimize the data acquisition module to further improve the monitoring accuracy;

[0059] The working process of the entire self-calibration module includes: the sensor error detection unit discovers the errors caused by external environmental changes in a timely manner by comparing real-time data with standard values; the correction algorithm unit automatically adjusts the sensor data using physical models or algorithms according to the error feedback to eliminate the errors caused by ice and snow accumulation and moisture in environmental factors; the feedback mechanism unit adjusts the working parameters of the data acquisition module in real time according to the corrected data to ensure the long-term stability and accuracy of the system. Through this mechanism, the self-calibration module can ensure that the highway pavement icing monitoring system maintains high precision under various environmental conditions and provides timely and accurate pavement icing risk assessments.

[0060] The correction algorithm unit analyzes the source of the error. According to the preset correction algorithm, the process of dynamically correcting the data includes: receiving feedback information from the sensor error detection unit, the feedback content includes the deviation between the sensor output data and the preset standard data, specifically including the deviation amplitude and error type of the data. The error type includes temperature deviation and moisture deviation. The feedback information is the basis for subsequent error analysis. The correction algorithm unit performs a preliminary analysis on the received feedback data to identify the source of the error. For temperature error analysis, by checking the output value of the temperature sensor, it is determined whether the temperature sensor error is caused by the external environment. The external environment includes ice and snow accumulation and sudden drop in temperature. For example, if the output value of the temperature sensor is significantly lower than the actual temperature, it may be an error caused by ice and snow accumulation. For moisture error analysis, the output value of the moisture sensor is checked to analyze whether the error is caused by changes in environmental humidity or precipitation. For example, in humid weather, moisture may affect the accuracy of the moisture sensor. The error source is analyzed through a physical model to obtain an analysis result. The correction algorithm unit applies the physical model to deeply analyze the error source. Based on the physical model, a temperature error analysis is performed. When the temperature sensor When the sensor data is low, it may be due to the error caused by ice and snow accumulation or frost. The correction algorithm applies the physical principles of the temperature change model and the heat conduction model, combined with environmental factors, to calculate the actual temperature value, and compares it with the output of the sensor to confirm the source of the error. Among them, environmental factors include air temperature, humidity, and wind speed. Based on the moisture compensation rule, the moisture error analysis is performed. The error of the moisture sensor is usually caused by excessive humidity or meteorological changes. The correction algorithm compares the current ambient humidity with the sensor output value through the moisture compensation model to determine whether the moisture sensor is affected by moisture changes and makes appropriate corrections; the correction algorithm confirms the error source based on the analysis results. Temperature error confirmation: The correction algorithm confirms whether ice and snow accumulation or frost is the main source of temperature sensor error through the temperature model. If it is determined that the error is caused by ice and snow accumulation, the correction algorithm will generate a correction strategy to adjust the sensor data. Among them, the temperature model includes a temperature change model and a heat conduction model. Moisture error confirmation: Through the moisture compensation model, the correction algorithm confirms whether moisture changes have caused errors to the moisture sensor. If it is determined to be a moisture error, the correction algorithm will make corrections based on the actual environmental data and compensation rules.

[0061] Once the error sources are identified, the correction algorithm unit formulates specific correction strategies and dynamically adjusts the sensor data for temperature correction. If the error is due to ice and snow accumulation or frost, the correction algorithm calculates the true temperature value based on the environmental data and dynamically adjusts the output of the temperature sensor through a physical model. For moisture correction, for the error of the moisture sensor, the correction algorithm uses the moisture compensation rule to adjust the output of the moisture sensor to ensure its consistency with the actual humidity value. As the system operates over a long period, the correction algorithm self-optimizes based on the continuously accumulating historical data. Through the long-term historical data, the error analysis and correction strategies are continuously optimized, enabling the system to adapt to changes under different environmental conditions and providing a more accurate correction algorithm. The optimized correction strategy is fed back to the data acquisition module to further improve the system's operational stability and data accuracy. The correction algorithm unit finally outputs the adjusted sensor data and transfers this data to the data acquisition module to replace the original incorrect data. These corrected data provide accurate data support for subsequent data processing, icing risk analysis, and prediction.

[0062] The process by which the correction algorithm unit calculates the true temperature value based on the environmental data and dynamically adjusts the output of the temperature sensor includes:

[0063] Obtain the original output data of the temperature sensor from the temperature and humidity sensor and the infrared sensor. This data may be biased due to ice and snow accumulation or frost. At the same time, collect the surrounding environmental parameter data, including air temperature, humidity, and wind speed, as the reference basis for temperature correction. Filter, smooth, and denoise the collected environmental data and temperature sensor data to remove noise and ensure the stability and reliability of the data. Integrate the temperature data collected by each sensor with the environmental parameter data to form a complete environmental data set for subsequent processing;

[0064] Apply a physical model to calculate the true temperature. Select a mathematical model based on heat conduction or temperature decay and determine the key parameters in the model. The key parameters include the ice and snow accumulation influence coefficient and the environmental temperature compensation coefficient. Use the integrated environmental data, that is, the environmental data set as the input, and calculate the true temperature value that the temperature sensor might have before being affected by ice and snow and frost factors according to the physical model. The model automatically calculates the correction factor by comparing the environmental temperature with the sensor reading, and obtains the true temperature value based on the correction factor;

[0065] Based on the difference between the calculated true temperature value and the original data of the temperature sensor, calculate the required dynamic adjustment amount. Using the preset adjustment rules, through linear or non-linear mapping, dynamically adjust the output of the temperature sensor, and update the original data to the corrected true temperature value. The adjustment process is continuously executed in the real-time data stream to ensure that when the environment changes (where the environmental changes include sudden temperature drops, ice and snow accumulation changes), the sensor output can continuously reflect the corrected temperature information. Feed the true temperature value corrected by the physical model back to the data acquisition module to replace the originally error-prone data for subsequent data processing and icing risk prediction. Store the data before and after correction, correction factors, and model parameter information in the database for long-term optimization and further correction of the model.

[0066] The process by which the correction algorithm unit calculates the true temperature value based on the environmental data and dynamically adjusts the output of the temperature sensor through the physical model includes: The correction algorithm unit first receives the feedback data of the humidity sensor from the sensor error detection unit. This feedback data includes the deviation information between the output of the humidity sensor and the preset standard humidity value. The deviation information involves the specific values of the data being too high or too low and their fluctuation ranges. Analyze the feedback data to determine whether the abnormal output of the humidity sensor is caused by high humidity environment, rainfall, dew or condensation phenomena among the external environmental humidity factors. This process is determined by comparing the sensor data with the factory calibration value of the device, historical data or external environmental standard humidity data. Synchronously collect the environmental parameter data related to humidity measurement. The environmental parameter data includes air temperature, air pressure, and filter, smooth and integrate these data to form a complete environmental data set, providing a necessary reference for subsequent humidity compensation. According to the preset humidity compensation rules, use the integrated environmental data to calculate the compensation factor for the humidity sensor data. The compensation rules consider the influence of environmental temperature and air pressure factors on the humidity sensor readings, and determine the compensation coefficient through a linear or non-linear mapping relationship, thereby estimating the deviation of the humidity sensor caused by humidity influence. Use the calculated compensation factor to dynamically correct the original humidity data. The adjusted data can more accurately reflect the actual environmental humidity. The correction process is executed in real time to ensure that when the humidity conditions change, the output of the humidity sensor can be updated immediately to keep consistent with the actual humidity. Feed the humidity data corrected by the humidity compensation rules back to the data acquisition module, and store the data before and after correction, compensation factors, and environmental parameter information for continuous optimization and adjustment of the humidity compensation rules and correction algorithms in the future.

[0067] The prediction module uses multiple regression analysis and time series prediction algorithms to predict the likelihood of road icing by analyzing historical data and real-time collected data, and generates icing warning reports. The process includes: extracting historical environmental data, sensor data, and previous road icing records from the database to form the basis for model training. Obtaining real-time temperature, humidity, infrared sensor data, and meteorological parameters, including wind speed, air pressure, and precipitation, after self-calibration processing through the data collection module. Conducting missing value processing, filtering, smoothing, and normalization on historical and real-time data to ensure data consistency and comparability. Using a multiple non-linear regression model, with various environmental parameters and sensor data as independent variables and the road icing state or degree of icing as the dependent variable, to establish a prediction model. Training the model with historical data to determine the regression coefficients of each independent variable and capture the relationship between various factors and icing risks. Using cross-validation and residual analysis to test the accuracy of the model, and adjusting the model structure and parameters if necessary to obtain the results of multiple regression analysis. For the dynamic characteristics of real-time data, using ARIMA and LSTM time series prediction algorithms to analyze the trends, periodic changes, and short-term fluctuations of the data, combining historical data to extract long-term trends, seasonal changes, and the impacts of emergencies, providing a time series reference for subsequent predictions. Based on the current data and historical trends, predicting the probability or risk value of road icing within a certain period in the future to obtain the time series prediction results. Weightedly fusing the results of multiple regression analysis and time series prediction results to form a comprehensive icing risk index. Setting warning thresholds based on the comprehensive risk index and classifying the road icing risks into mild, moderate, and severe levels for intuitive judgment. Organizing the prediction results, risk classification, and trend analysis information to generate a detailed icing warning report, which includes the current risk assessment, future risk trends, and recommended traffic management measures. Intuitively displaying the prediction data through charts and curves to facilitate traffic management personnel to quickly understand the risk situation. Transmitting the warning report to the traffic management department in real-time through the user interface module, display screen, or mobile terminal to ensure timely response. Recording the prediction results, actual road conditions, and environmental parameters in real-time to form a new historical data set, and regularly retraining and adjusting the parameters of the multiple regression model and time series prediction model using the latest data to continuously optimize the prediction accuracy and response speed.

[0068] The process of weightedly fusing the results of multiple regression analysis and time series prediction results to form a comprehensive icing risk index is as follows: Using historical data and real-time environmental data, establishing the relationship between various environmental parameters such as temperature, humidity, wind speed, and air pressure and road icing risks through a multiple regression model to generate the multiple regression prediction result R reg , which reflects the icing risk level under the current environmental conditions. Using the time series prediction algorithm ARIMA to model the time dynamic changes of real-time data to obtain the time series prediction result R time, reflecting the trend change of the icing risk in a future period. To ensure the consistency of the numerical ranges of different model outputs, R reg and R time are normalized respectively, mapping the data to the interval from 0 to 1 for subsequent weighted fusion calculation. According to the prediction accuracy of each model in historical data and real-time environmental feedback, the relative performance of the multiple regression model and the time series prediction model is evaluated to determine the weighting coefficients α and β, where α + β = 1, which is a fixed weight. An adaptive weight strategy can also be adopted: under certain climate conditions, if the multiple regression prediction shows more stability, α can be set larger; otherwise, the proportion of β is increased. The comprehensive icing risk index R total is calculated using the following fusion formula:

[0069] ;

[0070] This formula synthesizes the prediction results of the two models according to the weighting coefficients to obtain a unified index that can reflect the current and future road icing risks: the comprehensive icing risk index;

[0071] According to the numerical range of the comprehensive icing risk index R total , the risk level division criteria are preset. 0 ≤ R total < T1: low icing risk, T1 ≤ R total < T2: medium icing risk, R total ≥ T2: high icing risk. The thresholds T1 and T2 are adjusted according to historical data statistics and actual application requirements to ensure the accuracy and effectiveness of risk classification. According to the comprehensive risk index R total and its corresponding risk level, a detailed icing warning report is generated. The report content includes the current risk assessment, future trend prediction, impact analysis of each environmental factor, and recommended traffic management measures. Through the user interface module, the warning report is timely conveyed to the traffic management department in an intuitive form of charts and curves; where T1: the demarcation threshold between low icing risk and medium icing risk, T2: the demarcation threshold between medium icing risk and high icing risk. During the operation of the system, the prediction results and the actual road conditions are continuously recorded to form new historical data. These data are used to retrain the multiple regression and time series prediction models regularly, and at the same time, the weighting coefficients are dynamically adjusted to ensure the continuous improvement of the accuracy and adaptability of the comprehensive prediction and achieve the self-optimization of the model;

[0072] Through the above process, the results of multiple regression analysis and time series prediction are effectively weighted and fused to form a comprehensive icing risk index, providing accurate and timely risk assessment data for highway road icing monitoring and warning;

[0073] The data processing module includes a data preprocessing unit, which is used to filter, smooth, and denoise the collected raw data to ensure data quality for subsequent analysis and prediction.

[0074] The data processing module includes the following steps:

[0075] S1: Compare the temperature, humidity, and infrared sensor data collected in real time with the preset standard temperature and humidity data and infrared data. Determine whether there is an ice formation risk on the road surface through the comparison, and preliminarily classify it into mild ice formation, moderate ice formation, or severe ice formation levels;

[0076] S2: Evaluate the moderately ice-covered sections based on the meteorological data collected in real time, and combine with historical ice formation data to correct the preliminary classification results. Among them, the meteorological data includes wind speed and air pressure;

[0077] S3: Finally confirm the ice formation levels of all sections, generate an ice formation risk assessment report, and feedback it to traffic management personnel through the user interface module.

[0078] It should be further noted that in the specific implementation process, when the data processing module corrects the moderately ice-covered sections, the process of using the real-time traffic data of vehicle detour rate and vehicle deceleration gradient to perform secondary correction on the ice formation level is as follows: The data processing module first compares the data of temperature, humidity, and infrared sensors with the preset standards, and preliminarily classifies the ice formation risks of each section into mild, moderate, and severe; for the sections initially determined to be "moderately ice-covered", it is considered that these areas need further refined evaluation to more accurately reflect the actual road surface conditions; through cameras or vehicle detection devices installed on the road surface, the proportion of vehicles choosing to detour when passing through this section is monitored in real time; this data reflects the intuitive reaction of drivers to the ice formation condition on the road surface; using a high-speed camera or sensor system, the deceleration situation of vehicles when passing through this section is recorded in real time, including the average acceleration of vehicle deceleration, to reflect the impact of road surface anomalies on driving behavior; the system presets standard vehicle detour rate and standard vehicle deceleration gradient values, and these standard values can be determined based on historical data, field measurements, or relevant traffic safety specifications; the data processing module compares the real-time collected vehicle detour rate and deceleration gradient with the corresponding standard values respectively: if the actual vehicle detour rate is significantly higher than the standard value, it indicates that drivers on this section generally take detour measures due to ice formation, suggesting that the risk may be higher than the preliminary assessment; if the vehicle deceleration gradient increases significantly, it indicates that vehicles need to decelerate sharply on this section, further corroborating that the ice formation degree on the road surface may be relatively high, and obtaining the comparison result; according to the comparison result, the system performs secondary correction on the initially determined moderate ice formation level through a preset correction formula; the following correction formula is used:

[0079] ;

[0080] where Rinitial is the initially divided icing risk level; W real and D real are the real-time vehicle detour rate and vehicle deceleration gradient respectively; W standard and D standard are preset standard values; k1 and k2 are correction factors, which are set according to the actual situation;

[0081] When the calculation result shows that the comprehensive risk index increases, the system adjusts the medium-risk section to a severe icing risk; conversely, if the risk index decreases, it may be adjusted to a mild icing risk; after secondary correction, the data processing module generates the final comprehensive icing risk index, which fully reflects the correlation between the road icing situation and the real-time traffic response; according to the comprehensive icing risk index, the system further classifies the section risk and updates the icing warning report to ensure that traffic management personnel obtain accurate risk assessment information; the corrected icing risk level is fed back to the user interface module through the data interaction module and is displayed in real time on the monitoring terminal or mobile device; the system also records all secondary correction data and relevant traffic data to provide a basis for subsequent long-term analysis and model optimization, thereby continuously improving the prediction accuracy and risk assessment accuracy; through the above process, the data processing module uses real-time traffic data such as vehicle detour rate and vehicle deceleration gradient to perform secondary correction on the sections initially determined to be moderately icy, ensuring that the icing risk level more accurately reflects the actual road surface conditions and providing more accurate warning information for the traffic management department;

[0082] Through steps S1 to S3, the system not only makes a preliminary division based on real-time data and standard data, but also can be corrected and calibrated according to further environmental factors, and finally obtains an accurate icing level; by comparing the actual data with the preset standard data, the system can divide the road icing situation into three levels: mild, moderate, and severe icing; this comparison method enables the monitoring system to dynamically evaluate the icing risk and ensure that the icing situation of each section can be accurately reflected; through this detailed technical description, combined with the standard comparison and correction steps, the accuracy and reliability of the highway pavement icing monitoring can be effectively improved.

[0083] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0084] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An ice condensation monitoring system for highway pavement, characterized in that, Including: A data acquisition module that collects environmental data and road surface icing status information on highway road surfaces; A self-calibration module, connected to the data acquisition module, which self-calibrates the data acquisition module according to the real-time collected environmental data and road surface icing status information, and corrects the sensor errors caused by external environmental factors; A data processing module, connected to the self-calibration module, processes the collected data, analyzes and predicts the road surface icing situation based on the corrected data; also classifies the road surface icing degree through standard comparison. The grades include light icing, moderate icing and heavy icing, and based on the actual situation of data collection and comparison with preset standard data, determines the icing risk level of the current section; A prediction module, connected to the data processing module, predicts the road surface icing situation through machine learning algorithms based on the real-time corrected data, and generates an icing risk assessment report; A user interface module that provides real-time data of icing risk information, weather warnings, and road condition monitoring to traffic management personnel through a display screen or a mobile device, for presenting the road surface icing prediction results and risk assessment information to users; Among them, the prediction module adopts multiple regression analysis and time series prediction algorithms, predicts the possibility of road surface icing by analyzing historical data and real-time collected data, and generates an icing warning report.

2. The ice condensation monitoring system for highway pavement according to claim 1, wherein: The data acquisition module includes a temperature and humidity sensor, an infrared sensor, a meteorological sensor, and a heating device; The data acquisition module is installed on both sides of the highway road surface or along the street lamp crossbeam and bridge, and obtains the road surface environmental data in real time, including: the temperature and humidity data of the current air collected by the temperature and humidity sensor, the road surface surface temperature collected by the infrared sensor, and the meteorological sensor obtains the current meteorological data, including wind speed, air pressure, precipitation. The data acquisition module also continuously monitors the road surface temperature through the infrared sensor, monitors the road surface icing status, and obtains the road surface icing status information.

3. The ice condensation monitoring system for highway pavement according to claim 2, characterized in that: The self-calibration module includes: A sensor error detection unit, responsible for monitoring the deviation between the data output by the data acquisition module and the preset standard value in real time, obtaining the real-time data from each sensor from the data acquisition module, comparing the real-time data with the preset standard data, and if the sensor output data deviates from the predetermined standard, marking the data as abnormal, giving a real-time alarm and recording the abnormal data to form feedback information; A correction algorithm unit, based on the feedback information provided by the sensor error detection unit, automatically adjusts the readings of the sensor data to eliminate the errors caused by environmental changes; the process includes: receiving the feedback of the sensor error detection unit, analyzing the error source, and according to the preset correction algorithm, adjusting the sensor error according to the temperature correction and moisture compensation rules based on the physical model to correct the data; A feedback mechanism unit, dynamically adjusts the working parameters of the data acquisition module according to the corrected data. After correcting the data, adjusts the parameters of the data acquisition module according to the corrected information. When the external environment changes, adjusts the parameters of the data acquisition module in real time by automatically adjusting the calibration coefficient or the acquisition method.

4. The ice formation monitoring system for highway pavement according to claim 3, wherein: The process of the correction algorithm unit analyzing the error source and dynamically correcting data according to a preset correction algorithm includes: receiving feedback information, performing preliminary analysis, identifying the error source, by checking the output value of the temperature sensor to determine whether there is an error in the temperature sensor caused by the external environment, checking the output value of the humidity sensor to analyze whether there is an error caused by environmental humidity changes or precipitation, analyzing the error source through a physical model to obtain an analysis result. When the temperature sensor data is low, the correction algorithm applies a temperature change model and a heat conduction model, combines environmental factors, calculates the actual temperature value, and compares it with the output of the sensor to confirm the error source. The correction algorithm uses a humidity compensation model to compare the current environmental humidity with the sensor output value to determine whether the humidity sensor is affected by humidity changes and makes corrections; the correction algorithm confirms the error source according to the analysis result, and through the temperature model, determines whether ice and snow accumulation or frost is the main source of the temperature sensor error. If it is determined that the error is caused by ice and snow accumulation, the correction algorithm generates a correction strategy to adjust the sensor data. Through the humidity compensation model, the correction algorithm confirms whether humidity changes have caused an error in the humidity sensor. If it is determined to be a humidity error, the correction algorithm corrects it according to the actual environmental data and compensation rules; If the error is caused by ice and snow accumulation or frost, calculate the true temperature value based on environmental data, and dynamically adjust the output of the temperature sensor through a physical model. For the error of the humidity sensor, use the humidity compensation rule to adjust the output of the humidity sensor to ensure consistency with the actual humidity value, and output the adjusted sensor data, which is transmitted to the data acquisition module to replace the original incorrect data.

5. The ice condensation monitoring system for highway pavement according to claim 4, characterized in that: The process of the correction algorithm unit calculating the true temperature value based on environmental data and dynamically adjusting the output of the temperature sensor includes: Obtain the original output data of the temperature sensor from the temperature and humidity sensor and the infrared sensor. At the same time, collect the surrounding environmental parameter data, filter, smooth and denoise the collected environmental data and temperature sensor data, remove the noise, and integrate the temperature data collected by each sensor with the environmental parameter data to form an environmental data set; Select a physical model suitable for temperature correction, determine the key parameters in the model based on the mathematical model of heat conduction or temperature decay, use the environmental data set as the input, calculate the true temperature value of the temperature sensor before being actually affected by ice and snow and frost factors according to the physical model, calculate the correction factor by comparing the environmental temperature with the sensor reading, and obtain the true temperature value based on the correction factor; Calculate the dynamic adjustment amount according to the difference between the true temperature value and the original data of the temperature sensor, use the preset adjustment rule to dynamically adjust the output of the temperature sensor, update the original data to the corrected true temperature value, and feedback the temperature data corrected by the physical model to the data acquisition module to replace the original data with errors.

6. The ice condensation monitoring system for highway pavement according to claim 5, wherein: The process by which the correction algorithm unit calculates the true temperature value based on environmental data and dynamically adjusts the output of the temperature sensor through a physical model includes: receiving feedback data from the humidity sensor, analyzing the feedback data, determining whether the abnormal output of the humidity sensor is caused by external environmental humidity factors through comparison with the device factory calibration value, historical data, or external environmental standard humidity data, synchronously collecting environmental parameter data related to humidity measurement, and performing filtering, smoothing, and integration to form an environmental data set. According to the preset humidity compensation rule, using the integrated environmental data, calculating the compensation factor for the humidity sensor data, and determining the compensation coefficient through a linear or non-linear mapping relationship, estimating the deviation caused by humidity in the humidity sensor, and using the compensation factor to correct the original humidity data.

7. The ice condensation monitoring system for highway pavement according to claim 6, characterized in that: The prediction module uses multiple regression analysis and time series prediction algorithms to predict the possibility of road icing by analyzing historical data and real-time collected data, and generates an icing warning report. Extract historical environmental data, sensor data, and previous road icing records from the database to form the basis for model training. Obtain real-time temperature, humidity, infrared sensor data, and meteorological parameters after self-calibration processing through the data acquisition module. Perform missing value processing, filtering, smoothing, and normalization on historical and real-time data. Use a multiple regression model with various environmental parameters and sensor data as independent variables and the road icing state as the dependent variable to establish a prediction model. Use historical data to train the model to determine the regression coefficients of each independent variable, capture the relationship between each factor and the icing risk, and use cross-validation and residual analysis to test the accuracy of the model to obtain the multiple regression analysis result. For the dynamic characteristics of real-time data, use ARIMA and LSTM time series prediction algorithms to analyze the trends, periodic changes, and short-term fluctuations of the data, combine historical data to extract long-term trends, seasonal changes, and the impact of emergencies, and predict the probability or risk value of road icing based on current data and historical trends to obtain the time series prediction result. Weightedly fuse the multiple regression analysis result and the time series prediction result to form a comprehensive icing risk index. Set an early warning threshold based on the comprehensive risk index, divide the road icing risk into mild, moderate, and severe levels, organize the prediction results, risk grading, and trend analysis information, generate a warning report, display the prediction data through charts and curves, and transmit the warning report to the traffic management department through the user interface module.

8. The ice condensation monitoring system for highway pavement according to claim 7, characterized in that: The weighted fusion of the multiple regression analysis results and the time series prediction results forms a comprehensive icing risk index. Using historical data and real-time environmental data, the relationship between temperature, humidity, wind speed, air pressure and road icing risk is established through a multiple regression model to generate the multiple regression prediction result R reg , and a time series prediction algorithm is adopted to model the time dynamic changes of real-time data to obtain the time series prediction result R time , for R reg and R time , normalization processing is carried out respectively. According to the prediction accuracy of each model in historical data and real-time environmental feedback, the relative performance of the multiple regression model and the time series prediction model is evaluated to determine the weighting coefficients α and β, where α + β = 1. The prediction results of the two models are combined according to the weighting coefficients to obtain the comprehensive icing risk index; According to the comprehensive icing risk index R total Within the numerical range, the risk level division criteria are preset. 0 ≤ R total <T1: Low icing risk, T1 ≤ R total <T2: Moderate icing risk, R total ≥ T2: High icing risk. According to the comprehensive risk index R total and its corresponding risk level, an icing warning report is generated and conveyed to the traffic management department in the form of charts and curve graphs through the user interface module; Among them, T1: the demarcation threshold between mild icing risk and moderate icing risk, T2: the demarcation threshold between moderate icing risk and severe icing risk.

9. The ice condensation monitoring system for highway pavement according to claim 8, wherein: The data processing module includes the following steps: S1: Compare the real-time collected temperature, humidity, and infrared sensor data with the preset standard temperature and humidity data and infrared data, judge whether there is an icing risk on the road through the comparison, and initially classify it into mild icing, moderate icing, or severe icing levels. S2: Evaluate moderately frozen road sections based on real-time collected meteorological data, and combine with historical icing data to correct the preliminary classification results. The meteorological data includes wind speed and air pressure; S3: Finally confirm the icing levels of all road sections, generate an icing risk assessment report and feedback it to traffic management personnel through the user interface module.

10. The ice condensation monitoring system for highway pavement according to claim 9, wherein: When the data processing module corrects moderately frozen road sections, it uses real-time traffic data such as vehicle detour rate and vehicle deceleration gradient to perform secondary correction on the icing levels. Compare the data of temperature, humidity, and infrared sensors with preset standards, and preliminarily divide the icing risks of each road section into mild, moderate, and severe; through cameras or vehicle detection devices installed on the road surface, real-time monitor the proportion of vehicles choosing to detour when passing through this road section, and use high-speed cameras or sensor systems to record the deceleration of vehicles in real time when passing through this road section; preset the standard vehicle detour rate and standard vehicle deceleration gradient values, and compare the real-time collected vehicle detour rate and deceleration gradient with the corresponding standard values respectively: if the actual vehicle detour rate is higher than the standard value, it indicates that the risk is higher than the preliminary assessment; if the vehicle deceleration gradient increases significantly and the road surface icing degree is high, obtain the comparison result; perform secondary correction on the preliminary moderate icing level through the correction formula according to the comparison result; when the calculation result shows that the comprehensive risk index increases, adjust the moderate risk road section to a severe icing risk; On the contrary, if the risk index decreases, adjust it to a mild icing risk; After secondary correction, generate a comprehensive icing risk index. According to the comprehensive icing risk index, further classify the road section risks and update the icing warning report.

Images