Safety early warning system for high-risk road section of mountain road

Abstract

The invention discloses a mountain road high-risk road section safety early warning system, which comprises the steps of S1, generating real-time sensing data through a multi-type sensor network; s2, the data acquisition unit is used for receiving the real-time sensing data and transmitting the real-time sensing data to the central processing unit; the central processing unit comprises a processing module and a storage module; s4, the danger evaluation module analyzes the dynamic environment model by using a fuzzy logic control algorithm, identifies a high-risk road section and generates a corresponding early warning signal; s5, the early warning control module outputs corresponding safety early warning information according to the early warning signal; s6, the user interaction interface is used for displaying the early warning signal and the safety early warning information and interacting with the driver in real time; and S7, the network communication module is used for sending the early warning signal and the dynamic environment model to a traffic control department and a nearby road monitoring system through a wireless communication network. The method has the advantages of being high in real-time performance, high in precision and rapid in response.

Description

Technical Field

[0001] The present invention relates to the technical field of safety early warning, and in particular to a safety early warning system for high-risk sections of mountain roads. Background Art

[0002] With the rapid development of the transportation industry, the safety of mountain roads has become an important challenge in traffic management. Mountain roads usually have complex terrain and severe weather conditions, and are prone to natural disasters such as landslides, mountain collapses, and rainstorms, which increase the risk of traffic accidents. Especially in some dangerous sections, drivers cannot obtain accurate road safety information in a timely manner, which can easily lead to traffic accidents and seriously affect driving safety.

[0003] In the existing technology, traditional mountain highway safety warning systems often rely on fixed sensors and predetermined thresholds, and cannot adapt to the ever-changing road and weather environment in real time. These traditional methods have the following obvious defects when facing the complex mountain highway environment: 1. Lack of dynamic adaptability: Traditional safety warning systems are usually based on preset thresholds and rules, which make it difficult to reflect changes in road and weather conditions in real time, and it is impossible to update and adjust warning strategies in a timely manner.

[0004] 2. Inefficient environmental monitoring: Existing safety warning systems mostly rely on a single type of sensor and are unable to fully obtain multi-dimensional data such as road, weather, and road conditions, resulting in one-sided monitoring results and a lack of sufficient accuracy.

[0005] 3. Unable to accurately predict dangerous situations: Existing technologies make it difficult to predict potential dangerous situations through comprehensive analysis of real-time data, especially the inability to identify dynamically changing high-risk road sections, resulting in inaccurate or delayed warning information.

[0006] 4. Lack of a comprehensive safety warning mechanism: Traditional methods usually rely on a single type of alarm information, fail to take corresponding warning measures according to different levels of dangerous situations, and cannot meet the immediate needs of drivers or traffic management personnel.

[0007] Therefore, how to provide a safety warning system for high-risk sections of mountain roads is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0008] One purpose of the present invention is to provide a safety warning system for high-risk sections of mountain roads. By deploying multiple types of sensors and collecting real-time data, the present invention uses fuzzy logic control algorithms and dynamic environmental models to analyze road conditions, accurately identify high-risk sections and predict potential dangerous situations, and has the advantages of strong real-time performance, high accuracy and rapid response.

[0009] According to an embodiment of the present invention, a safety warning system for high-risk sections of mountainous roads includes: S1, a multi-type sensor network, including temperature sensors, humidity sensors, light sensors, air pressure sensors and vibration sensors, which are installed on key sections of mountain roads to generate real-time sensor data; S2, a data acquisition unit, used to receive real-time sensor data and transmit the real-time sensor data to a central processing unit; S3, a central processing unit, including a processing module and a storage module, wherein the processing module is used to construct a dynamic environment model according to real-time sensor data and monitor environmental changes, and the storage module is used to store the dynamic environment model and real-time sensor data; S4, the danger assessment module, uses fuzzy logic control algorithm to analyze the dynamic environment model, identify high-risk sections, predict potential dangerous situations, and generate corresponding warning signals; S5, an early warning control module outputs corresponding safety early warning information according to the early warning signal; S6, user interaction interface, used to display warning signals and safety warning information, and interact with the driver in real time; S7, network communication module, used to send warning signals and dynamic environment models to traffic control departments and nearby road monitoring systems through wireless communication networks.

[0010] Optionally, the S1 specifically includes: S11, temperature sensor, used to detect the temperature data of key sections of mountain roads The temperature sensing range of the temperature sensor is to ; S12, humidity sensor, used to monitor the humidity data of the road surface and surrounding environment in real time , the humidity sensor working range is to Relative humidity; S13, light sensor, used to detect the light intensity of key sections in real time and generate light intensity data The light sensor can sense the range from arrive Light intensity; S14, an air pressure sensor for real-time monitoring of air pressure changes, the air pressure sensor is configured to work at sea level to The air pressure range is 100 meters, which can detect small air pressure changes and output air pressure data. ; S15, vibration sensor, used to sense road vibration or vehicle dynamic behavior in real time, and generate vibration data by detecting small vibration changes in the road surface The frequency range that the vibration sensor can monitor is to ; S16, a data fusion unit, used to receive the temperature data, humidity data, light intensity data, air pressure data and vibration data output by the above sensors, and perform fusion processing on the sensor data to generate real-time sensor data: ;in, represents real-time sensor data, is the temperature data output by the temperature sensor, The humidity data output by the humidity sensor. The light intensity data output by the light sensor. It is the air pressure data output by the air pressure sensor. It is the vibration data output by the vibration sensor.

[0011] Optionally, the S3 specifically includes: S31, a processing module, used to generate a dynamic environment model according to real-time sensor data, the processing module includes a data receiving unit, a data processing unit, a model building unit and a model evaluation unit; S32, a storage module, used for storing dynamic environment models and real-time sensor data; S33、 The model updating unit is used to update the constructed dynamic environment model in real time according to the new real-time sensor data, and the update is performed by comparing the real-time sensor data with the currently constructed dynamic environment model to perform error correction: ;in, is the updated value of the dynamic environment model, is the real-time sensor data currently received, is the current dynamic environment model output, is the change value of the dynamic environment model updated in the previous round, and To adjust the parameters.

[0012] Optionally, the S31 specifically includes: S311, data receiving unit, used to receive real-time sensor data from the data fusion unit , and perform preliminary format analysis and verification; S312, a data processing unit is used to process the received real-time sensor data, wherein the data processing includes signal denoising, data cleaning, data standardization, time and space completion, and data normalization processing to generate processed real-time sensor data ; S313, a model building unit, is used to build a dynamic environment model using a support vector machine algorithm for the processed real-time sensor data: ;in, For a dynamic environment model, is the first data points, is the kernel function used to calculate the data points and the current processed real-time sensor data The similarity between is the weight coefficient of the support vector, is the deviation term, is the number of support vectors; S314, a model evaluation unit, used to evaluate the constructed dynamic environment model and generate a model evaluation error: ;in, is the model evaluation error of the dynamic environment model, is the first data points, The first data points, is the number of data points.

[0013] Optionally, the S4 specifically includes: S41, a fuzzy logic control algorithm unit, used to analyze the constructed dynamic environment model, wherein the fuzzy logic control algorithm unit performs fuzzy reasoning according to the processed real-time sensor data in the dynamic environment model; ;in, Real-time sensor data after fuzzy processing The corresponding membership function is, and To adjust the parameters, used to control the shape of the membership function, is the base of the natural logarithm. This membership function maps the real-time sensor data to a Membership values ​​within the range; S42, a danger identification unit, used to identify high-risk road sections according to the membership function, wherein the danger identification unit identifies high-risk road sections by analyzing road conditions, weather changes, slight changes in road structure and other environmental factors: ;in, is the danger value of the high-risk road section, For the The membership degree of each data point is is the first data points, For the The weight of the data point, is the number of data points; S43, a potential danger prediction unit, used to simulate and predict the impending dangerous situation based on the identified high-risk road sections, environmental change trends and historical data, and generate potential danger prediction results; S44, a warning generation unit, used to generate a warning signal according to the potential danger prediction result.

[0014] Optionally, the S5 specifically includes: S51, a warning signal receiving unit, used to receive a warning signal generated by a risk assessment module; S52, the early warning processing unit analyzes the potential danger level according to the received early warning signal, and determines the response measures according to the predetermined danger level classification standard; S53, a warning output unit, configured to output corresponding safety warning information according to the response measures generated by the warning processing unit, wherein the safety warning information includes sound warning, light signal warning and vibration warning; S54, early warning control logic unit, is used to select the appropriate early warning signal output mode through logical control judgment according to the early warning signal and the danger level: ;in, is the overall priority of the warning signal, For the The danger level of the warning signal is the weight coefficient of the corresponding warning signal, is the number of all warning signals.

[0015] The beneficial effects of the present invention are: (1) The present invention achieves accurate monitoring and early warning of high-risk sections of mountain roads by combining adaptive sensor networks, real-time environmental modeling, fuzzy logic control algorithms and hazard prediction technology. The system can obtain multi-dimensional environmental data in real time and analyze it based on dynamic environmental models, accurately identify high-risk sections and predict potential dangerous situations, thereby providing drivers with timely safety warnings and significantly improving driving safety on mountain roads.

[0016] (2) The present invention uses real-time data processing and fuzzy reasoning technology, combined with an adaptive early warning mechanism and multiple safety early warning output methods, to generate appropriate early warning information according to different danger levels. This technology not only enhances the real-time performance and accuracy of the system, but also greatly improves the response speed and reliability of early warning information, reducing the risk of accidents caused by potential dangers.

[0017] (3) The present invention provides a comprehensive understanding of the mountain highway environment by combining multi-sensor data fusion and dynamic modeling technology, enabling the system to adapt to complex and changing road and weather conditions, timely identify high-risk sections and predict possible dangers, and has strong adaptability and intelligence. This technology can effectively reduce the need for reliance on human intervention, improve the degree of automation of safety warnings and the system's ability to operate continuously. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a general framework diagram of a safety warning system for high-risk sections of mountain roads proposed by the present invention. DETAILED DESCRIPTION

[0019] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0020] refer to Figure 1 , a safety warning system for high-risk sections of mountain roads, the system comprising: S1, a multi-type sensor network, including temperature sensors, humidity sensors, light sensors, air pressure sensors and vibration sensors, which are installed on key sections of mountain roads to generate real-time sensor data; In this implementation, S1 specifically includes: S11, temperature sensor, used to detect the temperature data of key sections of mountain roads The temperature sensing range of the temperature sensor is to ; S12, humidity sensor, used to monitor the humidity data of the road surface and surrounding environment in real time , the humidity sensor working range is to Relative humidity; S13, light sensor, used to detect the light intensity of key sections in real time and generate light intensity data The light sensor can sense the range from arrive Light intensity; S14, an air pressure sensor for real-time monitoring of air pressure changes, the air pressure sensor is configured to work at sea level to The air pressure range is 100 meters, which can detect small air pressure changes and output air pressure data. ; S15, vibration sensor, used to sense road vibration or vehicle dynamic behavior in real time, and generate vibration data by detecting small vibration changes in the road surface The frequency range that the vibration sensor can monitor is to ; S16, a data fusion unit, used to receive the temperature data, humidity data, light intensity data, air pressure data and vibration data output by the above sensors, and perform fusion processing on the sensor data to generate real-time sensor data: ;in, represents real-time sensor data, is the temperature data output by the temperature sensor, The humidity data output by the humidity sensor. The light intensity data output by the light sensor. It is the air pressure data output by the air pressure sensor. It is the vibration data output by the vibration sensor.

[0021] This implementation method generates sensor data in real time by deploying a multi-type sensor network on key sections of mountain roads, including temperature sensors, humidity sensors, light sensors, air pressure sensors, and vibration sensors. The system can fully acquire environmental data, covering information in multiple dimensions such as weather, road conditions, and vibration.

[0022] S2, a data acquisition unit, used to receive real-time sensor data and transmit the real-time sensor data to a central processing unit; This embodiment receives multi-dimensional environmental data from sensors in real time through a data acquisition unit and transmits it to a central processing unit. This unit ensures efficient and accurate transmission of real-time data, allowing the system to obtain and process environmental change information in the first place.

[0023] S3, a central processing unit, including a processing module and a storage module, wherein the processing module is used to construct a dynamic environment model according to real-time sensor data and monitor environmental changes, and the storage module is used to store the dynamic environment model and real-time sensor data; In this implementation, S3 specifically includes: S31, a processing module, used to generate a dynamic environment model according to real-time sensor data, the processing module includes a data receiving unit, a data processing unit, a model building unit and a model evaluation unit; S32, a storage module, used for storing dynamic environment models and real-time sensor data; S33, a model updating unit, used to update the constructed dynamic environment model in real time according to the new real-time sensing data, wherein the updating is performed by comparing the real-time sensing data with the currently constructed dynamic environment model to perform error correction: ;in, is the updated value of the dynamic environment model, is the real-time sensor data currently received, is the current dynamic environment model output, is the change value of the dynamic environment model updated in the previous round, and To adjust the parameters.

[0024] The S31 specifically includes: S311, data receiving unit, used to receive real-time sensor data from the data fusion unit , and perform preliminary format analysis and verification; S312, a data processing unit is used to process the received real-time sensor data, wherein the data processing includes signal denoising, data cleaning, data standardization, time and space completion, and data normalization processing to generate processed real-time sensor data ; S313, a model building unit, is used to build a dynamic environment model using a support vector machine algorithm for the processed real-time sensor data: ;in, For a dynamic environment model, is the first data points, is the kernel function used to calculate the data points and the current processed real-time sensor data The similarity between is the weight coefficient of the support vector, is the deviation term, is the number of support vectors; S314, a model evaluation unit, used to evaluate the constructed dynamic environment model and generate a model evaluation error: ;in, is the model evaluation error of the dynamic environment model, is the first data points, The first data points, is the number of data points.

[0025] This embodiment combines the processing module and storage module of the central processing unit to build a dynamic environmental model in real time and monitor environmental changes. The processing module can generate an accurate environmental model based on real-time sensor data, reflecting factors such as road conditions, weather changes, and road structure changes on mountain roads in real time, thereby enhancing the system's dynamic adaptability. The storage module ensures the long-term preservation of historical data and dynamic environmental models, allowing the system to continue to operate under a variety of environmental conditions and provide reliable data support for future hazard prediction and analysis.

[0026] S4, the danger assessment module, uses fuzzy logic control algorithm to analyze the dynamic environment model, identify high-risk sections, predict potential dangerous situations, and generate corresponding warning signals; In this implementation, S4 specifically includes: S41, a fuzzy logic control algorithm unit, used to analyze the constructed dynamic environment model, wherein the fuzzy logic control algorithm unit performs fuzzy reasoning according to the processed real-time sensor data in the dynamic environment model; ;in, Real-time sensor data after fuzzy processing The corresponding membership function is, and To adjust the parameters, used to control the shape of the membership function, is the base of the natural logarithm. This membership function maps the real-time sensor data to a Membership values ​​within the range; S42, a danger identification unit, used to identify high-risk road sections according to the membership function, wherein the danger identification unit identifies high-risk road sections by analyzing road conditions, weather changes, slight changes in road structure and other environmental factors: ;in, is the danger value of the high-risk road section, For the The membership degree of each data point is is the first data points, For the The weight of the data point, is the number of data points; S43, a potential danger prediction unit, used to simulate and predict the impending dangerous situation based on the identified high-risk road sections, environmental change trends and historical data, and generate potential danger prediction results; S44, a warning generation unit, used to generate a warning signal according to the potential danger prediction result.

[0027] This implementation method uses a hazard assessment module combined with a fuzzy logic control algorithm to conduct an in-depth analysis of the dynamic environment model, which can identify high-risk sections in real time and predict potential dangerous situations. The fuzzy logic control algorithm can process complex and uncertain data, accurately analyze multi-dimensional environmental information, identify possible risk factors, and generate corresponding warning signals.

[0028] S5, an early warning control module outputs corresponding safety early warning information according to the early warning signal; In this implementation, S5 specifically includes: S51, a warning signal receiving unit, used to receive a warning signal generated by a risk assessment module; S52, the early warning processing unit analyzes the potential danger level according to the received early warning signal, and determines the response measures according to the predetermined danger level classification standard; S53, a warning output unit, configured to output corresponding safety warning information according to the response measures generated by the warning processing unit, wherein the safety warning information includes sound warning, light signal warning and vibration warning; S54, early warning control logic unit, is used to select the appropriate early warning signal output mode through logical control judgment according to the early warning signal and the danger level: ;in, is the overall priority of the warning signal, For the The danger level of the warning signal is the weight coefficient of the corresponding warning signal, is the number of all warning signals.

[0029] S6, user interaction interface, used to display warning signals and safety warning information, and interact with the driver in real time; This implementation method uses a user interaction interface to display warning signals and safety warning information in real time, and interacts with the driver in real time to ensure that the driver can intuitively understand the current road conditions and potential safety risks. The interface can automatically adjust the display content according to the warning level and environmental changes, provide clear and easy-to-understand prompts, and help the driver respond quickly.

[0030] S7, network communication module, used to send warning signals and dynamic environment models to traffic control departments and nearby road monitoring systems through wireless communication networks.

[0031] This implementation uses a network communication module to send warning signals and dynamic environment models to traffic control departments and nearby road monitoring systems in real time through a wireless communication network. This module ensures efficient data sharing and information synchronization between the road monitoring system and the traffic management department, allowing relevant departments to obtain the latest road safety information in a timely manner and respond quickly.

[0032] Example: In order to verify the feasibility of the present invention, the present invention is applied to a mountain highway safety monitoring system. The highway is located in the western mountainous area and is affected by bad weather and complex terrain all year round, with many high-risk sections. Due to the particularity of geographical conditions and climate change, traditional traffic monitoring systems cannot accurately identify and predict the safety risks of high-risk sections in a timely manner. Therefore, traffic accidents occur from time to time, causing a large number of casualties and property losses. In order to meet these safety challenges, the mountain highway high-risk section safety warning system based on adaptive sensor networks and real-time environment modeling of the present invention is applied in the region.

[0033] In this highway system, a multi-type sensor network is installed to cover the real-time monitoring of multiple environmental parameters such as temperature, humidity, light, air pressure and vibration in key sections. The data collected by the sensor network is transmitted to the central processing unit in real time through the data acquisition unit, and the processing module constructs a dynamic environmental model. This model can reflect road conditions and weather changes in real time, helping traffic management departments to obtain safety information on road sections in a timely manner. At the same time, the dynamic environmental model is analyzed using fuzzy logic control algorithms. The system can identify high-risk sections and predict potential dangerous situations, and generate corresponding warning signals.

[0034] During the implementation process, the system can accurately identify the danger level of different road sections, and according to the predetermined danger level classification standards, timely output the corresponding safety warning information through the warning control module, such as sound warning, light signal warning and vibration warning. In addition, the user interaction interface enables the driver to obtain warning signals and safety warning information in real time, ensuring that the driver can respond in time. The network communication module sends the warning information and dynamic environment model to the traffic control department and the nearby road monitoring system through the wireless network, realizing cross-regional safety warning and data sharing.

[0035] Through the deployment of this system, the safety monitoring and early warning capabilities of mountain roads have been significantly improved. The following is a specific data example showing the effect of the system after application:

[0036] Data Category describe Before deployment Post-deployment Number of traffic accidents per month Number of traffic accidents reported per month 18 times 4 times High-risk road section recognition rate The accuracy of the system in identifying high-risk sections 70% 95% Warning response time Mean time from prediction of hazardous situation to actual warning 25 minutes 5 minutes Accuracy The accuracy of dangerous situations predicted and confirmed by the system 82% 96% False Positive Rate The proportion of high-risk sections or dangerous situations misjudged by the system 15% 2% Traffic Management Response Time Average response time from receiving warning information to taking action 35 minutes 7 minutes From the data in Table 1, we can see that before the deployment of the system, the number of traffic accidents on this mountain highway was 18 per month, while after the deployment of the system, the number was reduced to 4 per month, reducing the traffic accident rate by more than 75%. At the same time, the recognition rate of high-risk sections of the system has been significantly improved, from 70% to 95%, so that high-risk areas can be warned and handled in a timely manner. The accuracy of the system's prediction and confirmation of dangerous situations has increased from 82% to 96%, and the false alarm rate has also dropped from 15% to 2%, greatly improving the accuracy and reliability of the warning. The response time of the traffic management department has also been significantly reduced, from 35 minutes to 7 minutes, greatly improving the efficiency of responding to safety incidents.

[0037] For example, under the influence of a continuous rainstorm, the system judged that a landslide might occur on a certain section of road through the data of the air pressure sensor and the humidity sensor. The system sent a warning signal through the early warning module within about 5 minutes, successfully restricting the passage of vehicles on this section of road and avoiding traffic accidents.

[0038] Through this embodiment, the high-risk road section safety warning system of the mountain highway of the present invention can realize real-time monitoring, accurate identification and timely warning, effectively reducing the occurrence of traffic accidents and improving driving safety. At the same time, through accurate danger prediction and efficient response mechanism, the system can provide safety protection for drivers in bad weather and complex road conditions, greatly enhancing the level of traffic safety management of mountain highways.

[0039] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A safety warning system for high-risk sections of mountainous roads, characterized in that: The system comprises: S1, a multi-type sensor network, including temperature sensors, humidity sensors, light sensors, air pressure sensors and vibration sensors, which are installed on key sections of mountain roads to generate real-time sensor data; S2, a data acquisition unit, used to receive real-time sensor data and transmit the real-time sensor data to a central processing unit; S3, a central processing unit, including a processing module and a storage module, wherein the processing module is used to construct a dynamic environment model according to real-time sensor data and monitor environmental changes, and the storage module is used to store the dynamic environment model and real-time sensor data; S4, the danger assessment module, uses fuzzy logic control algorithm to analyze the dynamic environment model, identify high-risk sections, predict potential dangerous situations, and generate corresponding warning signals; S5, an early warning control module outputs corresponding safety early warning information according to the early warning signal; S6, user interaction interface, used to display warning signals and safety warning information, and interact with the driver in real time; S7, network communication module, used to send warning signals and dynamic environment models to traffic control departments and nearby road monitoring systems through wireless communication networks.

2. A safety warning system for high-risk sections of mountainous highways according to claim 1, characterized in that: The S1 specifically includes: S11, temperature sensor, used to detect the temperature data of key sections of mountain roads The temperature sensing range of the temperature sensor is to ; S12, humidity sensor, used to monitor the humidity data of the road surface and surrounding environment in real time , the humidity sensor working range is to Relative humidity; S13, light sensor, used to detect the light intensity of key sections in real time and generate light intensity data The light sensor can sense the range from arrive Light intensity; S14, an air pressure sensor for real-time monitoring of air pressure changes, the air pressure sensor is configured to work at sea level to The air pressure range is 100 meters, which can detect small air pressure changes and output air pressure data. ; S15, vibration sensor, used to sense road vibration or vehicle dynamic behavior in real time, and generate vibration data by detecting small vibration changes in the road surface The frequency range that the vibration sensor can monitor is to ; S16, a data fusion unit, used to receive the temperature data, humidity data, light intensity data, air pressure data and vibration data output by the above sensors, and perform fusion processing on the sensor data to generate real-time sensor data: ;in, represents real-time sensor data, is the temperature data output by the temperature sensor, The humidity data output by the humidity sensor. The light intensity data output by the light sensor. It is the air pressure data output by the air pressure sensor. It is the vibration data output by the vibration sensor.

3. A safety warning system for high-risk sections of mountainous highways according to claim 2, characterized in that: The S3 specifically includes: S31, a processing module, used to generate a dynamic environment model according to real-time sensor data, the processing module includes a data receiving unit, a data processing unit, a model building unit and a model evaluation unit; S32, a storage module, used for storing dynamic environment models and real-time sensor data; S33、 The model updating unit is used to update the constructed dynamic environment model in real time according to the new real-time sensor data, and the update is performed by comparing the real-time sensor data with the currently constructed dynamic environment model to perform error correction: ;in, is the updated value of the dynamic environment model, is the real-time sensor data currently received, is the current dynamic environment model output, is the change value of the dynamic environment model updated in the previous round, and To adjust the parameters.

4. A safety warning system for high-risk sections of mountainous highways according to claim 3, characterized in that: The S31 specifically includes: S311, data receiving unit, used to receive real-time sensor data from the data fusion unit , and perform preliminary format analysis and verification; S312, a data processing unit is used to process the received real-time sensor data, wherein the data processing includes signal denoising, data cleaning, data standardization, time and space completion, and data normalization processing to generate processed real-time sensor data ; S313, a model building unit, is used to build a dynamic environment model using a support vector machine algorithm for the processed real-time sensor data: ;in, For a dynamic environment model, is the first data points, is the kernel function used to calculate the data points and the current processed real-time sensor data The similarity between is the weight coefficient of the support vector, is the deviation term, is the number of support vectors; S314, a model evaluation unit, used to evaluate the constructed dynamic environment model and generate a model evaluation error: ;in, is the model evaluation error of the dynamic environment model, is the first data points, The first data points, is the number of data points.

5. A safety warning system for high-risk sections of mountainous highways according to claim 4, characterized in that: The S4 specifically includes: S41, a fuzzy logic control algorithm unit, used to analyze the constructed dynamic environment model, wherein the fuzzy logic control algorithm unit performs fuzzy reasoning according to the processed real-time sensor data in the dynamic environment model; ;in, Real-time sensor data after fuzzy processing The corresponding membership function is, and To adjust the parameters, used to control the shape of the membership function, is the base of the natural logarithm. This membership function maps the real-time sensor data to a Membership values ​​within the range; S42, a danger identification unit, used to identify high-risk road sections according to the membership function, wherein the danger identification unit identifies high-risk road sections by analyzing road conditions, weather changes, slight changes in road structure and other environmental factors: ;in, is the danger value of the high-risk road section, For the The membership degree of each data point is is the first data points, For the The weight of the data point, is the number of data points; S43, a potential danger prediction unit, used to simulate and predict the impending dangerous situation based on the identified high-risk road sections, environmental change trends and historical data, and generate potential danger prediction results; S44, a warning generation unit, used to generate a warning signal according to the potential danger prediction result.

6. A safety warning system for high-risk sections of mountainous highways according to claim 1, characterized in that: The S5 specifically includes: S51, a warning signal receiving unit, used to receive a warning signal generated by a risk assessment module; S52, the early warning processing unit analyzes the potential danger level according to the received early warning signal, and determines the response measures according to the predetermined danger level classification standard; S53, a warning output unit, configured to output corresponding safety warning information according to the response measures generated by the warning processing unit, wherein the safety warning information includes sound warning, light signal warning and vibration warning; S54, early warning control logic unit, is used to select the appropriate early warning signal output mode through logical control judgment according to the early warning signal and the danger level: ;in, is the overall priority of the warning signal, For the The danger level of the warning signal is the weight coefficient of the corresponding warning signal, is the number of all warning signals.

Images