A traffic control system for highway engineering construction

Abstract

The application discloses a traffic control system for highway engineering construction, comprising: an acoustic wave reflection signal acquisition module for acquiring acoustic wave reflection signals of a highway construction section; a stress risk area identification module for determining the acoustic wave reflection source type of the acoustic wave reflection signals and the position of the stress risk area; a construction traffic control module for determining the maximum allowable speed of a construction traffic control area; a vehicle speed limit pre-adjustment module for determining a vehicle speed limit scheme for a future preset time period; a traffic density control module for implementing traffic density control measures on the construction traffic control area; a facility stability analysis module for evaluating the stability of construction facilities in the highway construction area; and a traffic control effect evaluation module for evaluating the traffic control effect and adjusting the vehicle speed limit and heavy vehicle traffic density. The application provides a method for dynamically optimizing traffic control during highway construction, and significantly improves the safety of highway construction and the smoothness of traffic flow.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent traffic management, and in particular to a traffic command system for highway engineering construction. BACKGROUND

[0002] With the rapid development of modern highway transportation network and the continuous increase of traffic flow, the number and scale of highway engineering construction projects are also expanding. During the process of highway construction, the stress distribution of roadbed and pavement, the stability of construction facilities, and the management of traffic flow become key safety issues. Traditional traffic control methods mainly rely on static speed limits, simple traffic diversion, and manual experience judgment, which are difficult to respond to dynamic changes in the construction site in real time, and have many shortcomings. During the highway construction period, the bearing capacity of the roadbed and pavement changes due to construction operations and traffic pressure, which may cause stress concentration or stress overload in local areas. If these high-stress areas cannot be identified and addressed in a timely manner, serious consequences such as roadbed settlement, cracking, or collapse may occur, affecting the quality and service life of highway construction. Traditional methods often use periodic manual detection, which has limited detection frequency and accuracy, and cannot achieve real-time monitoring of the stress distribution of the construction area, thereby increasing the construction risk. Secondly, the traffic control plan for the highway construction area is usually based on fixed speed limits and diversion, which is difficult to adapt to the changing construction site and external conditions such as weather and traffic flow. In particular, under sudden traffic density increases or adverse weather conditions, fixed speed limit schemes may not effectively prevent traffic pressure from impacting the construction area, and the lack of dynamic optimization based on real-time data makes it difficult to balance the traffic flow and safety of the construction area, which may cause construction delays and traffic congestion. In addition, traditional traffic density control often relies on experience or manual intervention, lacks scientific evaluation based on real-time data, and the dynamic pressure of heavy vehicles on the roadbed is the main factor affecting the stress changes of the roadbed in the construction area. If the traffic density of heavy vehicles cannot be managed in real time, it is easy to cause stress accumulation in the roadbed, which may eventually lead to structural damage. Therefore, traditional traffic density control lacks precision for specific high-stress areas and cannot effectively disperse traffic pressure. Furthermore, construction facilities such as roadblocks, warning signs, construction equipment, and construction materials are often placed in the highway construction site, and their stacking method and stability directly affect the safety of the construction area. However, traditional construction facility placement management relies on manual experience and is difficult to comprehensively evaluate the impact of factors such as facility stacking pattern, weight distribution, and support area on its stability. The identification and disposal of facility tilting, sliding, and other risks often lag behind accidents, and cannot effectively prevent safety problems. In order to solve the above problems, there is an urgent need for an intelligent traffic command method based on real-time data to dynamically adjust the construction traffic control plan and comprehensively evaluate and optimize the traffic flow command and management during highway construction. SUMMARY

[0003] The present application provides a traffic control system for highway engineering construction to solve the above problems in the prior art, mainly comprising:

[0004] The sound wave reflection signal acquisition module is configured to determine the sound wave emission parameters of the sound wave emitter according to the sound wave reflection signal receiving effect of the construction road section, and to acquire the sound wave reflection signal of the construction road section.

[0005] The stress risk area identification module is configured to use a short-time Fourier transform algorithm to extract the frequency spectrum characteristics, to determine the sound wave reflection source type of the sound wave reflection signal and the position of the stress risk area.

[0006] The construction traffic control module is configured to construct a vehicle speed adjustment model according to the traffic density, stress data and environmental factors of the construction traffic control area, and to determine the maximum allowable speed of the construction traffic control area.

[0007] The vehicle speed limit pre-adjustment module is configured to determine the vehicle speed limit scheme of the construction traffic control area in a future preset time period according to the temperature, humidity and rainfall of the construction traffic control area in the future preset time period.

[0008] The traffic density control module is configured to implement traffic density control measures according to the heavy vehicle traffic density of the construction traffic control area in the future preset time period and the real-time stress value of the stress risk area.

[0009] The facility stability analysis module is configured to evaluate the stability of the construction facilities in the highway construction area according to the weight, support area and stacking mode of the construction facilities, and to adjust the real-time vehicle speed limit scheme of the construction road section based on the stability evaluation result.

[0010] The traffic control effect evaluation module is configured to evaluate the traffic control effect based on the stress data and traffic data before and after the implementation of the vehicle speed limit scheme and the traffic density control measures, and to adjust the vehicle speed limit and the heavy vehicle traffic density.

[0011] Further, the sound wave reflection signal acquisition module is configured to determine the sound wave emission parameters of the sound wave emitter according to the sound wave reflection signal receiving effect of the construction road section, and to acquire the sound wave reflection signal of the construction road section, comprising:

[0012] The historical sound wave emission parameters of the sound wave emitter, the road material composition of the construction road section corresponding to the detection time, the road surface humidity, and the reflection signal receiving effect are obtained through the sound wave reflection monitoring database, a recurrent neural network is used for model training, a sound wave emission parameter prediction model of the sound wave emitter is constructed, the sound wave emission parameters of the sound wave emitter with an optimal sound wave reflection signal receiving effect in the current road construction road section are determined, the emission parameters include emission frequency, amplitude, and angle, the material composition includes but is not limited to concrete and asphalt, and the receiving effect includes excellent, good, and poor; the sound wave emitter and the directional array sound wave receiver are arranged at the starting point of the road construction road section, the sound wave emitter emits sound waves to the road construction road section according to the set sound wave emission parameters, and the directional array sound wave receiver obtains the sound wave reflection signal and the corresponding timestamp information; according to the sound wave reflection signal of the road construction road section, the sound wave reflection signal is separated through an independent component analysis algorithm to obtain the sound wave reflection signals of different sound wave reflection sources, and is saved to the sound wave reflection monitoring database.

[0013] Further, the stress risk area identification module is configured to extract frequency spectrum features of the stress risk area using a short-time Fourier transform algorithm, determine a sound wave reflection source type of the sound wave reflection signal and a position of the stress risk area, and includes:

[0014] The time-domain sound wave reflection signal is converted into frequency-domain data using a short-time Fourier transform algorithm, and the frequency spectrum features are extracted, including frequency, frequency offset, and amplitude; the historical sound wave emission frequency, amplitude, and frequency spectrum features of the sound wave reflection signal are obtained through the sound wave reflection monitoring database, and the sound wave reflection source type is labeled, a support vector machine algorithm is used for model training, a sound wave reflection source type identification model is constructed, the sound wave reflection source type of the sound wave reflection signal is determined, and the sound wave reflection source type includes a stress risk area reflection source and a non-stress risk area reflection source; the position of the stress risk area relative to the directional array sound wave receiver is calculated through time difference estimation according to the echo time of the obtained sound wave reflection signal, and the position of the stress risk area is determined; and the construction traffic control area division unit is used to divide the construction traffic control area according to the position of the stress risk area.

[0015] Further, the construction traffic control area division unit is configured to divide the construction traffic control area according to the position of the stress risk area, and specifically includes:

[0016] The stress risk area in the road construction road section is divided into a construction traffic control area; if the number of stress risk areas in the road construction road section is greater than 1, the positions of the stress risk areas in the road construction road section are obtained, and the distances between the stress risk areas are determined; if the distance is less than a preset safety distance threshold, the stress risk areas are divided into the same construction traffic control area.

[0017] Further, the construction traffic control module is configured to construct a vehicle speed adjustment model according to the traffic density, stress data and environmental factors of the construction traffic control area, and determine the maximum allowable speed of the construction traffic control area, including:

[0018] The temperature, humidity and rainfall of the construction traffic control area are obtained through real-time weather forecast, and an environmental factor formula is used to determine the environmental factor of the construction traffic control area, wherein H is the relative humidity, T is the temperature, T max is the maximum temperature, R is the rainfall, and R max is the maximum rainfall; a strain gauge sensor is installed in the stress risk area of the construction traffic control area to monitor the stress value of the stress risk area in real time; a vehicle speed adjustment model is constructed according to the traffic density, stress data and environmental factors of the construction traffic control area to determine the maximum allowable speed of the construction traffic control area, wherein V max is the maximum allowable speed of the vehicle, S is the stress value of the current stress risk area, S th is a preset stress safety threshold, D is the traffic density, and α and β are respectively the traffic density weight parameter and the environmental factor weight parameter, which are used to adjust the influence degree of the traffic density and the environmental factor on the speed, and are obtained by fitting historical data, K is a constant coefficient, which is used to adjust the speed range and is set according to the maximum speed limit of the road section design, and E is the environmental factor, which represents the influence of the environment on the subgrade stress; if there are multiple stress risk areas in the construction traffic control area, the minimum value of the maximum allowable speeds of the multiple stress risk areas is selected as the vehicle speed limit of the construction traffic control area; a vehicle speed limit scheme of the construction traffic control area is developed according to the vehicle speed limit of the construction traffic control area; if the highway construction engineering stage changes, the position of the new stress risk area is determined through the real-time sound wave reflection signal of the highway construction section, and the construction traffic control area is updated; the vehicle speed limit of the updated construction traffic control area is determined by using the vehicle speed adjustment model according to the traffic density, stress data and environmental factors of the updated construction traffic control area, and the vehicle speed limit scheme of the construction traffic control area is adjusted.

[0019] Further, the vehicle speed limit pre-adjustment module is configured to determine the vehicle speed limit scheme of the construction traffic control area in a future preset time period according to the temperature, humidity and rainfall of the construction traffic control area in the future preset time period, including:

[0020] The history traffic density data of the construction traffic control area is obtained through the traffic monitoring database, the long short-term memory network is used for model training, the traffic density data of the construction traffic control area in the future preset time period is predicted, including the heavy vehicle passing density; the temperature, humidity and rainfall of the construction traffic control area in the future preset time period are obtained through the weather forecast, and the vehicle speed adjustment model is used to determine the vehicle speed limit scheme of the construction traffic control area in the future preset time period.

[0021] Further, the passing density control module is configured to implement passing density control measures according to the heavy vehicle traffic density of the construction traffic control area in the future preset time period and the real-time stress value of the stress risk area, including:

[0022] If the predicted heavy vehicle passing density of the construction traffic control area in the future preset time period is greater than the preset density threshold, the time point at which the heavy vehicle passing density of the construction traffic control area in the future is greater than the preset density threshold is determined, and the passing density control measures are implemented in advance, the passing density control measures include limiting the heavy vehicle passing density in the construction traffic control area, when the upper limit of the heavy vehicle passing number is reached, temporarily limiting new heavy vehicles from entering the area; the stress value of the stress risk area is monitored in real time through the strain gauge sensor installed in the stress risk area of the construction traffic control area, if the real-time stress data exceeds the preset stress safety threshold, the passing density control measures are implemented until the stress falls below the preset stress safety threshold.

[0023] Further, the facility stability analysis module is configured to evaluate the stability of the construction facility in the highway construction area according to the weight, support area and stacking mode of the construction facility, and adjust the real-time vehicle speed limit scheme of the highway construction section based on the stability evaluation result, including:

[0024] The camera of the road construction section is used to obtain the construction facility placement image of the road construction section, the Canny edge detection algorithm is used to identify the edge contour of the construction facility on the road construction section, the shape and boundary information of the construction facility are obtained through the findContours method in OpenCV, and the size of the construction equipment is determined; according to the construction facility placement image, the convolutional neural network is used for model training, the stacking mode and facility type of the construction facility are judged, and the weight and material of each facility are obtained according to the facility type, the facility type includes but is not limited to roadblock, warning sign, construction equipment and construction material, and the stacking mode includes but is not limited to row stacking, horizontal stacking, vertical stacking, staggered stacking, ring stacking and pyramid stacking; the relative distance, angle and position between the facilities are calculated by using the minimum enclosing rectangle method, the spatial relationship between the facilities is obtained, and the actual supporting area of the goods in the stacking process is identified; the stability of the construction facility of the road construction section is evaluated in combination with the weight, supporting area and stacking mode of the construction facility, the inclination, sliding or movement risk is identified, and the stability includes good, good and poor; if the stability of the construction facility of the road construction section is good or poor, the road section where the construction facility is located is divided into a construction traffic control area, a vehicle speed limiting scheme is implemented to limit the speed of the vehicle on the road construction section, and a warning information is sent to the person in charge of the road construction section; the camera of the road construction section is used to continuously obtain the construction facility placement image, the Kalman filter is used to judge the movement and change of the construction facility with time, the dynamic update of the real-time construction facility stacking mode is obtained, and the stability of the construction facility in the road construction area is evaluated in real time.

[0025] Further, the traffic control effect evaluation module is used to evaluate the traffic control effect based on the stress data and traffic data before and after the implementation of the vehicle speed limiting scheme and the passing density control measure, and adjust the vehicle speed limit and the heavy vehicle passing density, including:

[0026] The stress data and traffic data before and after the implementation of the vehicle speed limiting scheme and the passing density control measure in the construction traffic control area are obtained, the traffic control effect of the current vehicle speed limiting scheme and the passing density control measure is evaluated based on the stress recovery speed and amplitude and the passing efficiency of the construction traffic control area, and the vehicle speed limit and the heavy vehicle passing density are adjusted, the vehicle speed limiting scheme and the passing density control measure of the construction traffic control area are updated until the traffic control effect reaches the expectation.

[0027] The technical scheme provided by the embodiment of the application can include the following beneficial effects:

[0028] The application provides a traffic control system for highway engineering construction. The application can quickly identify the position of stress risk area by extracting the spectral characteristics of the sound wave reflection signal in real time, effectively solving the problem that the traditional method cannot monitor the stress distribution of the construction area in real time. Based on the traffic density, stress data and environmental factors, the maximum allowable speed of the construction area is dynamically adjusted to fully adapt to traffic and weather changes and avoid safety hazards and traffic congestion caused by fixed speed limit schemes. The application combines future traffic density and environmental prediction data to optimize the speed limit and traffic density control scheme of the construction traffic control area, effectively manages the dynamic pressure of heavy vehicles on the roadbed, and prevents structural damage caused by stress accumulation. At the same time, the application uses the weight, support area and stacking mode of the construction facilities to evaluate the stability of the facilities, identify and warn the risks of tilting and sliding in time, and ensure the safety of the construction site. Through real-time evaluation and optimization of the traffic control effect, the application forms a dynamic closed-loop traffic control and management system for highway construction, which can continuously improve the traffic control effect of the highway construction section, optimize the traffic efficiency while ensuring traffic safety, and fully meet the demand for efficient and safe traffic management in the modern highway construction process, thereby providing a strong guarantee for the stability of the traffic order and the smooth progress of the construction progress in the highway construction area. BRIEF DESCRIPTION OF DRAWINGS

[0029] Fig. 1 A flowchart of a traffic control system for highway engineering construction according to the application;

[0030] Fig. 2 A schematic diagram of a traffic control system for highway engineering construction according to the application;

[0031] Fig. 3 Another schematic diagram of a traffic control system for highway engineering construction according to the application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical strategy and advantages of the application clearer, the application will be described in detail below in combination with the drawings and specific embodiments.

[0033] As Figs. 1-3 , the traffic control system for highway engineering construction according to the embodiment specifically can include:

[0034] Step S101, a sound wave reflection signal acquisition module, configured to determine the sound wave emission parameters of the sound wave emitter according to the sound wave reflection signal receiving effect of the highway of the construction section, and acquire the sound wave reflection signal of the highway construction section.

[0035] The historical sound wave emission parameters of the sound wave emitter, the road material composition of the construction road section corresponding to the detection time, the road surface humidity, and the reflection signal receiving effect are obtained from the sound wave reflection monitoring database, a recurrent neural network is used for model training, a sound wave emitter sound wave emission parameter prediction model is constructed, the sound wave emission parameters of the sound wave emitter with optimal sound wave reflection signal receiving effect in the current road construction road section are determined, the emission parameters include emission frequency, amplitude and angle, the material composition includes but is not limited to concrete and asphalt, and the receiving effect includes excellent, good and poor. The sound wave emitter and the directional array sound wave receiver are arranged at the starting point of the road construction road section, the sound wave emitter emits sound waves to the road construction road section according to the set sound wave emission parameters, and the directional array sound wave receiver obtains the sound wave reflection signal and the corresponding timestamp information. According to the sound wave reflection signal of the road construction road section, the sound wave reflection signal is separated by an independent component analysis algorithm to obtain the sound wave reflection signals of different sound wave reflection sources, and is saved to the sound wave reflection monitoring database.

[0036] For example, on a certain road construction road section, the roadbed condition of the road section is monitored in real time by the sound wave reflection monitoring system, the historical sound wave emission parameters and related environmental data of the road section are obtained from the sound wave reflection monitoring database, and it is found that when the sound wave emission frequency is set to 40 kHz, the amplitude is set to 10 Pa, and the emission angle is 15 degrees, the concrete pavement can obtain excellent reflection signal receiving effect under the condition of 50% humidity. When the sound wave emission frequency is set to 25 kHz, the amplitude is 8 Pa, and the emission angle is 10 degrees, the asphalt material road surface can obtain excellent reflection signal receiving effect under the condition of about 60% humidity. According to the historical sound wave emission parameters and related environmental data of the road section, a recurrent neural network is used for model training to construct a sound wave emitter sound wave emission parameter prediction model. According to the current environmental conditions, the concrete pavement and the humidity of 50%, the emission parameters of the sound wave emitter are automatically set to the frequency of 40 kHz, the amplitude of 10 Pa and the emission angle of 15 degrees. At the starting point of the construction road section, the sound wave emitter and the directional array sound wave receiver are installed, and the emitter emits sound waves to the road section in front according to the set parameters. The independent component analysis algorithm is applied to process the received reflection signal, separate the sound wave reflection signals of multiple reflection sources that may exist on the construction road section, such as water accumulation points and stress risk areas, and save the sound wave reflection signals of different sound wave reflection sources to the sound wave reflection monitoring database.

[0037] In step S102, the stress risk area identification module is used to extract the frequency spectrum characteristics by using the short-time Fourier transform algorithm, to determine the sound wave reflection source type of the sound wave reflection signal and the position of the stress risk area.

[0038] The time-domain acoustic wave reflection signal is converted into frequency-domain data using a short-time Fourier transform algorithm, and the spectral features thereof are extracted, including frequency, frequency shift, and amplitude. The historical acoustic wave emission frequency, amplitude, and spectral features of the acoustic wave reflection signal are obtained through the acoustic wave reflection monitoring database, and the acoustic wave reflection source type is labeled. A support vector machine algorithm is used for model training to construct an acoustic wave reflection source type identification model to determine the acoustic wave reflection source type of the acoustic wave reflection signal. The acoustic wave reflection source type includes a stress risk area reflection source and a non-stress risk area reflection source. According to the echo time of the obtained acoustic wave reflection signal, the position of the stress risk area relative to the directional array acoustic wave receiver is calculated through time difference estimation to determine the position of the stress risk area. A construction traffic control area division unit is used to divide the construction traffic control area according to the position of the stress risk area.

[0039] For example, a set of acoustic wave signals with a frequency of 40 kHz and an amplitude of 10 Pa are emitted by the acoustic wave emitter. After short-time Fourier transform from time domain to frequency domain, a reflection signal with a frequency of 40 kHz and an amplitude of about 8 Pa is obtained, as well as a weak shift of a specific frequency in the acoustic wave signal. Historical data are called through the acoustic wave reflection monitoring database to obtain the historical acoustic wave emission frequency, amplitude, and spectral features of the acoustic wave reflection signal, and the stress risk area reflection source or the non-stress risk area reflection source is labeled. Based on these historical data, a support vector machine algorithm is used for model training to construct an acoustic wave reflection source type identification model to classify acoustic wave reflection signals with different features into stress risk area reflection sources or non-stress risk area reflection sources. According to the acoustic wave reflection source type identification model, it is identified that the spectral features of the current signal conform to the acoustic wave reflection characteristics of the stress risk area, so it is judged that the acoustic wave reflection source type is a stress risk area reflection source. The time difference between acoustic wave emission and reflection signal reception is measured, and the distance of the stress risk area from the first receiver of the directional array acoustic wave receiver is calculated to be about 300 meters, the distance from the second receiver is 301 meters, and the distance from the third receiver is 300.5 meters. According to the direction and distance of the source of the acoustic wave reflection signal, the stress risk area is located at a certain position in the central area of the construction road section, so the construction traffic control area division unit is used to divide the area within 20 meters around the area as a construction traffic control area to reduce the frequent passage of heavy vehicles in this high stress area and avoid further aggravating the subgrade pressure.

[0040] The construction traffic control area division unit is used to divide the construction traffic control area according to the position of the stress risk area.

[0041] The stress risk area in the highway construction section is divided into a construction traffic control area. If the number of stress risk areas in the highway construction section is greater than 1, the positions of each stress risk area in the highway construction section are obtained, and the distance between each stress risk area is determined. If the distance is less than the preset safety distance threshold, it is divided into the same construction traffic control area.

[0042] For example, in a certain highway construction section, the acoustic wave monitoring system detects two stress risk areas. The first stress risk area is located at 200 meters of the construction section, and the second is located at 220 meters of the construction section. If the preset safety distance threshold is 30 meters, which is used to determine whether adjacent stress risk areas are close enough to be combined into one construction traffic control area. After calculation, the distance between the two stress risk areas is 20 meters, which is lower than the preset safety distance threshold of 30 meters. Therefore, the two stress risk areas are divided into the same construction traffic control area.

[0043] Step S103, the construction traffic control module, is configured to construct a vehicle speed adjustment model according to the traffic density, stress data and environmental factors of the construction traffic control area, and determine the maximum allowable speed of the construction traffic control area.

[0044] The temperature, humidity and rainfall of the construction traffic control area are obtained through real-time weather forecast, and the environmental factor formula is used The environmental factor of the construction traffic control area is determined, wherein H is the relative humidity, T is the temperature, T max is the maximum temperature, R is the rainfall, and R max is the maximum rainfall. The strain gauge sensor is installed in the stress risk area in the construction traffic control area to monitor the stress value of the stress risk area in real time. According to the traffic density, stress data and environmental factors of the construction traffic control area, a vehicle speed adjustment model is constructed The maximum allowable speed of the construction traffic control area is determined, wherein V max is the maximum allowable speed of the vehicle, S is the stress value of the current stress risk area, and S thTo preset the stress safety threshold, D represents traffic density, α and β are traffic density weighting parameters and environmental factor weighting parameters, respectively, used to adjust the influence of traffic density and environmental factors on traffic speed. These are obtained through fitting historical data. K is a constant coefficient used to adjust the speed range, set according to the maximum speed limit designed for the road section. E is the environmental factor, representing the influence of the environment on the roadbed stress. If multiple stress risk areas exist within the construction traffic control area, the minimum maximum permissible traffic speed among these areas is selected as the vehicle speed limit for the construction traffic control area. Based on the vehicle speed limit in the construction traffic control area, a vehicle speed limit scheme is formulated. If the highway construction phase changes, the location of the new stress risk area is determined using real-time acoustic wave reflection signals from the construction section, and the construction traffic control area is updated. Based on the updated traffic density, stress data, and environmental factors of the construction traffic control area, a speed adjustment model is used to determine the updated vehicle speed limit, and the vehicle speed limit scheme for the construction traffic control area is adjusted.

[0045] For example, within a construction traffic control area for highway construction, a real-time weather forecast shows that the current relative humidity H = 80%, temperature T = 25°C, and rainfall R = 5 mm per hour. The highest historical temperature T in this area is... max =40℃ and historical maximum rainfall R max =10mm. Using the environmental factor formula. The environmental factor E of the construction traffic control area was determined to be 0.8064. Strain gauge sensors were installed in the stress risk zone within this construction traffic control area to monitor the current stress value S = 80 MPa in real time. Based on the traffic density, stress data, and environmental factor of the construction traffic control area, a vehicle speed adjustment model was constructed. If the safety threshold S of stress th =100MPa, current traffic density D = 50 vehicles / minute. The weighting parameter for traffic density α = 0.05, the weighting parameter for environmental factors β = 0.3, and the constant coefficient K = 80. Based on the maximum speed limit set in the road section design, the maximum permissible speed V in the current construction traffic control area is calculated. max= 16.1 km / h. If there are multiple stress risk areas within the construction traffic control area, the maximum allowable speed of each stress risk area is calculated, and the minimum value is taken as the overall speed limit of the area. For example, if the maximum allowable speed of other stress risk areas is calculated to be 15 km / h and 18 km / h, 15 km / h is selected as the speed limit of the entire construction traffic control area. Through the vehicle speed adjustment scheme adjustment unit, real-time monitoring of the highway construction engineering stage changes is performed. If the highway construction engineering stage changes, the new stress risk area position is determined through the real-time sound wave reflection signal of the highway construction section, and the construction traffic control area is updated. According to the traffic density, stress data and environmental factors of the updated construction traffic control area, the vehicle speed adjustment model is used to determine the vehicle speed limit of the updated construction traffic control area, and the vehicle speed limit scheme of the construction traffic control area is adjusted.

[0046] In step S104, the vehicle speed limit pre-adjustment module is used to determine the vehicle speed limit scheme of the construction traffic control area in the future preset time period according to the temperature, humidity and rainfall of the construction traffic control area in the future preset time period.

[0047] Through the traffic monitoring database, the historical traffic density data of the construction traffic control area is obtained, and the long short-term memory network is used for model training to predict the traffic density data of the construction traffic control area in the future preset time period, including the heavy vehicle traffic density. Through the weather forecast, the temperature, humidity and rainfall of the construction traffic control area in the future preset time period are obtained, and according to the vehicle speed adjustment model, the vehicle speed limit scheme of the construction traffic control area in the future preset time period is determined.

[0048] For example, in a certain highway construction traffic control area, the traffic density data in the past week is obtained through the traffic monitoring database, the long short-term memory network model is used to train the historical data, and it is predicted that the traffic density from 7:00 to 9:00 tomorrow morning will reach 65 vehicles per minute, including 10 heavy vehicles per minute. Through the weather forecast system, the weather conditions of the construction area tomorrow morning are obtained, including a relative humidity of 85%, a temperature of 30°C, and a rainfall of 5mm per hour. According to these predicted environmental data and traffic density data, they are substituted into the vehicle speed adjustment model to calculate the vehicle speed limit from 7:00 to 9:00 tomorrow morning as 20 km / h. Therefore, according to this prediction result, the vehicle speed limit scheme of the construction traffic control area from 7:00 to 9:00 tomorrow morning is formulated. The construction management department will set up corresponding speed limit signs in advance at the entrance of the construction section, and publish speed limit information on the nearby traffic control center and navigation system to remind vehicles to slow down during this period to ensure the safety of the construction area and the smoothness of the traffic flow.

[0049] Step S105, the traffic density control module, is configured to implement traffic density control measures according to the heavy vehicle traffic density of the construction traffic control area in the future preset time period and the real-time stress value of the stress risk area.

[0050] If the predicted heavy vehicle traffic density of the construction traffic control area in the future preset time period is greater than the preset density threshold, the time point at which the heavy vehicle traffic density of the future construction traffic control area is greater than the preset density threshold is determined, and the traffic density control measures are implemented in advance. The traffic density control measures include limiting the heavy vehicle traffic density in the construction traffic control area, and temporarily restricting new heavy vehicles from entering the area when the number of heavy vehicles reaches the upper limit. The strain gauge sensor installed in the stress risk area of the construction traffic control area is used to monitor the stress value of the stress risk area in real time. If the real-time stress data exceeds the preset stress safety threshold, the traffic density control measures are implemented until the stress falls below the preset stress safety threshold.

[0051] For example, if the predicted heavy vehicle traffic density of a certain highway construction traffic control area from 3 pm to 5 pm tomorrow will reach 25 vehicles per minute, which is greater than the preset density threshold of 20 vehicles per minute. To prevent dense traffic from causing excessive pressure on the construction area, it is decided to implement traffic density control measures in advance before 3 pm tomorrow, including limiting the traffic density of heavy vehicles in the construction traffic control area, setting a maximum of 20 heavy vehicles per minute, and once the number of heavy vehicles reaches this limit, new heavy vehicles will be temporarily prohibited from entering the area until the next period is reopened. At the same time, strain gauges are installed in the stress risk area of the construction traffic control area to monitor the stress of the roadbed in real time. If the current stress safety threshold for this area is 100 MPa, and while controlling the traffic density of heavy vehicles, the strain gauge sensor continues to monitor the stress value, which reaches 100 MPa at 3:30 pm, the traffic density control measures are immediately strengthened. At this time, not only is the traffic of heavy vehicles strictly limited, but the traffic density of all vehicles is further reduced until the stress value falls below the safety threshold.

[0052] Step S106, the facility stability analysis module, is configured to evaluate the stability of the construction facilities in the highway construction area according to the weight, support area and stacking mode of the construction facilities, and to implement real-time vehicle speed limit schemes for the highway construction section based on the stability evaluation results.

[0053] The camera of the road construction section is used to obtain the construction facility placement image of the road construction section. The Canny edge detection algorithm is used to identify the edge contour of the construction facility on the road construction section, and the findContours method in OpenCV is used to obtain the shape and boundary information of the construction facility, so as to determine the size of the construction equipment. According to the construction facility placement image, a convolutional neural network is used for model training to judge the stacking mode and facility type of the construction facility, and according to the facility type, the weight and material of each facility are obtained. The facility types include but are not limited to roadblocks, warning signs, construction equipment and construction materials, and the stacking modes include but are not limited to row stacking, horizontal stacking, vertical stacking, staggered stacking, ring stacking and pyramid stacking. The minimum bounding rectangle method is used to calculate the relative distance, angle and position between the facilities, obtain the spatial relationship between the facilities, and identify the actual supporting area of the items in the stacking process. Combined with the weight, supporting area and stacking mode of the construction facility, the stability of the construction facility on the road construction section is evaluated, and the inclination, sliding or movement risk is identified. The stability includes good and poor. If the stability of the construction facility on the road construction section is good or poor, the road section where the construction facility is located is divided into a construction traffic control area, a vehicle speed limiting scheme is implemented to limit the speed of vehicles on the road construction section, and warning information is sent to the person in charge of the road construction section. The camera of the road construction section is used to continuously obtain the construction facility placement image, the Kalman filter is used to judge the movement and change of the construction facility over time, the dynamic update of the real-time construction facility stacking mode is obtained, and the stability of the construction facility in the road construction area is evaluated in real time.

[0054] For example, in a road construction section, the camera captures the image of the facility placement of the construction section, and identifies that there are various construction facilities placed on site, including roadblocks, warning signs, construction equipment and construction materials, etc. Using the Canny edge detection algorithm and the findContours method of OpenCV, the contour and boundary of each facility are extracted, and the shape of the roadblock is obtained as a cuboid with an average size of 2 meters long, 0.5 meters wide and 1 meter high. The shape of a certain construction equipment is a cuboid with a size of 1.5 meters long, 0.5 meters wide and 1 meter high. According to the placement image of the construction facility, the stacking mode and facility type of the construction facility are identified by a convolutional neural network model, and the stacking mode includes but is not limited to row stacking, horizontal stacking, vertical stacking, staggered stacking, ring stacking and pyramid stacking. The stacking mode of the facility is staggered stacking, and all the facilities are placed within a range of 2 meters outside the road of the construction section. The construction facility type identification result is roadblock, warning sign and construction equipment, and the weight information of each facility is obtained from the database, which is about 80 kg for the roadblock, about 150 kg for the construction equipment cart, and the material information. The relative distance, angle and position between the construction facilities are calculated by using the minimum circumscribed rectangle method, and the average distance between the roadblocks is 0.5 meters. There are also some other construction materials stacked beside the cart, including reinforcing steel bars, cement bags, formwork and steel pipes. The support area of each facility is calculated based on the shape and size information of these construction facilities to evaluate the support effect when stacking. Combined with the weight, support area and row stacking mode of the construction facility, the stability of the construction facility in the road construction section is evaluated, and the risk of inclination, sliding or movement is identified. The stability includes excellent, good and poor, and the overall stability of the current construction facility is poor, and part of the construction materials has a sliding risk. Therefore, the road section where the construction facility is located is divided into a construction traffic control area. In order to ensure safety, warning information is automatically sent to the person in charge of the construction section, suggesting adjustment or reinforcement, and a vehicle speed limit scheme is implemented in the section, reducing the speed limit from the original 40 km / h to the preset speed threshold of 20 km / h, to reduce the vibration impact on the facility when the vehicle is driving. The placement of the construction facility is continuously monitored by the camera in the construction section, and the Kalman filter is used to track the position change of the facility. The stability of the construction facility is evaluated every 5 minutes at a preset time interval, and the stability of the facility is ensured to meet the expected value in the subsequent construction process through the dynamically updated stacking mode, and the safety management on site is further optimized.

[0055] In step S107, the traffic control effect evaluation module is configured to evaluate the traffic control effect based on the stress data and traffic data before and after the implementation of the vehicle speed limit scheme and the traffic density control measure, and adjust the vehicle speed limit and the heavy vehicle traffic density.

[0056] The stress data and traffic data before and after the implementation of the vehicle speed limit scheme and the traffic density control measures in the construction traffic control area are acquired, and the traffic control effect of the current vehicle speed limit scheme and the traffic density control measures is evaluated based on the stress recovery speed and amplitude and the traffic efficiency in the construction traffic control area. If the traffic control effect is lower than expected, the vehicle speed limit and the heavy vehicle traffic density are adjusted, the vehicle speed limit scheme and the traffic density control measures in the construction traffic control area are updated, and the traffic control effect is adjusted until the traffic control effect reaches the expected level.

[0057] For example, in a certain highway construction traffic control area, the management department implemented a vehicle speed limit scheme and a traffic density control measure, setting the vehicle speed limit to 20 km / h and limiting the maximum number of heavy vehicles passing through to 20 per minute. Before the implementation of the measure, the stress value in the stress risk area was 110 MPa, and the stress safety threshold of the construction roadbed was 100 MPa. Within 20 minutes after the implementation of the traffic density control measure and the speed limit scheme, the stress monitoring data showed that the stress decreased to 102 MPa, and the traffic efficiency remained at 50 vehicles per minute. The evaluation result showed that the effect of the current speed limit scheme and the traffic density control measure was lower than expected, and the traffic efficiency also decreased. To further improve the traffic control effect, the management department decided to further reduce the vehicle speed limit to 15 km / h and adjust the upper limit of the heavy vehicle traffic density to 15 vehicles per minute. After the implementation of the adjusted scheme, the stress data and traffic data were recorded again. Under the new control measure, the stress value decreased to 90 MPa within the next minute, reaching the safety threshold, and the traffic efficiency remained at 70 vehicles per minute, close to the expected level of the management department. Through this adjustment, an effective stress recovery speed and a reasonable traffic efficiency were achieved, ensuring the safety of the construction area and the smoothness of the traffic flow. Therefore, the construction management department will continue to implement the adjusted speed limit and traffic density scheme as the new traffic control measure and real-time monitoring to ensure that the roadbed in the construction area remains in a safe state during the construction period.

[0058] The above description is merely preferred embodiments of the present application and a description of the principles of the technology employed. It will be understood by those skilled in the art that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or equivalent features without departing from the concept of the present application. For example, the above features can be replaced with technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A traffic control system for use in highway construction, characterized in that The system includes: The acoustic wave reflection signal acquisition module is used to determine the acoustic wave transmission parameters of the acoustic wave transmitter based on the acoustic wave reflection signal reception effect of the highway construction section, and to acquire the acoustic wave reflection signal of the highway construction section. The stress risk area identification module is used to extract its spectral features using the short-time Fourier transform algorithm to determine the type of acoustic wave reflection source and the location of the stress risk area. The construction traffic control module is used to construct a vehicle speed adjustment model based on traffic density, stress data and environmental factors in the construction traffic control area, and to determine the maximum allowable speed in the construction traffic control area. The vehicle speed limit pre-adjustment module is used to determine the vehicle speed limit scheme for the construction traffic control area based on the temperature, humidity and rainfall of the construction traffic control area in the future preset time period. The traffic density control module is used to implement traffic density control measures based on the heavy vehicle traffic density in the construction traffic control area and the real-time stress value of the stress risk area during a future preset time period. The facility stability analysis module is used to assess the stability of construction facilities within the highway construction area based on their weight, support area, and stacking pattern, and to implement vehicle speed limit schemes for highway construction sections based on the stability assessment results. The traffic control effectiveness evaluation module is used to evaluate the effectiveness of traffic control based on stress data and traffic data before and after the implementation of vehicle speed limit schemes and traffic density control measures, and to adjust vehicle speed limits and heavy vehicle traffic density. The facility stability analysis module is used to assess the stability of construction facilities within the highway construction area based on their weight, support area, and stacking pattern, and to implement vehicle speed limit schemes for the highway construction section based on the stability assessment results, including: Images of the construction facilities' placement along the highway construction section are acquired using cameras. The Canny edge detection algorithm is used to identify the edge contours of these facilities, and the `findContours` method in OpenCV is used to obtain their shape and boundary information, determining the dimensions of the equipment. Based on the placement images, a convolutional neural network is used to train a model to determine the stacking pattern and type of the facilities. The weight and material of each facility are obtained based on its type, which includes, but is not limited to, roadblocks, warning signs, construction equipment, and construction materials. Stacking patterns include, but are not limited to, row stacking, horizontal stacking, vertical stacking, staggered stacking, circular stacking, and pyramid stacking. The minimum bounding rectangle method is used to calculate the relative distances, angles, and other parameters between the facilities. The system identifies the location and spatial relationships between facilities, and determines the actual support area of ​​items during stacking. Combining the weight, support area, and stacking pattern of the construction facilities, it assesses the stability of the construction facilities in the highway construction section, identifying risks of tilting, slipping, or movement. Stability is categorized as excellent, good, or poor. If the stability of the construction facilities in the highway construction section is good or poor, the highway section where the construction facilities are located is designated as a construction traffic control zone, and a vehicle speed limit scheme is implemented to restrict vehicle speed in this section. A warning message is sent to the person in charge of the highway construction section. Cameras in the highway construction section continuously acquire images of the placement of construction facilities, and Kalman filtering is used to determine the movement and changes of the construction facilities over time, obtaining dynamic updates of the real-time stacking pattern of the construction facilities and assessing the stability of the construction facilities within the highway construction area in real time.

2. The system according to claim 1, wherein, The acoustic wave reflection signal acquisition module is used to determine the acoustic wave transmission parameters of the acoustic wave transmitter based on the acoustic wave reflection signal reception effect of the highway construction section, and to acquire the acoustic wave reflection signal of the highway construction section, including: Historical acoustic emission parameters of acoustic transmitters, road material composition, pavement moisture, and reflection signal reception effects at the corresponding detection time are obtained from an acoustic reflection monitoring database. A recurrent neural network is used to train a model to construct an acoustic emission parameter prediction model for the acoustic transmitters. This model determines the acoustic emission parameters of the acoustic transmitters that provide excellent acoustic reflection signal reception at the current road construction section. Emission parameters include emission frequency, amplitude, and angle. Material composition includes, but is not limited to, concrete and asphalt. Reception effects are categorized as excellent, good, and poor. An acoustic transmitter and a directional array acoustic receiver are installed at the starting point of the road construction section. The acoustic transmitter emits acoustic waves to the road construction section according to the set emission parameters, and the directional array acoustic receiver acquires the acoustic reflection signals and corresponding timestamp information. Based on the acoustic reflection signals from the road construction section, an independent component analysis algorithm is used to separate the acoustic reflection signals, obtaining acoustic reflection signals from different sources, which are then saved to the acoustic reflection monitoring database.

3. The system according to claim 1, wherein, The stress risk area identification module is used to extract its spectral features using a short-time Fourier transform algorithm. Determine the type of acoustic wave reflection source and the location of the stress risk area, including: The time-domain acoustic wave reflection signal is converted into frequency-domain data using a short-time Fourier transform algorithm, and its spectral features, including frequency, frequency shift, and amplitude, are extracted. Historical acoustic wave emission frequencies, amplitudes, and spectral features of the reflected signals are obtained from an acoustic wave reflection monitoring database, and the acoustic wave reflection source types are labeled. A support vector machine algorithm is used to train a model to construct an acoustic wave reflection source type identification model, determining the acoustic wave reflection source type of the reflected signal. The acoustic wave reflection source types include reflection sources in stress-risk areas and reflection sources in non-stress-risk areas. Based on the echo time of the acquired acoustic wave reflection signal, the position of the stress-risk area relative to the directional array acoustic wave receiver is calculated through time difference estimation, thus determining the location of the stress-risk area. Construction traffic control area delineation units are used to divide the area into construction traffic control zones based on the location of the stress-risk area.

4. The system according to claim 3, wherein, The construction traffic control zone delineation unit is used to delineate construction traffic control zones based on the location of stress risk areas, including: The stress risk areas in the highway construction section are divided into construction traffic control areas. If the number of stress risk areas in the highway construction section is greater than 1, the location of each stress risk area in the highway construction section is obtained, and the distance between each stress risk area is determined. If the distance is less than the preset safe distance threshold, they are divided into the same construction traffic control area.

5. The system according to claim 1, wherein, The construction traffic control module is used to construct a vehicle speed adjustment model based on traffic density, stress data, and environmental factors in the construction traffic control area, and to determine the maximum permissible traffic speed in the construction traffic control area, including: Temperature, humidity, and rainfall in the construction traffic control area were obtained through real-time weather forecasts, and environmental factor formulas were used. Determine the environmental factors in the construction traffic control area, where H is relative humidity and T is temperature. R represents the highest temperature, and R represents the rainfall. The maximum rainfall was recorded. Strain gauge sensors were installed in the stress risk areas within the construction traffic control zone to monitor stress values ​​in real time. A vehicle speed adjustment model was constructed based on traffic density, stress data, and environmental factors within the construction traffic control zone. Determine the maximum permissible traffic speed in the construction traffic control area, among which... Where S is the maximum permissible speed for vehicles, and S is the stress value of the current stress risk area. To preset the stress safety threshold, D represents traffic density, α and β are traffic density weighting parameters and environmental factor weighting parameters, respectively, used to adjust the influence of traffic density and environmental factors on traffic speed. These are obtained through fitting historical data. K is a constant coefficient used to adjust the speed range, set according to the maximum speed limit designed for the road section. E is the environmental factor, representing the influence of the environment on the roadbed stress. If multiple stress risk areas exist within the construction traffic control area, the minimum maximum allowable traffic speed among the multiple stress risk areas is selected as the vehicle speed limit for the construction traffic control area. Based on the vehicle speed limit for the construction traffic control area, a vehicle speed limit scheme is formulated. If the highway construction phase changes, the location of the new stress risk area is determined through real-time acoustic wave reflection signals of the highway construction section, and the construction traffic control area is updated. Based on the updated traffic density, stress data, and environmental factors of the construction traffic control area, a vehicle speed adjustment model is used to determine the updated vehicle speed limit for the construction traffic control area, and the vehicle speed limit scheme for the construction traffic control area is adjusted.

6. The system according to claim 1, wherein, The vehicle speed limit pre-adjustment module is used to determine the vehicle speed limit scheme for the construction traffic control area based on the temperature, humidity, and rainfall in the construction traffic control area during a future preset time period, including: Historical traffic density data of the construction traffic control area is obtained through a traffic monitoring database. A long short-term memory network is used to train the model to predict the traffic density data of the construction traffic control area in the future, including the traffic density of heavy vehicles. The temperature, humidity and rainfall of the construction traffic control area in the future, according to the weather forecast, are obtained. The model is adjusted according to the vehicle speed to determine the vehicle speed limit scheme for the construction traffic control area in the future, according to the vehicle speed.

7. The system according to claim 1, wherein, The traffic density control module is used to implement traffic density control measures based on the heavy vehicle traffic density in the construction traffic control area and the real-time stress value of the stress risk area during a preset future time period, including: If the predicted heavy vehicle traffic density in the construction traffic control area is greater than the preset density threshold in the future, then the time point when the heavy vehicle traffic density in the construction traffic control area will exceed the preset density threshold will be determined, and traffic density control measures will be implemented in advance. The traffic density control measures include limiting the heavy vehicle traffic density in the construction traffic control area, and temporarily restricting new heavy vehicles from entering the area once the upper limit of the number of heavy vehicles is reached; and monitoring the stress value in the stress risk area in real time through strain gauge sensors installed in the stress risk area of ​​the construction traffic control area. If the real-time monitored stress data exceeds the preset stress safety threshold, then traffic density control measures will be implemented until the stress drops below the preset stress safety threshold.

8. The system according to claim 1, wherein, The traffic control effectiveness evaluation module is used to evaluate the effectiveness of traffic control based on stress data and traffic data before and after the implementation of vehicle speed limit schemes and traffic density control measures, and to adjust vehicle speed limits and heavy vehicle traffic density, including: Obtain stress and traffic data before and after implementing vehicle speed limit schemes and traffic density control measures in the construction traffic control area. Based on the stress recovery speed and magnitude and traffic efficiency in the construction traffic control area, evaluate the traffic control effect of the current vehicle speed limit scheme and traffic density control measures. If the traffic control effect is lower than expected, adjust the vehicle speed limit and heavy vehicle traffic density, and update the vehicle speed limit scheme and traffic density control measures in the construction traffic control area until the traffic control effect reaches the expected level.

Images