Road construction scheduling system and method based on multi-element environment information digital twinning and storage medium

Abstract

The invention discloses a road construction scheduling system and method based on multi-element environment information digital twinning and a storage medium, and belongs to the technical field of road construction. The system comprises a data acquisition unit, a digital twin platform and a construction scheduling control unit which are in communication connection with one another, the data acquisition unit is responsible for acquiring construction environment and equipment state information of each stage of paving of a paver, initial pressing, re-pressing and final pressing of a road roller, and transmitting the information to the digital twin platform; the platform constructs a virtual road construction scene containing spatio-temporal information according to the received information and a preset rule; and the construction scheduling control unit inputs the construction environment information of each stage into a pre-trained pavement temperature attenuation prediction model to obtain pavement temperature attenuation changes in different preset scenes, and performs strategy scheduling on the construction equipment according to the pavement temperature attenuation changes. According to the invention, by comprehensively sensing the multi-element environment information of the construction site, the optimization of the scheduling strategy is realized, and the efficiency and accuracy of road construction are improved.

Description

Technical Field

[0001] The present invention relates to a road construction scheduling system, method and storage medium based on multi-environment information digital twin, belonging to the technical field of road construction. Background Art

[0002] During the entire process of road paving, the change trend of pavement temperature is one of the core indicators for measuring construction quality. During construction, the pavement temperature does not change evenly and steadily, and its attenuation is affected by a variety of complex factors. Differences in natural environment will lead to different pavement temperature attenuation. In addition to natural factors, material preparation, construction technology, and transportation conditions of paving materials will also significantly affect the temperature change of road construction pavement. In addition, each stage of road paving has specific requirements for pavement temperature. Therefore, temperature detection in a single stage alone cannot fully reflect the changing trend of pavement temperature. Continuous monitoring of pavement temperature and environmental information is particularly important.

[0003] However, most of the detection solutions on the market currently focus on temperature detection, and these solutions are relatively simple and mainly limited to temperature monitoring of pavers. These solutions usually cover the temperature detection of raw materials before paving, the temperature monitoring of the ironing plate during paving, and the short-term changes in the road surface temperature within a limited distance after paving. These single temperature detection methods are not enough to meet the needs of long-term monitoring of road surface temperature change trends, because they mainly focus on the immediate temperature changes after paving, while ignoring the temperature fluctuations over long spans and long distances. At the same time, these detection solutions also have the problem of independent closed-loop systems, and the coverage of the control system is not wide enough. For example, although the temperature scanning system of the paver can display the attenuation of material temperature within a certain range, it cannot achieve effective data exchange with the control systems of other construction equipment (such as rollers), so it is impossible to track the entire process of road surface temperature from paving to rolling. The environmental information detection and road surface temperature detection during the whole process of road paving are aimed at having a more scientific and reasonable scheduling basis for road construction equipment, and reducing the interference and influence of changes in multiple environmental factors on the temperature attenuation of road construction pavement through the scheduling of construction equipment.

[0004] Therefore, in view of the above situation, the present invention urgently needs to develop a new and effective road construction scheduling system and scheduling strategy to solve the related technical defects faced in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a road construction scheduling system, method and storage medium based on multi-environmental information digital twin, aiming to achieve comprehensive perception and precise scheduling of the road construction process by integrating multi-environmental information digital twin technology.

[0006] In order to achieve the above objectives / solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0007] On the one hand, the present invention provides a road construction scheduling system based on multi-environment information digital twin, which includes: a data acquisition unit, a digital twin platform and a construction scheduling control unit that are communicatively connected to each other; The data acquisition unit is used to respectively acquire the construction environment information and the construction equipment status information of the paver paving stage, the roller initial compaction stage, the roller recompaction stage and the roller final compaction stage, and transmit the construction environment information and the construction equipment status information corresponding to different construction stages to the digital twin platform; The digital twin platform is used to construct a virtual road construction scene integrating time and space based on the received construction environment information and construction equipment status information corresponding to different construction stages and preset information splicing rules; The construction scheduling control unit is used to input the construction environment information obtained from the paver paving stage, the roller initial compaction stage, the roller re-compaction stage and the roller final compaction stage into a pre-trained pavement temperature attenuation prediction model to obtain the pavement temperature attenuation change results corresponding to different preset scenarios, and then schedule the construction strategy of related construction equipment according to the pavement temperature attenuation change results.

[0008] Optionally, the construction environment information includes: road surface temperature scanning information, meteorological data information and equipment GNSS positioning information at different construction stages; the construction equipment status information includes at least: vehicle equipment characteristic information corresponding to asphalt mixing plants, asphalt transfer trucks, pavers and rollers.

[0009] Optionally, the road surface temperature scanning information is collected by an infrared thermal imager installed on a paver and a roller; the meteorological data is collected by a vehicle-mounted micro-meteorological station installed on the paver and the roller.

[0010] Optionally, the meteorological data information includes: one or more of temperature, humidity, atmospheric pressure, wind speed and wind direction.

[0011] Optionally, a virtual road construction scene integrating time and space is constructed based on the received construction environment information and construction equipment status information corresponding to different construction stages and preset information splicing rules, including: During each construction phase, when the distance moved by the construction equipment in a certain direction exceeds the preset single scan range, a second scan is performed until the construction equipment completes the entire scan within the corresponding preset overall scan coverage range, thereby obtaining several sets of continuous and uninterrupted road surface temperature scanning information; splicing the plurality of groups of continuous and uninterrupted road surface temperature scanning information according to the equipment GNSS positioning information to obtain the local temperature field information in each construction stage; Obtain the meteorological data information collected at each construction stage, associate and fuse the local temperature field information at each construction stage with the corresponding meteorological data information to obtain associated and fused information; The associated and fused information is spliced ​​according to the equipment GNSS positioning information to construct a virtual road construction scene integrating time and space.

[0012] Optionally, in the process of determining the local temperature field information in each construction stage, the middle row area of ​​the thermal imaging image within a single preset scannable range is selected as the splicing object of the local temperature field information; wherein the confirmation process of the splicing object includes: The middle row area is divided into several squares of the same area, the average temperature within the unit area is measured, and the average temperature values ​​of each unit area are spliced ​​to obtain the temperature distribution of an area with a fixed length and width as the splicing object of the local temperature field information.

[0013] Optionally, the road surface temperature attenuation prediction model includes: a temperature attenuation and natural environmental factor correlation model at different locations at the same time, corresponding to preset scenario one, and a temperature attenuation and natural environmental factor correlation model at the same location at different times, corresponding to preset scenario two.

[0014] In a second aspect, the present invention further provides a road construction scheduling method based on multi-environmental information digital twins applicable to the road construction scheduling system based on multi-environmental information digital twins as described in the first aspect, comprising: Obtain construction environment information corresponding to the paving stage of the paver, the initial compaction stage of the roller, the secondary compaction stage of the roller, and the final compaction stage of the roller; Inputting the construction environment information into a pre-trained road surface temperature attenuation prediction model to obtain road surface temperature attenuation change results corresponding to different preset scenarios; According to the pavement temperature attenuation change results, construction strategy scheduling is performed on relevant construction equipment.

[0015] Optionally, the construction environment information includes: equipment GNSS positioning information, meteorological data information and pavement temperature scanning information during the paving stage of the paver, meteorological data information and pavement temperature scanning information during the initial compaction stage of the roller, meteorological data information and pavement temperature scanning information during the re-compaction stage of the roller, and meteorological data information and pavement temperature scanning information during the final compaction stage of the roller.

[0016] Optionally, the road surface temperature attenuation prediction model adopts a long short-term memory network, and its calculation formula is as follows: ; In the formula, represents the input gate, represents the activation function, represents the weight of the input gate, Indicates the hidden state, Represents the input at the current time. represents the forget gate, represents the weight of a part of the forget gate, represents the weight of the other part of the forget gate, represents the output gate, represents the weight of the output gate, Indicates the cell state at the current time, Indicates the cell state at the previous time. Indicates the output at the current time.

[0017] Optionally, different preset scenarios include: preset scenario one and preset scenario two; wherein scenario one is the impact of natural environmental factors on road surface temperature changes at different locations at the same time, and scenario two is the impact of natural environmental factors on road surface temperature changes at the same location at different times.

[0018] In the third aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the road construction scheduling method based on multi-dimensional environmental information digital twin as described in the second aspect are implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention installs on-board infrared thermal imaging scanners and meteorological data sensors on paver and roller, so that the system can fully perceive the multi-faceted environmental information of the construction site. At the same time, using GNSS positioning information, the system can accurately splice the road surface temperature field information at different construction stages to construct a complete road construction virtual scene, providing accurate data support for construction scheduling. On this basis, the present invention predicts the road surface temperature attenuation by using a long short-term memory network (LSTM), taking into account the influence of various natural environmental factors on temperature attenuation, so that the stability and prediction accuracy of the prediction model are significantly improved; (2) The present invention also constructs a digital twin model by combining construction environment information and construction equipment status information, so that the system can meet the full-cycle detection of environmental information required during the road paving process according to the digital twin model, and achieve dual traceability of road construction data and construction environment data in time and space, which to a certain extent helps managers better understand the actual situation and potential problems at the construction site; (3) The present invention also reduces data storage space and improves data transmission and storage efficiency by adopting a temperature field matrix instead of the data processing method of infrared thermal imaging images, thereby achieving a rapid and accurate description of the road surface temperature distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The figure shows the structural composition diagram of the temperature field of the construction road surface of the present invention; Figure 2 The figure shows the principle schematic diagram of the vehicle-mounted infrared thermal imaging scanning device of the present invention; Figure 3 Shown is a schematic diagram of the construction of the road temperature field of the present invention; Figure 4 Shown is a schematic diagram of constructing a digital twin model of the present invention; Figure 5 Shown is a schematic diagram of the application of the neural network training of the present invention; Figure 6 It is a schematic diagram of neural network model training in the following scenario in the road construction scheduling method based on multi-environment information digital twin of the present invention; Figure 7 It is a schematic diagram of neural network model training under scenario 2 in the road construction scheduling method based on multi-environment information digital twin of the present invention; Figure 8 Shown is a flow chart of an embodiment of a road construction scheduling method based on multi-environmental information digital twin of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0022] The term "and / or" is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the associated objects are in an "or" relationship.

[0023] Example 1 refer to Figures 1 to 4 This embodiment introduces a road construction scheduling system based on multi-environment information digital twin, which includes: a data acquisition unit, a digital twin platform and a construction scheduling control unit that are communicatively connected to each other.

[0024] The data acquisition unit is used to respectively acquire the construction environment information and construction equipment status information of the paver paving stage, the roller initial compaction stage, the roller re-compaction stage and the roller final compaction stage, and transmit the construction environment information and construction equipment status information corresponding to different construction stages to the digital twin platform.

[0025] Specifically, the construction environment information includes: road surface temperature scanning information, meteorological data information and equipment GNSS positioning information at different construction stages. The construction equipment status information at least includes: vehicle equipment characteristic information corresponding to the asphalt mixing plant, asphalt transfer vehicle, paver and roller. The road surface temperature scanning information is collected by an infrared thermal imager installed on the paver and roller; the meteorological data is collected by a vehicle-mounted micro-meteorological station installed on the paver and roller. The meteorological data information includes: one or more of temperature, humidity, atmospheric pressure, wind speed and wind direction.

[0026] The digital twin platform is used to construct a virtual road construction scene integrating time and space based on the received construction environment information and construction equipment status information corresponding to different construction stages and preset information splicing rules.

[0027] Specifically, according to the received construction environment information and construction equipment status information corresponding to different construction stages, as well as the preset information splicing rules, a virtual road construction scene integrating time and space is constructed, including: During each construction phase, when the distance moved by the construction equipment in a certain direction exceeds the preset single scan range, a second scan is performed until the construction equipment completes the entire scan within the corresponding preset overall scan coverage range, thereby obtaining several sets of continuous and uninterrupted road surface temperature scanning information; splicing the plurality of groups of continuous and uninterrupted road surface temperature scanning information according to the equipment GNSS positioning information to obtain the local temperature field information in each construction stage; Obtain the meteorological data information collected at each construction stage, associate and fuse the local temperature field information at each construction stage with the corresponding meteorological data information to obtain associated and fused information; The associated and fused information is spliced ​​according to the equipment GNSS positioning information to construct a virtual road construction scene integrating time and space.

[0028] It is worth noting that, in the process of determining the local temperature field information in each construction stage, the present embodiment also selects the middle row area of ​​the thermal imaging image of a single preset scannable range as the splicing object of the local temperature field information; wherein the confirmation process of the splicing object includes: The middle row area is divided into several squares of the same area, the average temperature within the unit area is measured, and the average temperature values ​​of each unit area are spliced ​​to obtain the temperature distribution of an area with a fixed length and width as the splicing object of the local temperature field information.

[0029] The construction scheduling control unit is used to input the construction environment information obtained from the paver paving stage, the roller initial compaction stage, the roller recompaction stage and the roller final compaction stage into the pre-trained road surface temperature attenuation prediction model to obtain the road surface temperature attenuation change results corresponding to different preset scenarios, and then perform construction strategy scheduling for related construction equipment according to the road surface temperature attenuation change results. Among them, the road surface temperature attenuation prediction model includes: a correlation model of temperature attenuation and natural environmental factors at different locations at the same time, corresponding to preset scenario one, and a correlation model of temperature attenuation and natural environmental factors at different times at the same location, corresponding to preset scenario two.

[0030] In the actual application process of this embodiment, first, at each stage of road construction, such as paver paving, roller initial compaction, recompacting and final compaction, the system collects road surface temperature scanning information and meteorological data information (such as temperature, humidity, atmospheric pressure, wind speed and wind direction) in real time through infrared thermal imagers and vehicle-mounted micro-meteorological stations installed on construction equipment (such as pavers and rollers). At the same time, the system also collects status information of construction equipment, such as the vehicle equipment feature information of asphalt mixing plants, asphalt transfer trucks, pavers and rollers. The above collected information will be transmitted to the digital twin platform in real time to provide a basis for subsequent virtual scene construction and scheduling decisions.

[0031] Furthermore, the digital twin platform receives information from the data acquisition unit and constructs a virtual road construction scene that integrates time and space according to the preset information splicing rules. During the construction process, the system scans and splices multiple times to ensure that continuous and uninterrupted road surface temperature scanning information is obtained, and associates this information based on the equipment GNSS positioning information to form local temperature field information. Then, the system associates and fuses the local temperature field information with the corresponding meteorological data information, and finally constructs a complete virtual road construction scene.

[0032] Furthermore, the construction scheduling control unit uses the pre-trained road surface temperature attenuation prediction model to predict the construction environment information obtained from each construction stage. The model can predict the change results of road surface temperature attenuation under different preset scenarios (such as different locations at the same time, and the same location at different times). Then, based on the prediction results, the construction scheduling control unit can schedule the construction strategy for the relevant construction equipment, such as adjusting the operating parameters of the construction equipment, optimizing the construction sequence, etc., to ensure construction quality and efficiency.

[0033] Example 2 refer to Figures 1 to 8 Based on the same inventive concept as Example 1, this example introduces a road construction scheduling method based on multi-environmental information digital twin, which is suitable for the road construction scheduling system based on multi-environmental information digital twin as described in Example 1. The relevant structural design and specific function implementation process used in the road construction scheduling method are described as follows.

[0034] like Figure 1 As shown in the figure, during the road paving process, road construction consists of multiple stages. The material truck pours asphalt into the paver, the paver paves the road surface, the primary roller performs initial vibration compaction, the secondary roller and the final roller perform multiple rolling in different ways, and different construction processes and rolling strategies are used when the road surface experiences temperature decay at different stages, until the road surface temperature cools to a certain level and the rolling is stopped.

[0035] In view of this, the present embodiment proposes the concept of construction pavement temperature field. The vehicle-mounted infrared thermal imaging scanner carried by the equipment at different stages scans the temperature of the paved pavement. The temperature scanning range covered in each stage is different. The specific position of the scanned pavement is determined according to the GNSS information of the equipment. According to the principle of local splicing within the stage first and overall splicing between stages, the road temperature fields of the four stages of road paving are spliced ​​together, thereby reproducing the relevant physical model of the pavement temperature during the road paving construction process.

[0036] This embodiment also uses a temperature field matrix to replace the data processing process of the infrared thermal imaging image. Figure 3 ,Infrared thermal imaging images can be obtained through the vehicle-mounted infrared thermal imaging scanner. The part with the best image quality in the picture is selected, such as the middle row of the picture, and it is divided into squares of the same size per unit area. The thermal imaging image of the area is replaced by measuring the average temperature within the unit area. The temperature values ​​of multiple unit areas are spliced ​​to obtain the temperature distribution of an area with a fixed length and width.

[0037] It is worth noting that during the actual measurement process, the construction equipment is continuously moving. When the distance moved by the equipment in a certain direction exceeds the range of a single scan, a second scan will be performed, and the areas scanned twice are continuous and uninterrupted. The scanned temperature data is fixed and spliced ​​through GNSS positioning information to obtain the pavement temperature field matrix. Different colors are used to represent the temperature range to restore the low-resolution thermal imaging image. This method replaces the thermal imaging image with numerical text, which occupies less storage space and is more convenient for data transmission and storage. It greatly improves the processing and analysis capabilities of pavement temperature distribution information and is highly practical.

[0038] The vehicle-mounted infrared thermal imaging scanner mentioned above is installed at a higher position on the paver and roller. The scanning principle diagram is as follows: Figure 2 As shown. The scanning schematic diagram of the vehicle-mounted infrared thermal imaging scanner is represented by a three-dimensional coordinate system, point A is the installation position of the infrared thermal imager, the scanning direction is toward the y-axis, the x-axis represents the scanning width, the point where the thermal imager is vertically projected to the ground is set as the origin O, and the length of OA represents the height of the thermal imager. Since the field of view angle of the thermal imager is a fixed angle ∠BAC, the actual scanning width BC is determined by the pitch angle ∠OAD. When the resolution is fixed, as the pitch angle increases, the scanning width increases, the unit area of ​​the scanned range will increase, and the area of ​​the fixed number of temperature sampling points divided will become larger, resulting in a decrease in the resolution of the road temperature field. The vehicle-mounted infrared thermal imaging temperature scanner for the paver provided in this embodiment has the characteristics of wide width and large scanning range, and the vehicle-mounted infrared thermal imaging temperature scanner for the roller has the characteristics of fast speed and short scanning cycle. Both can obtain the road asphalt temperature and its distribution by scanning the road asphalt temperature.

[0039] The digital twin platform mentioned above specifically involves a digital twin model of a road construction scene based on multi-environmental information. Figure 4 , the construction process of the digital twin model is as follows: The digital twin model refers to: restoring the real environment or scene by collecting real physical data, building a virtual environment, and then predicting and evaluating the changes in the real scene through virtual simulation technology, and reacting to the real environment.

[0040] Since the temperature attenuation of the pavement is affected by many factors, including natural factors, material preparation factors, construction technology and transportation conditions, among which the material preparation factors directly affect the characteristics of the pavement temperature attenuation, the type, proportion and preparation process of the paving materials directly affect the physical properties of the material cooling, and the construction technology and transportation conditions are both artificially controllable. For example, there is a direct relationship between the temperature loss of asphalt during transportation and the thermal insulation performance of the asphalt transfer vehicle, the transportation distance and the construction waiting time. The cooling behavior of the paving material from paving to rolling to cooling is most obviously affected by natural environmental factors (meteorological data information). Ambient temperature, humidity, atmospheric pressure, wind speed and wind direction can directly affect the local and overall temperature attenuation trend of the paved pavement.

[0041] Therefore, this embodiment will introduce in detail the construction environment information splicing process of the road surface temperature scanning information based on the equipment GNSS positioning information and meteorological data information. The road surface temperature field scanning data obtained by a single device can be positioned by GNSS, and the single device road surface temperature field information can be spliced ​​into stage road surface temperature field information. At the same time, the stage meteorological data and road surface temperature field information are divided according to the stage and integrated. The impact of the meteorological environment at different stages on the road surface temperature change can be accurately analyzed to more carefully analyze the relationship between natural environment information and road surface temperature changes. Finally, through GNSS positioning and splicing, the overall temperature distribution of the construction road surface is obtained, and the temperature of each stage is affected by the natural environment of each stage.

[0042] At the same time according to Figure 7 For the digital twin model part, after the construction environment information is spliced, it is combined with the construction equipment status information to jointly construct a digital twin model. The road construction equipment that needs to be collected for the road construction equipment status information includes: asphalt mixing plants, asphalt transfer trucks, pavers, rollers and other engineering machinery equipment involved in road construction. The working status information and key construction index parameters of these equipment need to be collected. The specific collection process includes: obtaining the vehicle's own status through the vehicle communication bus, such as vehicle speed, engine status, positioning information and other equipment characteristic information; and obtaining sensor values ​​through network communications such as large-area MESH local area networks arranged at the construction site, such as other functional devices of the vehicle that can reflect the construction quality.

[0043] The digital twin model can view the status of the construction site in real time, view the construction information of different locations according to the location, and trace back the historical data according to time. At the same time, the digital twin model records the historical construction data, which is used for the training of the neural network model in the subsequent road construction scheduling system, providing a data basis.

[0044] Furthermore, using machine learning technology, the relevant data sets are trained using the long short-term memory network (LSTM). This neural network can use historical information to process sequence data, which can improve the stability and prediction accuracy of the prediction model and obtain more ideal prediction data. The specific operation process of LSTM is shown in the following formula: ; In the formula, represents the input gate, represents the activation function, represents the weight of the input gate, Indicates the hidden state, Represents the input at the current time. represents the forget gate, represents the weight of a part of the forget gate, represents the weight of the other part of the forget gate, represents the output gate, represents the weight of the output gate, Indicates the cell state at the current time, Indicates the cell state at the previous time. Indicates the output at the current time.

[0045] The internal operation process of the above-mentioned long short-term memory network can be divided into the following four steps: The first step is to calculate the forget gate to determine which part of the input information should be forgotten from the cell state at the previous moment. The second step is to calculate the input gate, which determines which information should be added to the cell state from the input at the current moment. The third step is to calculate the output gate to determine which information should be output from the cell state to the hidden layer state. The fourth step is to update the cell state and the hidden layer state, and perform a weighted combination based on the values ​​of the forget gate, input gate, and output gate to determine the final output. In this way, the correlation between the changes before and after the data in a long span can be effectively obtained.

[0046] Temperature decay prediction is a typical time series prediction problem. The decay rate of road asphalt temperature is affected by a variety of natural environmental factors, and different types of natural environmental factors have different degrees of influence on temperature decay. They are regarded as "weights" in neural networks, and different factors have different weights. Through the long short-term memory network (LSTM), not only can we get different time ranges. It can make it a temperature decay model affected by a variety of natural environmental factors, with the ability to predict temperature in short-term, medium-term, and long-term time ranges. Among them, the short-term time range can reflect the temperature decay of the same rolling stage at the same location, the medium-term time range refers to the temperature decay of different rolling stages at the same location, and the long-term time range refers to the temperature decay of the material at the same location from the paving stage of the paver to the complete cooling.

[0047] Figure 5 The specific implementation process of using neural network training is shown as follows: Before using a neural network to train the model, it is necessary to design a reasonable structure for the data set used for model training. This embodiment mainly trains the neural network model for two scenarios. Scenario 1 is the impact of natural environmental factors on road surface temperature changes at different locations at the same time, and scenario 2 is the impact of natural environmental factors on road surface temperature changes at the same location at different times. The data required for training is collected and recorded by the digital twin model, and the data set is designed according to different scenarios. The data set required for scenario one includes road surface temperature information, various meteorological data (including ambient temperature, humidity, wind force, wind direction, atmospheric pressure and other factors that affect temperature attenuation) and GNSS positioning information. The collected data set also needs to be preprocessed by the relevant system to process the data into a CSV format data set sample that meets the requirements of neural network training.

[0048] Furthermore, the processed samples need to be divided into training set and test set according to a certain ratio. Specifically, the data is imported and the data length is obtained. The range from the beginning of the total data set to the position where the total data length is multiplied by the set ratio is the training set data, and the test set data is from the end of the training set data to the end of the total data set. The purpose of dividing the data for testing is to verify whether the error between the predicted result of the trained model and the true value meets the requirements. Among them, the neural network model training process under different scenarios can be referred to respectively. Figure 6 and Figure 7 .

[0049] Specifically, at different locations at the same time, the meteorological data information and road surface temperature information of each stage of road construction will be divided according to the stage, and each piece of data will be composed of five parts: time, meteorological data and temperature data of the paving stage, meteorological data and temperature data of the initial pressure stage, meteorological data and temperature data of the re-pressure stage, and meteorological data and temperature data of the final pressure stage. At the same location but at different times, the composition of the data is similar to the other case, the difference is that the time of the first part of the data composition will be replaced by the location, and the data of subsequent stages will be changed from the same time data to the same location data. In the case of scenario 1, the time is the reference value of each piece of data, and in the case of scenario 2, the GNSS information is the reference value of each piece of data.

[0050] Furthermore, through the training of the long short-term memory network (LSTM), the correlation between temperature attenuation and natural environmental factors at the same time at different locations and at different times at the same location can be obtained, as well as the weight of each factor's influence on temperature attenuation. By comparing the influence of natural environmental factors on the pavement temperature changes at different locations, that is, at different construction stages at the same time, the correlation between the overall construction temperature attenuation and natural environmental factors can be accurately reflected; and by comparing the pavement temperature changes at different time periods at the same location, that is, in a fixed construction area, the correlation between local construction temperature and natural environmental factors can be accurately reflected.

[0051] Furthermore, different scenario models are trained using data sets compiled from historical data to obtain ideal temperature attenuation prediction models for temperature attenuation and natural environmental factors in different scenarios. By detecting meteorological data and real-time temperature scanning data at different construction stages, the trend of further temperature changes in the current natural environment can be determined based on model analysis. The road construction system adjusts the construction process in real time based on the determined temperature change trend.

[0052] In other words, the neural model is built and trained through historical data, tested with real-time data, and the prediction results are used to guide road construction scheduling. The overall construction link is regarded as a feedback control link, and the real-time detection of the construction pavement temperature field is used as the input of the system. The stable pavement temperature attenuation is regarded as the stable road paving quality. When natural environmental factors disturb the system, road construction equipment needs to be scheduled, and the construction process and related parameters need to be adjusted to reduce or offset the impact of natural environmental factors on pavement temperature attenuation.

[0053] It is worth noting that the road construction equipment status information obtained in the above manner basically covers the key parameters of the designed road paving quality, such as the positioning information of each device under construction, the driving speed and real-time specific position of the asphalt transfer vehicle, the paving speed of the paver, the screed status, and other key parameters related to paving quality control are collected and obtained, which plays an important role and reference value in judging the working status of the current equipment, and can further reflect the relationship between road construction quality and the status of road construction equipment. By collecting road construction equipment status information to obtain the working status and overall progress of construction equipment, it can reflect the construction efficiency and scheduling situation, which is conducive to mastering the overall construction dynamics.

[0054] In addition, since the influence of natural environmental factors has both advantages and disadvantages, when it has an adverse effect on the temperature attenuation of the pavement, adjusting the construction process can weaken the adverse effect. When the multi-environmental information is better than the predicted conditions, the construction equipment can enter the energy-saving mode by reducing the operating intensity and operating power of the construction equipment, so as to achieve the purpose of energy saving and emission reduction and optimize the construction process.

[0055] Figure 8 The specific implementation process of the road construction scheduling method based on multi-environment information digital twin is shown. By combining the construction environment information and the construction equipment status information to form a digital twin model, by retaining historical data and using machine learning and neural network training techniques, a road surface temperature attenuation prediction model affected by natural environmental factors and the road surface temperature attenuation under ideal conditions are trained. The road surface temperature change trend is further predicted based on actual data, and a construction equipment scheduling plan is provided to change the construction scheduling and construction process in real time, so as to achieve the purpose of intelligent construction and digital construction.

[0056] Furthermore, the adjustment of a single device is mainly to deal with the detection of temperature anomalies in a small area. At this time, the adverse effects of sudden changes in road surface temperature can be improved by using methods such as the vibration state of the roller and increasing the number of rolling passes; the adjustment of group equipment is mainly to deal with the abnormal changes in regional multi-environmental information. At this time, the paver can be used to increase the paving speed, increase the heating temperature of the ironing plate, the roller can be used to increase the rolling speed and shorten the rolling cycle, the roller can be used to increase the number of rolling passes for additional compaction, and the material truck can be used to increase the transportation speed and adjust the material delivery cycle. The adjustment of the overall construction cycle is based on weather. By detecting multi-environmental information and predicting the weather, the construction progress of the overall construction section can be adjusted, and the construction distance and the amount of asphalt processing in the construction cycle can be reasonably planned.

[0057] Taking the actual construction scene as an example, by collecting real-time temperature scanning data of the paver and roller cluster during asphalt paving, collecting meteorological data at each construction stage, collecting GNSS information and real-time status information of equipment involved in road construction (including asphalt trucks, asphalt mixing plants, etc.), and uploading their respective information through the network, the digital twin model will reproduce the real-time pavement temperature distribution of the construction site, real-time meteorological data at each stage, real-time GNSS positioning of each equipment and equipment operation status, simulate the real-time status of the construction site and asphalt material processing and material truck transportation, and view historical construction data at the same time. The road construction scheduling system makes judgments on the real-time overall or local multi-environmental information anomalies based on the model trained by the neural network, judges the advantages or disadvantages of road construction, predicts the pavement temperature changes under abnormal conditions, and dispatches construction equipment at different stages to make overall or local construction process adjustments. By changing the number of rolling passes, speeding up or shortening the paving speed, changing the ironing plate temperature, changing the vibration frequency, shortening or increasing the asphalt material processing speed, and the transportation speed of the transfer truck, the purpose of improving construction quality and efficiency can be achieved.

[0058] Example 3 This embodiment introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the road construction scheduling method based on multi-environmental information digital twin as described in Example 2 are implemented.

[0059] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0063] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A road construction scheduling system based on multi-environment information digital twin, characterized in that: include: A data acquisition unit, a digital twin platform, and a construction scheduling control unit that are communicatively connected to each other; The data acquisition unit is used to respectively acquire the construction environment information and the construction equipment status information of the paver paving stage, the roller initial compaction stage, the roller recompaction stage and the roller final compaction stage, and transmit the construction environment information and the construction equipment status information corresponding to different construction stages to the digital twin platform; The digital twin platform is used to construct a virtual road construction scene integrating time and space based on the received construction environment information and construction equipment status information corresponding to different construction stages and preset information splicing rules; The construction scheduling control unit is used to input the construction environment information obtained from the paver paving stage, the roller initial compaction stage, the roller re-compaction stage and the roller final compaction stage into a pre-trained pavement temperature attenuation prediction model to obtain the pavement temperature attenuation change results corresponding to different preset scenarios, and then schedule the construction strategy of related construction equipment according to the pavement temperature attenuation change results.

2. The road construction scheduling system based on multi-environment information digital twin according to claim 1 is characterized in that: The construction environment information includes: road surface temperature scanning information, meteorological data information and equipment GNSS positioning information at different construction stages; the construction equipment status information includes at least: vehicle equipment characteristic information corresponding to the asphalt mixing plant, asphalt transfer vehicle, paver and roller; The road surface temperature scanning information is collected by an infrared thermal imager installed on the paver and the roller; the meteorological data is collected by a vehicle-mounted micro-meteorological station installed on the paver and the roller; The meteorological data information includes: one or more of temperature, humidity, atmospheric pressure, wind speed and wind direction.

3. The road construction scheduling system based on multi-environment information digital twin according to claim 2 is characterized in that: Based on the received construction environment information and construction equipment status information corresponding to different construction stages, as well as the preset information splicing rules, a virtual road construction scene integrating time and space is constructed, including: During each construction phase, when the distance moved by the construction equipment in a certain direction exceeds the preset single scan range, a second scan is performed until the construction equipment completes the entire scan within the corresponding preset overall scan coverage range, thereby obtaining several sets of continuous and uninterrupted road surface temperature scanning information; splicing the plurality of groups of continuous and uninterrupted road surface temperature scanning information according to the equipment GNSS positioning information to obtain the local temperature field information in each construction stage; Obtain the meteorological data information collected at each construction stage, associate and fuse the local temperature field information at each construction stage with the corresponding meteorological data information to obtain associated and fused information; The associated and fused information is spliced ​​according to the equipment GNSS positioning information to construct a virtual road construction scene integrating time and space.

4. The road construction scheduling system based on multi-environment information digital twin according to claim 3 is characterized in that: In the process of determining the local temperature field information in each construction stage, the middle row area of ​​the thermal imaging image within a single preset scannable range is selected as the splicing object of the local temperature field information; wherein the confirmation process of the splicing object includes: The middle row area is divided into several squares of the same area, the average temperature within the unit area is measured, and the average temperature values ​​of each unit area are spliced ​​to obtain the temperature distribution of an area with a fixed length and width as the splicing object of the local temperature field information.

5. The road construction scheduling system based on multi-environment information digital twin according to claim 1 is characterized in that: The road surface temperature attenuation prediction model includes: a temperature attenuation and natural environmental factor correlation model at different locations at the same time, corresponding to preset scenario one, and a temperature attenuation and natural environmental factor correlation model at the same location at different times, corresponding to preset scenario two.

6. A road construction scheduling method based on multi-environmental information digital twins applicable to the road construction scheduling system based on multi-environmental information digital twins as described in any one of claims 1 to 5, characterized in that: include: Obtain construction environment information corresponding to the paving stage of the paver, the initial compaction stage of the roller, the secondary compaction stage of the roller, and the final compaction stage of the roller; Inputting the construction environment information into a pre-trained road surface temperature attenuation prediction model to obtain road surface temperature attenuation change results corresponding to different preset scenarios; According to the pavement temperature attenuation change results, construction strategy scheduling is performed on relevant construction equipment.

7. The road construction scheduling method based on multi-environment information digital twin according to claim 6 is characterized in that: The construction environment information includes: equipment GNSS positioning information, meteorological data information and pavement temperature scanning information during the paving stage of the paver, meteorological data information and pavement temperature scanning information during the initial compaction stage of the roller, meteorological data information and pavement temperature scanning information during the secondary compaction stage of the roller, and meteorological data information and pavement temperature scanning information during the final compaction stage of the roller.

8. The road construction scheduling method based on multi-environment information digital twin according to claim 7 is characterized in that: The road surface temperature attenuation prediction model adopts a long short-term memory network, and its calculation formula is as follows: ； In the formula, represents the input gate, represents the activation function, represents the weight of the input gate, Indicates the hidden state, Represents the input at the current time, represents the forget gate, represents the weight of a part of the forget gate, represents the weight of the other part of the forget gate, represents the output gate, represents the weight of the output gate, Indicates the cell state at the current time, Indicates the cell state at the previous time. Indicates the output at the current time.

9. The road construction scheduling method based on multi-environment information digital twin according to claim 8 is characterized in that: The different preset scenarios include: preset scenario one and preset scenario two; scenario one is the impact of natural environmental factors on road surface temperature changes at different locations at the same time, and scenario two is the impact of natural environmental factors on road surface temperature changes at the same location at different times.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the road construction scheduling method based on multi-environmental information digital twin described in any one of claims 6 to 9 are implemented.

Images