Ice aggregate layered spreading and filling control method and control system thereof

Abstract

The invention discloses an ice aggregate layered spreading and filling control method and a control system thereof, and relates to the technical field of ice aggregate construction. The method comprises the following steps: constructing a digital twinborn model, acquiring and transmitting data, establishing an energy consumption prediction model, optimizing construction parameters and equipment operation strategies, and controlling layered spreading and filling. The construction process is simulated and dynamically monitored in real time by constructing the digital twinborn model of the whole construction process of the ice aggregate, the construction parameters and the equipment operation state can be obtained in real time in combination with the data acquisition and transmission technology, and then the energy consumption prediction model and the construction parameter optimization are used for predicting the energy consumption of the ice aggregate. The precise control not only improves the construction efficiency of layered spreading and filling of the ice aggregate, but also ensures the consistency and stability of the construction quality.

Description

Technical Field

[0001] This invention relates to the field of ice aggregate construction technology, specifically to a method and control system for layered spreading and filling of ice aggregate. Background Technology

[0002] With the continuous advancement of infrastructure construction, ice aggregate, as a special building material, has shown unique advantages in cold regions and specific engineering conditions, such as good frost resistance, stability and certain load-bearing capacity. The layering and filling process of ice aggregate is directly related to the overall quality and durability of the engineering structure.

[0003] Traditional ice aggregate construction methods have the following main drawbacks: First, the construction quality is highly dependent on the experience and skill level of the operators. Differences in operation between different personnel can easily lead to fluctuations in construction quality, making it difficult to ensure the consistency and stability of construction quality. Second, traditional methods lack the ability to monitor and dynamically adjust construction parameters in real time, and cannot respond in a timely manner to changes in the construction process, such as the impact of environmental temperature and humidity on the melting and bonding of ice aggregate, thereby affecting the filling quality and construction efficiency.

[0004] In view of the problems of unstable quality, waste of resources, low construction efficiency and lack of emergency response mechanism in traditional ice aggregate construction methods, the present invention proposes a method for controlling the layered spreading and filling of ice aggregate and its control system, which is of particular importance. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a method and control system for the layered spreading and filling of ice aggregate. By constructing a digital twin model of the entire ice aggregate construction process, combined with data acquisition and transmission technology, energy consumption prediction model, and construction parameter optimization strategy, it achieves real-time simulation and dynamic monitoring of the construction process. This system can not only accurately control key construction parameters such as spreading amount and filling pressure to ensure the consistency and stability of construction quality, but also effectively reduce energy consumption and construction costs, and improve economic benefits.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On one hand, a method for controlling the layered spreading and filling of ice aggregate, the specific steps of which are as follows: Steps for building a digital twin model: Using 3D modeling technology, based on the design drawings and actual terrain data of the ice aggregate construction project, a digital twin model of the entire ice aggregate construction process is built. This model covers the construction site, spreading equipment, filling equipment, and ice aggregate material characteristics information, and can simulate the dynamic process of layered spreading and filling of ice aggregate in real time. Data acquisition and transmission steps: Install various sensors on the construction equipment, including spreading amount sensor, filling pressure sensor, and equipment operating status sensor, to collect data on the spreading amount of ice aggregate, filling pressure, equipment operating speed, and fuel consumption in real time, and transmit the collected data to the data processing center through a wireless network; Steps for establishing an energy consumption prediction model: The data processing center receives the collected data, combines it with the construction process data simulated by the digital twin model, and uses machine learning algorithms to establish an energy consumption prediction model for ice aggregate construction. This model takes construction parameters and equipment operating status as input variables and energy consumption as output variable, and can predict energy consumption under different construction parameters and equipment operating strategies. Construction parameter and equipment operation strategy optimization steps: Input the construction schedule requirements and quality standards into the energy consumption prediction model, and through the model's calculation and analysis, obtain the construction parameters and equipment operation strategies that meet the construction requirements and have the lowest energy consumption. Layered spreading and filling control steps: Based on the optimized construction parameters and equipment operation strategy, control the operation of spreading and filling equipment to achieve precise layered spreading and filling of ice aggregate. At the same time, during the construction process, the actual construction data is fed back to the digital twin model and energy consumption prediction model in real time, and the models are dynamically corrected and optimized to ensure that the construction process is always in the optimal state.

[0007] Furthermore, in the step of constructing the digital twin model, the 3D modeling technology adopts a modeling method based on an improved octree algorithm. By spatially discretizing the design drawings and actual terrain data, the construction area is divided into multiple 3D voxels. Considering the characteristics of ice aggregate materials, a particle model library is established for ice aggregates of different sizes and shapes. Using the Monte Carlo simulation method, particle models are randomly selected and distributed in the model according to the actual gradation of the ice aggregate, thereby improving the realism and accuracy of the digital twin model in simulating the ice aggregate construction process. The specific construction process of the improved octree algorithm is as follows: Let the initial 3D space be... Its side length is During the first division, Divide into 8 equal small cubes, each with a volume of . The side length is For each small cube, based on the design drawings and terrain data contained within, it is determined whether further subdivision is needed. If the internal data of the small cube is complex, and there are areas with significant differences in the morphology of different types of construction equipment components or aggregate accumulation, then further subdivision is performed. Let the volume of the small cube after the nth subdivision be... The side length is This process continues until the set subdivision accuracy requirements are met. These accuracy requirements can be determined based on the minimum dimensions of key construction parts. For the critical area near the ice aggregate spreading port, the subdivision accuracy should ensure that the initial distribution state of the ice aggregate during the spreading process can be accurately simulated. In this way, a more refined digital twin model infrastructure that conforms to the actual construction situation can be built.

[0008] Furthermore, in the data acquisition and transmission step, a novel spreading quantity detection device based on the ultrasonic time-difference method is used for the spreading quantity sensor. This device has ultrasonic transmitting and receiving probes installed opposite each other on both sides of the spreading pipe, and measures the time difference of ultrasonic wave propagation in the ice aggregate flow. Combined with pipe diameter And the empirical formula for the propagation speed of ultrasound in ice aggregate. ,in As the reference speed, A coefficient related to the properties of ice aggregate. The real-time density of the ice aggregate is calculated using data from pressure and temperature sensors combined with the ice aggregate state equation, and then using the formula... Calculate the amount of ice aggregate to be spread ,in To determine the ultrasonic propagation path length, a fiber Bragg grating pressure sensor is used for filling pressure sensors. The principle is that when pressure is applied to the fiber grating, the grating period... Changes occur, according to the Prague conditions. ,in For the Bragg wavelength, To determine the effective refractive index, changes in the wavelength of the reflected light are detected. The calibration relationship between pressure and wavelength changes is used. Get filling pressure ,in To calibrate the coefficients, a wireless network transmission protocol based on a combination of time division multiple access and orthogonal frequency division multiplexing is adopted for data transmission. Different sensor data are transmitted in an orderly manner according to time slices and frequency subcarriers, which improves the stability and anti-interference ability of data transmission and ensures that real-time data during the construction process can be transmitted to the data processing center accurately.

[0009] Furthermore, in the step of establishing the energy consumption prediction model, the machine learning algorithm used is an improved adaptive neural fuzzy inference system algorithm. First, the set of input variables is determined. ,in These represent construction parameters and equipment operating status variables, respectively, including spreading speed, filling thickness, equipment operating speed, and energy consumption. By performing cluster analysis on the collected data, the data is divided into different fuzzy subsets, each corresponding to a construction condition. For each fuzzy subset, a Gaussian membership function is used. To describe input variables Belongs to fuzzy sets The degree, of which The center of the membership function, The width is initially determined through data statistical features and expert experience, and is continuously adjusted during subsequent training. The fuzzy rule base is constructed based on construction experience and data features. Then, a hybrid learning algorithm combining least squares and gradient descent is used to train the parameters of the ANFIS model. During training, the prediction error is analyzed... ,in To obtain the model's predicted values, the parameters of the membership function are continuously adjusted. , The parameters of the fuzzy rule consequents are used to minimize the prediction error. After multiple iterations of training, the model can accurately predict energy consumption under different construction parameters and equipment operation strategies.

[0010] Furthermore, in the optimization steps of construction parameters and equipment operation strategies, the construction schedule requirements are transformed into construction time constraints. The quality standard is transformed into the lower limit of compaction degree for ice aggregate filling. and spreading uniformity index In the calculation process of the energy consumption prediction model, a simplified comprehensive constraint function is introduced. The system quantifies situations where construction requirements are not met, prompting the model to output a comprehensive constraint function that balances construction progress, quality, and energy consumption. The calculation formula is: ,in, These are constraint weighting coefficients for construction time, filling compaction degree, and spreading uniformity, which are set by the engineering team based on the project's emphasis on schedule and quality. , , For the status judgment variable, when the actual construction time hour ,otherwise When the actual compaction degree hour, ,otherwise When the actual spreading uniformity hour, ,otherwise In the calculation of comprehensive energy consumption in the energy consumption prediction model At that time, the comprehensive constraint function will be Compared with the basic energy consumption forecast value Combined, the calculation formula is as follows: ,in The amplification factor is used to adjust the degree of influence of constraints on energy consumption. The model uses an optimization algorithm to find the optimal factor in the parameter search space. The minimum combination of construction parameters and equipment operation strategies, including the speed of ice aggregate spreading, filling thickness, equipment operating speed and start-up and shutdown time, achieves a balanced optimization of construction progress, quality and energy consumption.

[0011] Furthermore, in the layered spreading and filling control step, the spreading equipment adopts a closed-loop control method during the layered spreading and filling control process, and the optimized spreading speed setpoint is used. During the process, the spreading equipment adopts a closed-loop control method, and the spreading speed feedback value is obtained in real time by the spreading quantity sensor. Comparisons are made, and the control quantity is calculated using a PID controller. ,in For speed deviation, This is the proportionality coefficient. The integral time constant is... These parameters, which are differential time constants, are determined using a parameter optimization method based on a genetic algorithm, and the control quantity... The drive motor of the spreading equipment is adjusted to control the spreading speed precisely. For the filling equipment, the pressure value fed back by the filling pressure sensor is compared with the set filling pressure range. When the pressure is lower than the lower limit, the compaction frequency or force of the filling equipment is increased. When the pressure is higher than the upper limit, the compaction frequency or force is appropriately reduced to ensure that the compaction degree of the aggregate always meets the quality standards during the filling process. At the same time, the running trajectory of the spreading and filling equipment is fine-tuned based on the real-time feedback of the digital twin model to avoid equipment collisions and construction dead zones, thereby improving the overall accuracy and efficiency of construction.

[0012] Furthermore, an environmental factor compensation mechanism is introduced throughout the construction process. This involves using temperature and humidity sensors and wind speed sensors installed at the construction site to collect ambient temperature data in real time. ,humidity Wind speed Environmental data was used to analyze the effects of ambient temperature and humidity on the melting and adhesion of ice aggregates during the spreading process. A state correction model for ice aggregates was established, and the melting rate was obtained by fitting experimental data to determine the influence of ambient temperature and humidity on the melting and adhesion of ice aggregates. The relationship with ambient temperature and humidity is ,in , , The melting rate is used as a fitting coefficient to correct the spreading amount and spreading uniformity. For the filling process, the influence of wind speed on dust generation and compaction of the ice aggregate is considered. When the wind speed exceeds a certain threshold... At the same time, by adjusting the compaction parameters of the filling equipment, the filling quality is ensured to be unaffected by excessive interference from environmental factors. Meanwhile, environmental factor data is used as an additional input variable and integrated into the digital twin model and energy consumption prediction model, so that the model can more accurately reflect the actual construction situation and further improve the accuracy and stability of construction control.

[0013] Furthermore, to address unforeseen circumstances during construction, an emergency decision-making module is established. This module monitors the operational status data of construction equipment and key indicator data during construction in real time. When an unforeseen situation is detected, the emergency decision-making module is quickly activated. First, it uses a digital twin model to simulate and analyze the unforeseen situation, assessing its impact on construction progress, quality, and energy consumption. Then, based on a pre-set emergency strategy library, combined with the current construction status and impact assessment results, it selects the optimal emergency response plan. When a malfunction is detected in the spreading equipment, if the malfunction can be repaired in a short time, the emergency decision-making module adjusts the construction plan, suspends the operation of other related equipment, and prioritizes the repair of the spreading equipment. If the malfunction takes a long time to repair, a backup spreading plan is selected from the emergency strategy library, such as activating temporary spreading equipment or adjusting the supply method of ice aggregate. At the same time, the energy consumption prediction model and construction parameter optimization strategies are adjusted accordingly to minimize the impact of unforeseen circumstances on construction progress and energy consumption while ensuring construction quality, thus ensuring the continuity and stability of the construction process.

[0014] Furthermore, after construction is completed, a post-construction analysis of the entire construction process is conducted. The simulated data from the digital twin model, the actual construction data, and the results of the energy consumption prediction model are compared to evaluate the execution effect of the construction process. Through data mining technology, the potential relationships between construction parameters, equipment operation strategies, construction quality, and energy consumption are analyzed to uncover key factors affecting construction quality and energy consumption. Through association rule analysis, a strong correlation is found between the combination of spreading speed and filling thickness and higher compaction degree and lower energy consumption. These analysis results are fed back into the construction of the digital twin model and the optimization of construction parameters for the next construction phase, continuously optimizing construction technology and control methods, forming a continuous improvement mechanism for the construction process, and further improving the overall level and economic benefits of ice aggregate construction.

[0015] On the other hand, a layered spreading and filling control system for ice aggregate includes a data acquisition and transmission module, a model building module, a parameter and strategy optimization module, an equipment control execution module, and a feedback and optimization iteration module. The data acquisition and transmission module consists of various sensors installed on the construction equipment, such as a spreading amount sensor, a filling pressure sensor, and an equipment operating status sensor, as well as a wireless network transmission component. The sensors collect relevant data during the construction process in real time, such as the spreading amount of ice aggregate, filling pressure, equipment operating speed, and fuel consumption. The wireless network transmission component adopts a transmission protocol that combines time division multiple access and orthogonal frequency division multiplexing to stably and accurately transmit the collected data to the data processing center, realizing efficient data flow from the acquisition end to the processing end. The model building module utilizes 3D modeling technology to construct a digital twin model of the entire construction process based on the design drawings, actual terrain data, and material properties of the ice aggregate construction project. It employs an improved octree algorithm to simulate the dynamic process of layered spreading and filling of ice aggregate in real time. After receiving the collected data and the simulation data from the digital twin model, the data processing center uses an improved adaptive neural fuzzy inference system algorithm to establish an energy consumption prediction model with construction parameters and equipment operating status as inputs and energy consumption as output, providing data support for subsequent optimization. The parameter and strategy optimization module transforms construction progress requirements and quality standards into specific constraints, inputs them into the energy consumption prediction model, introduces a comprehensive constraint function, and combines model calculation and analysis to obtain construction parameters and equipment operation strategies that meet construction requirements and have the lowest energy consumption. It determines key parameters such as ice aggregate spreading speed, filling thickness, and equipment start-up and shutdown time, thereby achieving multi-objective optimization of the construction process. The equipment control and execution module: Based on the output of the parameter and strategy optimization module, it precisely controls the spreading equipment and the filling equipment. It adopts a closed-loop control method, uses a PID controller to adjust the spreading speed of the spreading equipment, and adjusts the compaction operation of the filling equipment based on the feedback of the filling pressure sensor. This ensures that the layered spreading and filling of the ice aggregate are executed according to the optimized parameters and strategies, thereby achieving automation and precision in the construction process. The feedback and optimization iteration module collects actual construction data in real time during construction and feeds it back to the digital twin model and energy consumption prediction model to dynamically correct and optimize the models. At the same time, it introduces an environmental factor compensation mechanism to cope with external changes, establishes an emergency decision-making module to handle emergencies, and after construction is completed, it reviews and analyzes the construction data to identify key factors and form a continuous improvement mechanism for the construction process, so that the system can be continuously optimized and upgraded.

[0016] Compared with existing technologies, this method for controlling the layered spreading and filling of ice aggregate and its control system have the following advantages: I. This invention achieves real-time simulation and dynamic monitoring of the construction process by constructing a digital twin model of the entire ice aggregate construction process. Combined with data acquisition and transmission technology, it can obtain construction parameters and equipment operating status in real time. Then, through energy consumption prediction models and construction parameter optimization, it can derive construction parameters and equipment operation strategies that meet construction requirements and have the lowest energy consumption. This precise control not only improves the construction efficiency of ice aggregate layer spreading and filling, but also ensures the consistency and stability of construction quality, effectively avoiding quality fluctuations and resource waste that may occur in traditional construction methods.

[0017] Second, the energy consumption prediction model established by this invention can accurately predict the energy consumption under different construction parameters and equipment operation strategies. By optimizing the construction parameters and equipment operation strategies, it can find the construction scheme that meets the construction requirements and has the lowest energy consumption. This innovation not only helps construction units to effectively reduce energy consumption while ensuring construction quality, but also significantly reduces construction costs and improves economic benefits. At the same time, by introducing an environmental factor compensation mechanism and an emergency decision-making module, the system can flexibly respond to various changes and challenges in the construction process, ensuring the continuity and stability of the construction process, and further reducing additional costs and risks caused by unexpected situations.

[0018] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0020] Figure 1 A flowchart illustrating a method for controlling the layered spreading and filling of ice aggregate; Figure 2 A flowchart of a control system for layered spreading and filling of ice aggregate; Figure 3 This is a flowchart of the key modules of a method for controlling the layered spreading and filling of ice aggregate and its control system. Detailed Implementation

[0021] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0022] Example 1 In the construction of hydropower dams in high-altitude areas, the layering and filling quality of ice aggregate directly affect the stability and safety of the dam. The method of this invention can achieve precise and efficient construction.

[0023] First, a digital twin model was constructed. Considering the complex terrain, diverse construction equipment, and large quantity of ice aggregate in the hydropower station dam construction area, a 3D modeling technique based on an improved octree algorithm was used. The structural details of the dam in the design drawings were combined with the actual terrain data of the construction site. The entire construction site was spatially discretized, dividing it into multiple 3D voxels. Simultaneously, a specialized particle model library was established for ice aggregates of different sizes and shapes. A digital twin model including the construction site, spreading vehicles, vibratory rollers, and ice aggregate characteristics was constructed using Monte Carlo simulation. The algorithm construction process is as follows: Let the initial 3D space be... Its side length is During the first division, Divide into 8 equal small cubes, each with a volume of . The side length is For each small cube, based on the design drawings and terrain data contained within, it is determined whether further subdivision is needed. If the internal data of the small cube is complex, and there are areas with significant differences in the morphology of different types of construction equipment components or aggregate accumulation, then further subdivision is performed. Let the volume of the small cube after the nth subdivision be... The side length is The model continues until the set subdivision accuracy requirements are met. These accuracy requirements can be determined based on the minimum dimensions of key construction parts. The model can fully simulate the entire process from transporting ice aggregate to layered filling.

[0024] Next, we move on to the data acquisition and transmission stage. Ultrasonic time-of-flight sensors based on the ultrasonic method are installed on both sides of the spreading pipe of the spreading vehicle to monitor the spreading of the ice aggregate in real time. Fiber Bragg grating pressure sensors are installed on the compaction wheel of the vibratory roller to accurately acquire pressure data during the filling process. In addition, sensors record information such as the operating speed and fuel consumption of the equipment in real time. This data is transmitted to the data processing center in an orderly and stable manner through a wireless network transmission protocol based on a combination of time division multiple access and orthogonal frequency division multiplexing to ensure that the data is not lost or delayed.

[0025] Then, an energy consumption prediction model is established. The data processing center integrates the collected real-time data with the construction process data simulated by the digital twin model. Using an improved adaptive neuro-fuzzy inference system algorithm, with construction parameters such as spreading speed, filling thickness, and equipment operating speed, as well as equipment operating status, as input variables and energy consumption as the output variable, an energy consumption prediction model is constructed. First, the set of input variables is determined. ,in These represent construction parameters and equipment operating status variables, respectively, including spreading speed, filling thickness, equipment operating speed, and energy consumption. By performing cluster analysis on the collected data, the data is divided into different fuzzy subsets, each corresponding to a construction condition. For each fuzzy subset, a Gaussian membership function is used. To describe input variables Belongs to fuzzy sets The degree, of which The center of the membership function, For the width, a fuzzy rule base is constructed based on construction experience and data features. Then, the parameters of the ANFIS model are trained using a hybrid learning algorithm combining least squares and gradient descent. During training, the prediction error is analyzed... ,in To obtain the model's predicted values, the parameters of the membership function are continuously adjusted. , The model incorporates parameters for fuzzy rule consequents to minimize prediction errors. Through multiple iterations of training, the model is able to accurately predict energy consumption under different construction parameters and equipment operation strategies.

[0026] Next, construction parameters and equipment operation strategies are optimized. Based on the construction schedule requirements of the hydropower station dam, such as completing the filling at a certain elevation within a specified time, and the quality standards for the icing aggregate filling, such as the requirements for compaction degree and spreading uniformity, these factors are input into the energy consumption prediction model. The model then incorporates a comprehensive constraint function. Synthesis constraint function The calculation formula is: ,in, These are the constraint weighting coefficients for construction time, filling compaction degree, and spreading uniformity, respectively. , , As a state-judgment variable, considering factors such as construction time, filling compaction degree, and spreading uniformity, the calculation and analysis yield the construction parameters and equipment operation strategies that can meet the requirements of construction progress and quality while minimizing energy consumption. For example, determining the optimal driving speed of the spreading vehicle and the rolling frequency of the vibratory roller.

[0027] Finally, layered spreading and filling control were implemented. Based on optimized construction parameters and equipment operation strategies, the spreading vehicle and vibratory roller were controlled. The spreading vehicle employed a closed-loop control method, comparing the optimized spreading speed setpoint with the real-time spreading speed feedback value measured by sensors. A PID controller adjusted the drive motor speed to achieve precise layered spreading of the aggregate. The vibratory roller compared the pressure value fed back by the filling pressure sensor with the set pressure range. When the pressure was below the lower limit, the compaction frequency or intensity was increased; when it was above the upper limit, it was decreased to ensure filling quality. During construction, actual construction data was fed back in real-time to the digital twin model and energy consumption prediction model for dynamic correction and optimization. Meanwhile, temperature and humidity sensors and wind speed sensors installed at the construction site collect environmental data in real time. Through an environmental factor compensation mechanism, the spreading amount and uniformity are adjusted according to the ice aggregate state correction model. If the wind speed is too high, the compaction parameters of the vibratory roller will be adjusted appropriately to avoid affecting the filling effect. In case of sudden equipment failure, the emergency decision-making module will be activated quickly, using a digital twin model to simulate and analyze the impact of the failure on construction, and selecting the optimal solution from the preset emergency strategy library. After the construction is completed, the data of the entire construction process will be reviewed and analyzed to identify key factors affecting construction quality and energy consumption, providing experience for the construction of other parts of the dam and continuously optimizing the construction process.

[0028] Example 2 In the construction of railway subgrades in cold regions, the layered spreading and filling of ice aggregates need to cope with complex environments such as low temperature and strong winds. The method of this invention can effectively ensure construction efficiency and subgrade quality.

[0029] First, a digital twin model is constructed. Combining the design drawings of the railway subgrade in cold regions with the actual terrain data of the construction site, a 3D modeling technique based on an improved octree algorithm is used to spatially discretize the construction area and divide it into multiple 3D voxels. Considering the characteristics of the ice aggregate used in the railway subgrade in cold regions, a particle model library with different particle sizes and shapes is established. Through Monte Carlo simulation, a digital twin model containing information on the construction site, spreader, compactor and other equipment as well as ice aggregate is constructed. This model can simulate in detail the dynamic changes of ice aggregate during the layered spreading and filling process of the subgrade.

[0030] In the data acquisition and transmission stage, a spreading quantity sensor based on ultrasonic time difference method is installed on the spreading pipe of the spreader to monitor the spreading quantity of ice aggregate in real time. A fiber Bragg grating pressure sensor is installed at the contact point between the compactor and the roadbed to obtain filling pressure data. At the same time, sensors record data such as the operating speed and fuel consumption of the equipment. This data is accurately transmitted to the data processing center through a wireless network transmission protocol based on a combination of time division multiple access and orthogonal frequency division multiplexing.

[0031] Then, an energy consumption prediction model is established. After receiving the collected real-time data, the data processing center combines the construction process data simulated by the digital twin model and uses an improved adaptive neural fuzzy inference system algorithm. With construction parameters and equipment operating status as inputs and energy consumption as output, an energy consumption prediction model is constructed. This model can predict energy consumption under different construction parameters and equipment operating strategies.

[0032] Next, the construction parameters and equipment operation strategies are optimized. Based on the construction progress requirements of railway subgrade in cold regions, such as completing the filling of a certain section of subgrade before winter, and the quality standards of subgrade filling, these contents are input into the energy consumption prediction model. The model introduces a comprehensive constraint function, which comprehensively considers constraints such as construction time, filling compaction degree, and spreading uniformity. After calculation and analysis, the construction parameters and equipment operation strategies that meet the construction requirements and have the lowest energy consumption are obtained, such as determining the spreading width of the spreader and the travel path of the compactor.

[0033] Finally, layered spreading and filling control were implemented. Following optimized parameters and strategies, the spreader and compactor were controlled. The spreader employed closed-loop control, using a PID controller to adjust its operation based on speed deviations, achieving precise layered spreading of the ice aggregate. The compactor adjusted its compaction operation based on pressure values ​​from filling pressure sensors to ensure filling effectiveness. During construction, actual construction data was fed back in real-time to the digital twin model and energy consumption prediction model for dynamic correction and optimization. Simultaneously, environmental data was collected using temperature and humidity sensors and wind speed sensors. Through an environmental factor compensation mechanism, the spreading amount and uniformity were adjusted based on the ice aggregate condition. When wind speed exceeded a threshold, the compaction parameters of the compactor were adjusted to ensure filling quality. In case of extreme weather or other emergencies, an emergency decision-making module was activated, using the digital twin model to analyze the impact and select the optimal emergency plan. After construction, the construction data was reviewed and analyzed to identify key factors, providing a reference for subsequent construction of other sections of the cold-region railway and continuously optimizing the construction process.

[0034] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content without departing from the scope of the technical solution of the present invention, and any simple modifications, alterations and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A method for controlling the layered spreading and filling of ice aggregate, characterized in that, The specific steps of this method are as follows: Steps for building a digital twin model: Using 3D modeling technology, based on the design drawings and actual terrain data of the ice aggregate construction project, build a digital twin model of the entire ice aggregate construction process; Data acquisition and transmission steps: Install multiple sensors on the construction equipment to collect data on the amount of ice aggregate spread, filling pressure, equipment operating speed, and fuel consumption in real time, and transmit the collected data to the data processing center via wireless network; Steps for establishing an energy consumption prediction model: The data processing center receives the collected data, combines it with the construction process data simulated by the digital twin model, and uses machine learning algorithms to establish an energy consumption prediction model for ice aggregate construction. This model takes construction parameters and equipment operating status as input variables and energy consumption as output variable, and can predict energy consumption under different construction parameters and equipment operating strategies. Construction parameter and equipment operation strategy optimization steps: Input the construction schedule requirements and quality standards into the energy consumption prediction model, and through the model's calculation and analysis, obtain the construction parameters and equipment operation strategies that meet the construction requirements and have the lowest energy consumption. Layered spreading and filling control steps: Based on the optimized construction parameters and equipment operation strategy, control the operation of spreading and filling equipment to achieve precise layered spreading and filling of ice aggregate. At the same time, during the construction process, the actual construction data is fed back to the digital twin model and energy consumption prediction model in real time for dynamic correction and optimization of the model.

2. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, In the step of constructing the digital twin model, the 3D modeling technology adopts a modeling method based on an improved octree algorithm. By spatially discretizing the design drawings and actual terrain data, the construction area is divided into multiple 3D voxels. Considering the characteristics of ice aggregate materials, a particle model library is established for ice aggregates of different sizes and shapes. Using the Monte Carlo simulation method, particle models are randomly selected and distributed in the model according to the actual gradation of the ice aggregate. The specific construction process of the improved octree algorithm is as follows: Let the initial 3D space be... Its side length is During the first division, Divide into 8 equal small cubes, each with a volume of . The side length is For each small cube, based on the design drawings and terrain data contained within, it is determined whether further subdivision is needed. If the internal data of the small cube is complex, and there are areas with significant differences in the morphology of different types of construction equipment components or aggregate accumulation, then further subdivision is performed. Let the volume of the small cube after the nth subdivision be... The side length is This continues until the set subdivision accuracy requirement is met, which can be determined based on the minimum dimensions of the key construction parts.

3. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, In the data acquisition and transmission step, for the spreading quantity sensor, a novel spreading quantity detection device based on the ultrasonic time-difference method is used. This device has ultrasonic transmitting and receiving probes installed opposite each other on both sides of the spreading pipe, and measures the time difference of ultrasonic wave propagation in the ice aggregate flow. Combined with pipe diameter And the empirical formula for the propagation speed of ultrasound in ice aggregate. ,in As the reference speed, A coefficient related to the properties of ice aggregate. To determine the real-time density of ice aggregate, use the formula... Calculate the amount of ice aggregate to be spread ,in To determine the ultrasonic propagation path length, a fiber Bragg grating pressure sensor is used for filling pressure sensors. The principle is that when pressure is applied to the fiber grating, the grating period... Changes occur, according to the Prague conditions. ,in For the Bragg wavelength, To determine the effective refractive index, changes in the wavelength of the reflected light are detected. The calibration relationship between pressure and wavelength changes is used. Get filling pressure ,in To calibrate the coefficients, a wireless network transmission protocol based on a combination of time division multiple access and orthogonal frequency division multiplexing is adopted for data transmission, which transmits different sensor data in an orderly manner according to time slices and frequency subcarriers.

4. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, In the step of establishing the energy consumption prediction model, the machine learning algorithm used is the improved adaptive neuro-fuzzy inference system algorithm. First, the set of input variables is determined. ,in These represent construction parameters and equipment operating status variables, respectively, including spreading speed, filling thickness, equipment operating speed, and energy consumption. By performing cluster analysis on the collected data, the data is divided into different fuzzy subsets, each corresponding to a construction condition. For each fuzzy subset, a Gaussian membership function is used. To describe input variables Belongs to fuzzy sets The degree, of which The center of the membership function, For the width, a fuzzy rule base is constructed based on construction experience and data features. Then, the parameters of the ANFIS model are trained using a hybrid learning algorithm combining least squares and gradient descent. During training, the prediction error is analyzed... ,in To obtain the model's predicted values, the parameters of the membership function are continuously adjusted. , The parameters of the fuzzy rule consequents are used to minimize the prediction error. After multiple iterations of training, the model can accurately predict energy consumption under different construction parameters and equipment operation strategies.

5. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, In the optimization steps of construction parameters and equipment operation strategies, construction progress requirements are transformed into construction time constraints. The quality standard is transformed into the lower limit of compaction degree for ice aggregate filling. and spreading uniformity index In the calculation process of the energy consumption prediction model, a simplified comprehensive constraint function is introduced. The system quantifies situations where construction requirements are not met, prompting the model to output a comprehensive constraint function that balances construction progress, quality, and energy consumption. The calculation formula is: ,in, These are the constraint weighting coefficients for construction time, filling compaction degree, and spreading uniformity, respectively. , , For the status judgment variable, when the actual construction time hour ,otherwise When the actual compaction degree hour, ,otherwise When the actual spreading uniformity hour, ,otherwise In the calculation of comprehensive energy consumption in the energy consumption prediction model At that time, the comprehensive constraint function will be Compared with the basic energy consumption forecast value Combined, the calculation formula is as follows: ,in This is the amplification factor, used to adjust the degree of influence of constraints on energy consumption.

6. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, In the layered spreading and filling control steps, the spreading equipment adopts a closed-loop control method during the layered spreading and filling control process, and the optimized spreading speed setpoint is used. During the process, the spreading equipment adopts a closed-loop control method, and the spreading speed feedback value is obtained in real time by the spreading quantity sensor. Comparisons are made, and the control quantity is calculated using a PID controller. ,in For speed deviation, This is the proportionality coefficient. The integral time constant is... The differential time constant is the control quantity. The drive motor of the spreading equipment is adjusted to adjust its speed. For the filling equipment, the pressure value fed back by the filling pressure sensor is compared with the set filling pressure range. When the pressure is lower than the lower limit, the compaction frequency or force of the filling equipment is increased. When the pressure is higher than the upper limit, the compaction frequency or force is appropriately reduced. At the same time, the running trajectory of the spreading and filling equipment is finely adjusted according to the real-time feedback of the digital twin model to avoid equipment collisions and construction dead zones.

7. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, Throughout the construction process, an environmental factor compensation mechanism is introduced, using temperature and humidity sensors and wind speed sensors installed at the construction site to collect ambient temperature data in real time. ,humidity Wind speed Environmental data was used to analyze the effects of ambient temperature and humidity on the melting and adhesion of ice aggregates during the spreading process. A state correction model for ice aggregates was established, and the melting rate was obtained by fitting experimental data to determine the influence of ambient temperature and humidity on the melting and adhesion of ice aggregates. The relationship with ambient temperature and humidity is ,in , , The melting rate is used as a fitting coefficient to correct the spreading amount and spreading uniformity. For the filling process, the influence of wind speed on dust generation and compaction of the ice aggregate is considered. When the wind speed exceeds a certain threshold... At the same time, by adjusting the compaction parameters of the filling equipment, the filling quality is ensured to be unaffected by excessive interference from environmental factors. Meanwhile, environmental factor data is used as an additional input variable and integrated into the digital twin model and energy consumption prediction model, so that the model can more accurately reflect the actual construction situation.

8. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, To address unforeseen circumstances during construction, an emergency decision-making module is established. This module monitors the operational status data of construction equipment and key indicator data during construction in real time. When an emergency is detected, the emergency decision-making module is quickly activated. First, a digital twin model is used to simulate and analyze the emergency, assessing its impact on construction progress, quality, and energy consumption. Then, based on a pre-set emergency strategy library, combined with the current construction status and impact assessment results, the optimal emergency response plan is selected.

9. The method for controlling the layered spreading and filling of ice aggregate according to claim 1, characterized in that, After construction is completed, a review and analysis of the data from the entire construction process is conducted. The simulation data from the digital twin model, the actual construction data, and the results of the energy consumption prediction model are compared to evaluate the execution effect of the construction process. Through data mining technology, the potential relationship between construction parameters, equipment operation strategies, construction quality, and energy consumption is analyzed to uncover the key factors affecting construction quality and energy consumption.

10. A layered spreading and filling control system for ice aggregate, applicable to the layered spreading and filling control method for ice aggregate as described in any one of claims 1-9, characterized in that, The system includes a data acquisition and transmission module, a model building module, a parameter and strategy optimization module, an equipment control and execution module, and a feedback and optimization iteration module. The data acquisition and transmission module consists of various sensors installed on the construction equipment, such as a spreading amount sensor, a filling pressure sensor, and an equipment operating status sensor, as well as a wireless network transmission component. The sensors collect relevant data during the construction process in real time, such as the spreading amount of ice aggregate, filling pressure, equipment operating speed, and fuel consumption. The wireless network transmission component adopts a transmission protocol that combines time division multiple access and orthogonal frequency division multiplexing to stably and accurately transmit the collected data to the data processing center. The model building module utilizes 3D modeling technology to construct a digital twin model of the entire construction process based on the design drawings, actual terrain data, and material characteristics of the ice aggregate construction project. It employs an improved octree algorithm to simulate the dynamic process of layered spreading and filling of ice aggregate in real time. After receiving the collected data and the simulation data from the digital twin model, the data processing center uses an improved adaptive neural fuzzy inference system algorithm to establish an energy consumption prediction model with construction parameters and equipment operating status as inputs and energy consumption as output. The parameter and strategy optimization module transforms construction progress requirements and quality standards into specific constraints, inputs them into the energy consumption prediction model, and, by introducing a comprehensive constraint function and combining model calculation and analysis, derives construction parameters and equipment operation strategies that meet construction requirements and have the lowest energy consumption. The equipment control execution module: Based on the output of the parameter and strategy optimization module, it precisely controls the spreading equipment and the filling equipment. It adopts a closed-loop control method, uses a PID controller to adjust the spreading speed of the spreading equipment, and adjusts the compaction operation of the filling equipment based on the feedback of the filling pressure sensor, so as to ensure that the layered spreading and filling of the ice aggregate are executed according to the optimized parameters and strategies. The feedback and optimization iteration module collects actual construction data in real time during construction and feeds it back to the digital twin model and energy consumption prediction model to dynamically correct and optimize the models. At the same time, it introduces an environmental factor compensation mechanism to cope with external changes, establishes an emergency decision-making module to handle emergencies, and after construction is completed, it reviews and analyzes the construction data to identify key factors and form a continuous improvement mechanism for the construction process, so that the system can be continuously optimized and upgraded.

Images