New energy road paving equipment control system and method adaptable to terrain

Abstract

The present application discloses a control system and method for a new energy road paving device adaptable to terrain, belonging to the fields of intelligent transportation equipment and new energy technologies. The system includes the following modules: an intelligent perception module, which realizes the precise perception and recognition of terrain features and construction environment parameters, and completes the acquisition and feature analysis of construction working condition data; a new energy power management module, which realizes the intelligent optimization of battery management, energy consumption prediction, and power distribution; a construction parameter collaborative control module, which realizes the adaptive adjustment and collaborative control between key construction parameters; a terrain adaptive execution module, which realizes the adaptive adjustment of the road paving device under different terrain conditions; an intelligent decision-making control module, which formulates and supervises the execution of the optimal control strategy for the overall construction process through hierarchical reinforcement learning; a safety monitoring module, which ensures the prevention and emergency response of potential risks during the construction process; and a human-computer interaction module, which provides an intuitive visual interface and intelligent operation suggestions.

Description

Technical Field

[0001] This application relates to the fields of intelligent transportation equipment and new energy technologies. More specifically, it relates to a control system and method for a new energy road paving equipment that can adapt to terrain Background Art

[0002] With the continuous development of modern transportation infrastructure, the demand for road construction is also increasing. During the construction process of traditional road paving equipment, it is usually necessary to manually adjust the equipment parameters to adapt to different terrains and construction conditions, which not only has low efficiency but also has human errors and safety hazards. In addition, traditional equipment has high energy consumption and a large impact on the environment, which does not meet the requirements of sustainable development.

[0003] In recent years, the development of intelligent and new energy technologies has provided new ideas for the improvement of road paving equipment. Intelligent perception technology can achieve precise monitoring of terrain features and construction environments, while new energy power management technology can optimize the energy utilization efficiency of equipment. However, there are still problems in the existing technology, such as poor coordination between the intelligent perception and power management modules and insufficient terrain adaptability, which limit the intelligent and efficient development of road paving equipment.

[0004] In summary, how to achieve efficient coordination of multiple modules such as intelligent perception, new energy power management, construction parameter collaborative control, and terrain adaptive execution has become a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In order to overcome a series of defects existing in the prior art, the purpose of this application is to provide a control system for a new energy road paving equipment that can adapt to terrain, including the following modules for the above problems.

[0006] An intelligent perception module that realizes precise perception and recognition of terrain features and construction environment parameters, and completes the collection and feature analysis of construction condition data.

[0007] A new energy power management module that realizes intelligent optimization of battery management, energy consumption prediction, and power distribution.

[0008] The construction parameter collaborative control module realizes the adaptive adjustment and collaborative control between key construction parameters, including a parameter coupling analysis unit and an optimization strategy generation unit. Specifically: The parameter coupling analysis unit identifies the mutual influence and dependency relationships between parameters through the coupling analysis of various key construction parameters at the construction site; The optimization strategy generation unit generates the optimal parameter control strategy using a multi-objective optimization algorithm based on the output results of the parameter coupling analysis unit, which specifically includes the following steps: Based on the mutual influence and dependency relationships between parameters, construct multiple objective functions covering paving flatness, compaction degree, and energy consumption, and set evaluation indicators and quantification criteria for each objective function; Combining the actual engineering requirements and equipment physical limitations, establish a set of constraint conditions covering parameter value ranges, parameter change rates, and safety thresholds, and at the same time consider the coupling constraint relationships between parameters to construct a complete constraint equation system; Through integrating expert experience and historical data analysis, dynamically evaluate the importance of objectives under different construction conditions to form an adaptive weight adjustment mechanism; Use the non-dominated sorting genetic algorithm III to solve the multi-objective optimization problem, and continuously approximate the Pareto optimal solution set through population evolution iteration. At the same time, introduce crowding degree calculation to maintain the diversity of the solution set to ensure that a set of evenly distributed non-dominated solutions can be obtained; Based on the fuzzy decision-making theory, comprehensively evaluate the candidate solutions on the Pareto front, and select the parameter combination most suitable for the current construction requirements by establishing a decision matrix and combining the current working condition characteristics to form a specific control strategy to achieve the optimal trade-off between multiple objectives.

[0009] The terrain adaptive execution module realizes the adaptive adjustment of the road paving equipment under different terrain conditions.

[0010] The intelligent decision-making control module formulates and supervises the execution of the optimal control strategy for the overall construction process through hierarchical reinforcement learning.

[0011] The safety monitoring module ensures the prevention of potential risks and emergency response during the construction process.

[0012] The human-machine interaction module provides an intuitive visual interface and intelligent operation suggestions.

[0013] Furthermore, the intelligent perception module includes the following components.

[0014] The environment perception unit collects the environmental parameters of the construction site through multi-source sensors.

[0015] The terrain scanning unit is used to perform three-dimensional scanning and modeling of the construction area to achieve a high-precision digital expression of the terrain features.

[0016] The working condition monitoring unit collects the operation status and operation parameter data of the construction equipment using vibration, pressure, and displacement sensors.

[0017] The data preprocessing unit performs noise reduction, standardization, and feature extraction on the collected raw data.

[0018] The feature recognition unit performs pattern recognition and feature analysis on the preprocessed data and outputs key construction parameters.

[0019] The data storage unit classifies, stores, and manages the processed perception data, supporting historical data query and in-depth mining.

[0020] Furthermore, the new energy power management module includes the following components.

[0021] The battery management unit monitors the battery's power, temperature, and health status in real time, ensures the safe and efficient operation of the battery, and optimizes the charging and discharging strategies.

[0022] The energy consumption prediction unit uses historical data and environmental information to predict future energy consumption requirements.

[0023] The power distribution optimization unit, based on real-time energy consumption prediction and battery status, uses reinforcement learning algorithms to optimize the power distribution strategy to achieve the optimal utilization of electricity and resources.

[0024] The energy scheduling decision-making unit dynamically adjusts the usage strategies of different energy sources according to the prediction results and current demands, balances the load, and improves efficiency.

[0025] The charging and discharging strategy unit intelligently adjusts the charging and discharging strategies according to the feedback from the battery management unit.

[0026] The energy environment adaptation unit, based on the environmental data provided by the intelligent perception module, adjusts the energy consumption management and battery working mode in real time.

[0027] Furthermore, based on real-time energy consumption prediction and battery status, using reinforcement learning algorithms to optimize the power distribution strategy includes the following steps.

[0028] Construct a multi-dimensional state space covering the battery state of charge, temperature distribution, charge and discharge power, and historical energy consumption data. At the same time, based on the current construction working conditions and environmental conditions, extract key feature indicators reflecting the dynamic operation state characteristics of the paving equipment.

[0029] Define a continuous action space covering the power distribution ratio and power output. At the same time, based on the battery performance constraints and equipment power requirements, establish action boundary conditions and design corresponding penalty mechanisms.

[0030] Design a multi-objective reward function based on weighted summation to comprehensively evaluate the energy utilization efficiency, battery life, and power response performance.

[0031] The deep deterministic policy gradient algorithm is adopted to collect empirical data through environmental interaction and iteratively optimize the parameters of the power distribution policy network.

[0032] A policy fine-tuning trigger mechanism based on performance evaluation indicators is established to achieve online adaptive optimization of the policy network parameters.

[0033] Furthermore, the construction parameter collaborative control module further includes the following components.

[0034] The adaptive control unit evaluates the changes in the construction state in real time, dynamically adjusts the control strategy parameters, and ensures the adaptability of the control.

[0035] The conflict detection and coordination unit identifies possible conflicts or inconsistencies between different construction parameters and intervenes and coordinates them.

[0036] The construction parameter execution unit converts the optimized control instructions into specific execution actions to achieve precise control of the construction equipment.

[0037] Furthermore, the terrain adaptive execution module includes the following components.

[0038] The suspension mechanism adjustment unit adapts to terrain changes in real time by precisely controlling the angle and tension of the suspension mechanism.

[0039] The paving width adjustment unit automatically adjusts the paving width of the paving equipment according to terrain features and construction requirements.

[0040] The height compensation unit compensates for terrain undulations by adjusting the height of the paving equipment based on ground height changes.

[0041] The terrain adaptation execution unit calculates and executes the adjustment commands for the suspension mechanism, paving width, and height to achieve adaptive control.

[0042] The vibration control unit ensures uniform distribution of materials during the paving process by adjusting vibration parameters.

[0043] Furthermore, the intelligent decision-making control module includes the following components.

[0044] The system comprehensive state evaluation unit evaluates the construction system state from a global perspective based on the basic evaluation results of the intelligent perception module and generates the state feature vector required for decision-making.

[0045] The policy generation unit decomposes complex construction control problems into multiple levels of sub-tasks based on the hierarchical reinforcement learning algorithm and generates corresponding control policies for each level.

[0046] The action coordination unit coordinates and integrates the control policies at each level to form a unified control instruction sequence.

[0047] An execution supervision and evaluation unit that supervises and evaluates the control execution effects of each module, including parameter control effect evaluation and abnormal state identification.

[0048] A global policy optimization unit that uniformly optimizes and adjusts control strategies at each level based on the execution supervision and evaluation results.

[0049] Furthermore, the security monitoring module includes the following components.

[0050] A security risk identification unit that timely identifies potential security hazards and abnormal states based on predefined security threshold parameters and risk assessment models.

[0051] An intelligent fault diagnosis unit that conducts root cause analysis and precise positioning of potential security hazards and abnormal states based on preset diagnostic rules and historical data.

[0052] An early warning management unit that automatically generates hierarchical early warning information and accurately pushes it to relevant responsible persons according to the risk identification results and the output of fault diagnosis.

[0053] An emergency response unit that formulates standardized emergency response processes for different types of security incidents and provides real-time handling guidance and execution suggestions.

[0054] A closed-loop verification and optimization unit that continuously optimizes the security early warning and emergency response systems to improve the accuracy and response efficiency of security management.

[0055] The purpose of this application is also to provide a control method for new energy road paving equipment that can adapt to terrain, including the following steps.

[0056] Construct a digital construction scenario model that includes terrain features, environmental parameters, and equipment status to provide a data basis for subsequent decision-making and control.

[0057] Formulate initial control strategies at each level, establish a security monitoring system, and evaluate potential risks in real time and formulate emergency plans to ensure the safety and reliability of the decision-making process.

[0058] By designing a multi-objective reward function, combining historical data and current working conditions, predicting energy consumption requirements, and optimizing the charge and discharge strategies in real time, efficient management of new energy power is achieved.

[0059] By establishing a parameter coupling analysis and fuzzy decision-making mechanism, selecting the optimal parameter combination, and constructing a constraint equation set, adaptive adjustment and coordinated control of key construction parameters are achieved.

[0060] Precisely control the suspension mechanism, telescopic arm, and hydraulic cylinder using electro-hydraulic proportional valves to achieve dynamic adaptive adjustment of the paving equipment; at the same time, monitor the material supply rate and paving layer thickness in real time, and dynamically optimize compensation parameters based on the measured data to ensure that the construction quality always meets the specification requirements.

[0061] Compared with the prior art, the present application has the following beneficial effects.

[0062] Through intelligent perception, new energy power management, coordinated control of construction parameters, terrain adaptive execution, intelligent decision-making control, safety monitoring, and human-computer interaction modules, the present application realizes the all-round optimization of highway paving equipment, improves construction efficiency and quality, and at the same time ensures the safety and environmental protection of the construction process. Brief Description of the Drawings

[0063] Figure 1 It is a schematic structural diagram of a control system for a new energy highway paving equipment that can adapt to terrain disclosed in an embodiment of the present application.

[0064] Figure 2 It is a schematic flowchart of a control method for a new energy highway paving equipment that can adapt to terrain disclosed in an embodiment of the present application. Detailed Embodiments

[0065] To make the purpose, technical solutions, and advantages of the implementation of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, of the embodiments of the present invention.

[0066] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] The embodiments described below with reference to the accompanying drawings and directional terms are exemplary only and are intended to explain the present invention and should not be construed as limiting the present invention.

[0068] As Figure 1 shown, this embodiment provides a control system for a new energy highway paving equipment that can adapt to terrain, including the following modules.

[0069] An intelligent perception module that realizes the precise perception and recognition of terrain features and construction environment parameters, and completes the collection and feature analysis of construction condition data.

[0070] A new energy power management module that realizes the intelligent optimization of battery management, energy consumption prediction, and power distribution based on a predictive energy management strategy and a reinforcement learning algorithm.

[0071] The construction parameter collaborative control module realizes the adaptive adjustment and collaborative control between key construction parameters, including a parameter coupling analysis unit and an optimization strategy generation unit. Specifically: The parameter coupling analysis unit identifies the mutual influence and dependency relationships between parameters through the coupling analysis of various key construction parameters at the construction site; The optimization strategy generation unit generates the optimal parameter control strategy using a multi-objective optimization algorithm based on the output results of the parameter coupling analysis unit, which specifically includes the following steps: Based on the mutual influence and dependency relationships between parameters, construct multiple objective functions covering paving flatness, compaction degree, and energy consumption, and set evaluation indicators and quantification criteria for each objective function; Combining the actual engineering requirements and equipment physical limitations, establish a set of constraint conditions covering parameter value ranges, parameter change rates, and safety thresholds, and at the same time consider the coupling constraint relationships between parameters to construct a complete constraint equation set; Through integrating expert experience and historical data analysis, dynamically evaluate the importance of objectives under different construction conditions to form an adaptive weight adjustment mechanism; Use the non-dominated sorting genetic algorithm III to solve the multi-objective optimization problem, and continuously approximate the Pareto optimal solution set through population evolution iteration. At the same time, introduce crowding degree calculation to maintain the diversity of the solution set to ensure that a set of evenly distributed non-dominated solutions can be obtained; Based on the fuzzy decision-making theory, comprehensively evaluate the candidate solutions on the Pareto front, and select the parameter combination most suitable for the current construction requirements by establishing a decision matrix and combining the current working condition characteristics to form a specific control strategy to achieve the optimal trade-off between multiple objectives.

[0072] The terrain adaptive execution module realizes the adaptive adjustment of the road paving equipment under different terrain conditions through the suspension mechanism, paving width adjustment, and height compensation.

[0073] The intelligent decision-making control module formulates and supervises the execution of the optimal control strategy for the overall construction process through hierarchical reinforcement learning based on the working condition data provided by the intelligent perception module.

[0074] The safety monitoring module ensures the prevention and emergency response of potential risks during the construction process through the fault diagnosis and safety warning mechanism.

[0075] The human-machine interaction module provides an intuitive visual interface and intelligent operation suggestions, and realizes necessary intervention through the manual parameter adjustment interface to optimize the human-machine collaborative operation efficiency.

[0076] In this embodiment, the intelligent perception module plays a key role in realizing accurate terrain feature recognition and construction environment parameter perception. This module uses a variety of sensors to collect various information about the surrounding environment and ground conditions in real time. By analyzing this data, key features such as uneven ground, slope changes, and obstacles can be identified, and parameters such as temperature, humidity, and wind speed in the construction environment can be accurately detected. In addition, the intelligent perception module also supports the collection of construction working condition data, including information such as the current construction state, the operating speed of the paving equipment, and the working temperature. These data not only provide real-time feedback during the construction process but also provide important reference basis for subsequent modules, further promoting the improvement of construction efficiency and the optimal allocation of resources. By analyzing the characteristics of the perceived data, the behavior of the equipment can be dynamically adjusted to achieve efficient response to complex environments.

[0077] In this embodiment, the core role of the new energy power management module is to optimize the intelligent processes of battery management, energy consumption prediction, and power distribution through predictive energy management and reinforcement learning algorithms. This module combines the working load of the equipment, the construction environment, and the battery state to calculate the energy consumption demand in real time and make intelligent adjustments to ensure that the battery usage efficiency reaches the optimal. In terms of battery management, by monitoring information such as the remaining battery power, charging status, and temperature, the charging strategy is automatically adjusted to extend the battery life. Energy consumption prediction collects historical data and real-time working parameters, and uses machine learning models to predict the power consumption under different working conditions, providing decision support for the system to optimize power distribution. Through the reinforcement learning algorithm, based on the continuously changing construction tasks and terrain conditions, the power output can be dynamically adjusted, the battery power usage can be optimized, and the endurance of the equipment can be maximized to ensure the maximum utilization of energy and meet the construction requirements.

[0078] In this embodiment, the main objective of the construction parameter collaborative control module is to improve construction efficiency and quality through coupled analysis of key parameters during the construction process and multi-parameter optimization control. This module uses sensor data and real-time calculation and analysis to automatically adjust the key construction parameters of the equipment, such as paving speed, vibration frequency, compaction strength, etc., to ensure the stability and efficiency of the construction process. Through parameter coupled analysis, the mutual influence between various parameters can be deeply understood, such as the relationship between paving speed and road surface quality, so as to ensure the coordination and optimization between different construction parameters. Multi-parameter optimization control uses intelligent algorithms to comprehensively consider the interaction of multiple construction parameters and adjusts the control strategy in real time. In this way, the construction equipment can automatically adjust its operating state under different terrains, climates, and load conditions to ensure high-quality construction results and avoid substandard construction quality or low energy efficiency caused by parameter mismatch.

[0079] In this embodiment, the parameter coupling analysis unit includes the following processing steps: using the Granger causality test method with a lag order of 4 and a significance level α = 0.05 to identify the causal relationship between parameters; based on the mutual information theory, calculating the information entropy and mutual information between parameters to quantify the non-linear dependence relationship between parameters; constructing a parameter influence relationship diagram, where nodes represent construction parameters, edge weights represent the influence intensity, and the threshold is set to 0.4; using the structural equation model to fit the direct and indirect influence paths between parameters, and the model goodness-of-fit index CFI > 0.90; through sensitivity analysis, calculating the elasticity coefficient matrix between parameters to determine the key parameters and their influence ranges.

[0080] In this embodiment, the optimization strategy generation unit converts the analysis results output by the parameter coupling analysis unit into an optimal construction parameter control strategy through a multi-objective optimization algorithm. The introduction of the multi-objective optimization algorithm enables the system to simultaneously consider multiple optimization objectives and find the best balance among these objectives. During the construction process, common optimization objectives include construction efficiency, material utilization rate, equipment energy consumption, construction quality, etc., and these objectives often restrict each other. For example, increasing the paving speed will improve construction efficiency, but it will also lead to a decrease in paving quality or material waste. Through the multi-objective optimization algorithm, this unit can extract the optimal strategy from each construction objective, enabling the construction process to dynamically adjust among multiple objectives and avoiding the decline in system performance caused by the over-optimization of a single objective. Further, this unit can also subdivide the control requirements for different construction stages to ensure the most appropriate strategy is adopted in each stage. By continuously inputting real-time data and dynamically adjusting the objectives, the optimization strategy generation unit can ensure that the construction process is always in the optimal control state, thus significantly improving the overall construction efficiency and quality.

[0081] In this embodiment, the terrain adaptive execution module is a key part to ensure the smooth operation of new energy highway paving equipment under complex terrain conditions. This module realizes the adaptive adjustment of the equipment to different terrains such as ground undulations and slope changes by integrating advanced suspension mechanisms, paving width adjustment, and height compensation functions. The suspension mechanism can provide stable support in an uneven terrain environment, reducing the paving quality fluctuations caused by terrain undulations. The paving width adjustment device can dynamically adjust the paving width according to construction requirements and road surface conditions to ensure the consistency and flatness of road surface paving. The height compensation mechanism automatically adjusts the height of the paving equipment by real-time monitoring of the height changes of the terrain to ensure the accuracy of paving operations under different terrains. Through these adaptive adjustment functions, the equipment can efficiently cope with complex and changeable construction environments, improve the overall construction efficiency and quality, reduce manual intervention, and lower costs.

[0082] In this embodiment, the intelligent decision-making control module automatically optimizes the behavior strategy of the equipment by analyzing real-time data during the construction process, such as the operating status of the equipment, construction progress, energy consumption, and other information. The hierarchical reinforcement learning algorithm provides comprehensive intelligent control for the system through multi-level decision optimization, from low-level local control to high-level global decision-making. Through this intelligent decision-making mechanism, real-time adjustments can be made according to changes in the construction environment, such as automatically optimizing the paving speed, adjusting construction parameters, and even in case of emergencies, the system can quickly respond and execute the emergency plan to ensure that the construction task is completed as planned and improve the overall construction efficiency.

[0083] In this embodiment, the safety monitoring module can timely detect equipment failures or abnormal conditions and activate the warning mechanism by real-time monitoring of each key component of the equipment, including the power system, battery status, transmission system, etc. In terms of fault diagnosis, it can quickly locate the problem and provide solutions by analyzing the working state of the equipment and sensor feedback, preventing construction delays or safety accidents caused by equipment failures. The safety warning mechanism predicts possible risks in advance by monitoring environmental changes at the construction site, such as weather changes, ground conditions, etc., and takes preventive measures in a timely manner, such as adjusting the construction strategy or suspending operations, to ensure the safety of the construction process.

[0084] In this embodiment, the human-machine interaction module incorporates an intelligent operation suggestion function, which can provide guidance for the operator to optimize decisions based on the real-time analysis of the system, such as adjusting the paving speed, controlling the equipment load, etc. The manual parameter adjustment interface provides the operator with necessary intervention means. When full automation control is not possible, the operator can make manual adjustments through this interface to ensure the smooth progress of the construction task. In addition, the design of the module fully considers the convenience of the operator, adopting a simple and intuitive interface and operation process, greatly optimizing the human-machine collaborative operation efficiency and enhancing the operation experience during the construction process.

[0085] In summary, the new energy road paving equipment control system disclosed in this embodiment realizes efficient, precise, energy-saving, and safe construction management through intelligent perception, dynamic optimization, and adaptive adjustment technologies. Each module works together to enable the equipment to cope with complex terrains and changing construction environments, thus greatly improving the construction efficiency and pavement quality. It not only reduces the dependence on manual operations, lowers the construction cost, but also optimizes energy management and extends the service life of the equipment through intelligent control and prediction mechanisms. Through the integration of these innovative technologies, the new energy road paving equipment control system can play a more important role in future road construction, promoting intelligent, green, and efficient construction methods.

[0086] Furthermore, the intelligent perception module includes the following components.

[0087] The environmental perception unit collects environmental parameters of the construction site through multi-source sensors, providing basic data support for construction decision-making.

[0088] The terrain scanning unit is used to perform three-dimensional scanning and modeling of the construction area, realizing high-precision digital expression of terrain features.

[0089] The working condition monitoring unit collects data on the operating status and working parameters of construction equipment using vibration, pressure, and displacement sensors.

[0090] The data preprocessing unit performs noise reduction, standardization, and feature extraction on the collected raw data to improve the accuracy of subsequent analysis.

[0091] The feature recognition unit performs pattern recognition and feature analysis on the preprocessed data and outputs key construction parameters.

[0092] The data storage unit classifies, stores, and manages the processed perception data, supporting historical data query and in-depth mining.

[0093] In this embodiment, the environmental perception unit includes the following sensor components: a temperature and humidity sensor that monitors the environmental temperature range from -40°C to 85°C, the humidity range from 0 to 100%RH, with an accuracy of ±0.5°C and ±3%RH; a wind speed and direction sensor that monitors the wind speed range from 0 to 60 m / s, with a wind direction resolution of 8°; a light intensity sensor that monitors the light intensity range from 0 to 150,000 lux and is used to automatically adjust the construction lighting system; a rainfall sensor that monitors the precipitation range from 0 to 300 mm / h, with an accuracy of ±3 mm / h; and a barometric pressure sensor that monitors the barometric pressure range from 300 to 1100 hPa, with an accuracy of ±0.5 hPa and is used to predict the impact of weather changes on construction.

[0094] In this embodiment, the terrain scanning unit adopts millimeter-wave radar and lidar fusion technology, including: a millimeter-wave radar with a working frequency of 76 - 81 GHz, a detection distance of 0.2 - 200 m, and a distance resolution better than 0.2 m; a lidar with a point cloud density of 300,000 points per second, a scanning range of 360° horizontal × 30° vertical, and an accuracy better than ±8 mm; a dual-modal data fusion algorithm, a multi-sensor data fusion method based on Kalman filtering, to achieve all-weather terrain recognition; and a three-dimensional reconstruction processor that uses GPU-accelerated computing, with a processing speed of 30 frames per second and a real-time update rate of the generated terrain three-dimensional model not lower than 5 Hz.

[0095] In this embodiment, the sensor configuration of the working condition monitoring unit includes: a vibration sensor array, which uses 12 triaxial acceleration sensors with a measurement range of ±50g and a frequency response of 0 - 3 kHz; a pressure sensor network, which consists of 36 distributed pressure sensors with a range of 0 - 2 MPa and an accuracy of ±1% F.S.; a displacement sensor system, which is composed of 16 LVDT displacement sensors with a range of ±100 mm and an accuracy of ±0.3 mm; a temperature sensor array, which includes 24 K-type thermocouples with a temperature measurement range of -50°C to 800°C and an accuracy of ±1.5°C; an infrared thermal imager with a resolution of 384×288 pixels and a temperature resolution of 0.08°C, which is used to monitor the temperature distribution of paving materials.

[0096] In this embodiment, the data preprocessing unit adopts the following processing methods: wavelet transform for noise reduction, using the db4 wavelet basis, 4-level decomposition, soft threshold processing, with the signal-to-noise ratio increased by no less than 15 dB; Z-score normalization processing to make the mean 0 and the standard deviation 1, improving the comparability of data with different dimensions; principal component analysis, reducing the dimension to retain 90% of the information volume, reducing data redundancy and improving processing efficiency; data smoothing filtering, using an adaptive Savitzky-Golay filter with a dynamically adjustable window width ranging from 5 to 15; outlier detection and processing, based on the modified 3σ principle and the DBSCAN clustering algorithm, with an outlier detection rate greater than 92%.

[0097] In this embodiment, the core function of the feature recognition unit is to perform pattern recognition and feature analysis on the preprocessed data, and extract the key construction parameters that affect the construction quality. This unit conducts intelligent analysis on the data through advanced machine learning algorithms such as deep learning and support vector machines, and identifies potential patterns and trends. For example, when analyzing terrain data, it can identify areas with excessive slopes or patterns of uneven equipment loads during the construction process. Through feature analysis, potential problems during the construction process can be predicted, and optimization adjustments can be made in advance. Feature recognition not only helps the system better understand the status of the construction site, but also enables real-time assessment of the operating conditions of the equipment, thereby making corresponding control decisions. Through this intelligent analysis, the key factors affecting construction efficiency and quality can be accurately identified, and these factors can be adjusted in real time, providing effective decision-making support for the construction process.

[0098] In this embodiment, the data storage unit stores the data from each sensor in a certain structure for subsequent access and analysis. Through cloud storage or distributed storage technology, the data storage unit can provide high-speed read and write operations to ensure the real-time update and long-term preservation of the construction site data. The stored data includes not only the data of the current construction status but also the historical construction data, which provides valuable references for subsequent in-depth mining. For example, by analyzing the historical data, early signs of equipment failures can be discovered, and then potential future failures can be predicted and preventive maintenance can be carried out. In addition, the data storage unit also supports efficient retrieval of data, enabling project managers and engineers to query historical data at any time to help formulate more accurate construction plans and optimization schemes. Through its powerful data storage and management capabilities, the long-term availability and reliability of data can be guaranteed, promoting the continuous accumulation and utilization of data.

[0099] In summary, through the precise cooperation of multiple components, the intelligent perception module realizes the comprehensive perception, real-time monitoring, and accurate analysis of the construction site. The environmental perception unit, terrain scanning unit, working condition monitoring unit, data preprocessing unit, feature recognition unit, and data storage unit work together to ensure that each link from data collection to processing and then to storage is efficient and accurate. The combination of these technical effects enables the entire construction process to be monitored in real time and adjusted adaptively, greatly improving the accuracy and efficiency of construction. At the same time, the intelligent analysis and decision-making capabilities of the system continuously optimize construction parameters and resource allocation to ensure that various changes can be efficiently handled in a complex construction environment. Through the application of these technical means, the intelligent perception module not only enhances the automation and intelligence of the construction process but also provides strong data support for the optimization and management of the subsequent construction process, ultimately promoting the improvement of construction quality and efficiency.

[0100] Furthermore, the pattern recognition and feature analysis are performed on the preprocessed data to output key construction parameters, including the following steps.

[0101] Use the trained machine learning model to perform pattern recognition on the preprocessed data, automatically discover the potential patterns in the data, identify the feature combinations under different working conditions, and reflect the key states in the construction process.

[0102] Extract the most influential construction parameters by analyzing the feature importance and the impact of each parameter on construction quality and efficiency.

[0103] In summary, through pattern recognition and feature analysis, key parameters affecting construction quality and efficiency can be accurately identified in complex construction environments, greatly enhancing the intelligent level of the construction process. The machine learning model automatically discovers potential laws and anomalies in the construction process through learning historical data, and then provides data support for construction decisions. Through feature importance analysis, the most influential construction parameters can be screened out, and the construction strategy can be adjusted in real time to ensure the optimization of construction quality and efficiency. These technologies not only make the construction process more predictable and self-adaptive, but also provide a strong decision-making basis for the construction team, ensuring that construction tasks can be completed efficiently and accurately under different working conditions and environmental conditions.

[0104] Furthermore, the new energy power management module includes the following components.

[0105] The battery management unit monitors the battery's power, temperature, and health status in real time, ensuring the safe and efficient operation of the battery and optimizing the charge and discharge strategies.

[0106] The energy consumption prediction unit uses historical data and environmental information to predict future energy consumption requirements, providing an accurate prediction basis for power distribution and energy scheduling.

[0107] The power distribution optimization unit, based on real-time energy consumption prediction and battery status, uses reinforcement learning algorithms to optimize the power distribution strategy to achieve the optimal utilization of electricity and resources.

[0108] The energy scheduling decision-making unit dynamically adjusts the usage strategies of different energies according to the prediction results and current demands, balancing the load and improving efficiency.

[0109] The charge and discharge strategy unit intelligently adjusts the charge and discharge strategies according to the feedback of the battery management unit, ensuring the extension of battery life and the improvement of energy utilization efficiency.

[0110] The energy environment adaptation unit, based on the environmental data provided by the intelligent perception module, adjusts the energy consumption management and battery working modes in real time to cope with changing environmental conditions.

[0111] In this embodiment, the battery management unit has the following functional characteristics: it monitors the voltage of each battery cell in the battery pack in real time, with a voltage monitoring accuracy of ±0.01V and a temperature monitoring accuracy of ±0.5°C; it adopts a SOC estimation algorithm based on Kalman filtering, with a state of charge estimation accuracy better than ±3%; it implements a battery equalization strategy based on model predictive control, with a maximum allowable voltage difference between battery cells of 0.03V; a hybrid SOC estimation method based on current integration and open-circuit voltage correction, with an error not exceeding ±3% in the 10-90% SOC range; it has overcharge, over-discharge, over-current, and over-temperature protection functions, with a response time of less than 150ms.

[0112] In this embodiment, the energy consumption prediction unit realizes the following functions: Based on the LSTM-GRU hybrid network architecture, the input layer contains 10 feature nodes, the hidden layer is a bidirectional structure, with 96 neurons in each layer; the prediction duration is divided into short-term (0 - 2 hours), medium-term (2 - 8 hours), and long-term (8 - 24 hours), and the short-term prediction accuracy is better than 90%; using the sliding window technology, the window width is 180 minutes, and the step size is 30 minutes to achieve continuous update of the prediction model; integrating meteorological forecast data, including temperature, humidity, and wind speed, to improve the environmental adaptability of energy consumption prediction; adopting a regularization strategy with a Dropout rate of 0.3 to prevent model overfitting and improve generalization ability.

[0113] In this embodiment, the core function of the power distribution optimization unit is to optimize the power distribution strategy based on real-time energy consumption prediction and battery status through a reinforcement learning algorithm to achieve the optimal utilization of power and resources. The reinforcement learning algorithm automatically adjusts the power distribution strategy by simulating environmental changes and equipment requirements to improve energy use efficiency and reduce operating costs. In this process, the power distribution optimization unit first calculates the current and future energy demands through the energy consumption demand information provided by the real-time energy consumption prediction unit, and considers factors such as the current battery power, temperature, and health status. Based on this information, it can dynamically adjust the distribution between different power sources. For example, when the battery power is low, external energy can be preferentially used; while when the battery power is sufficient, more reliance on battery power supply can reduce the dependence on external power sources. This optimization strategy based on reinforcement learning can learn the optimal power distribution method through continuous feedback loops, thereby ensuring the maximization of power resource utilization efficiency under different construction conditions. In addition, the power distribution optimization unit can also make flexible adjustments according to the dynamic changes at the construction site, avoiding inefficiencies or energy waste caused by improper resource allocation and ensuring the reasonable use of energy.

[0114] In this embodiment, the energy scheduling decision-making unit plays a coordinating role, ensuring the continuous operation of equipment while ensuring the stable distribution and use of energy. Through real-time monitoring of energy supply and demand, the energy scheduling decision-making unit can make reasonable energy scheduling decisions at different time periods. For example, when the battery power is sufficient, the energy provided by the battery will be preferentially used, while when the battery power is insufficient, the power supply will be supplemented by switching to other energy sources. Through this intelligent scheduling, the risk of equipment downtime caused by the interruption of a single energy source can be avoided, and the battery can also be charged when the battery load is light to keep the battery power sufficient. In addition, the energy scheduling decision-making unit can also dynamically adjust the system working mode according to the predicted energy consumption demand, optimize the construction process, and avoid energy waste. For example, when the construction load is low, energy consumption can be reduced to optimize the energy resource allocation. Through precise energy scheduling, the system can improve construction efficiency and ensure the stability and reliability of energy supply.

[0115] In this embodiment, the charge and discharge strategy unit intelligently adjusts the charge and discharge strategies according to the feedback provided by the battery management unit, ensuring the extended service life of the battery and the improvement of energy utilization efficiency. The charging and discharging processes of the battery have important impacts on its life and performance. Overcharging or overdischarging will accelerate the aging of the battery. The charge and discharge strategy unit adjusts the charge and discharge strategies by monitoring the battery's power and health status in real time to prevent the battery from being damaged due to overcharging or overdischarging. For example, when the battery power is high, the charging rate will be reduced to avoid thermal runaway caused by overcharging the battery; when the battery power is low, appropriate discharge strategies will be adopted to avoid overdischarging the battery. Through the intelligent regulation of the battery's charging and discharging, the charge and discharge strategy unit not only extends the service life of the battery but also improves the energy utilization efficiency and avoids unnecessary energy losses.

[0116] In this embodiment, the energy and environment adaptation unit utilizes the environmental data provided by the intelligent sensing module to adjust the energy consumption management and battery operating mode in real time to cope with changing environmental conditions. Environmental factors such as temperature, humidity, and terrain changes at the construction site will all affect the energy demand. For example, a low-temperature environment will cause a decline in battery performance, while a high-temperature environment will increase the battery's load. The energy and environment adaptation unit dynamically adjusts the battery's operating mode and energy consumption strategy by obtaining and analyzing this environmental data in real time. For example, when the temperature is low, the system will increase the battery's operating temperature to ensure the normal operation of the battery; when the environmental temperature is too high, the system will reduce the load or turn on an additional cooling system to reduce the burden on the battery. By adapting to environmental changes in real time, the energy and environment adaptation unit can effectively optimize the battery performance and energy utilization efficiency, ensuring the stable operation of the system under different environmental conditions.

[0117] In summary, the new energy power management module ensures the efficient and safe use of the battery and optimizes the energy consumption management through the collaborative work of multiple intelligent units. The battery management unit guarantees the long-term health of the battery by monitoring the battery status in real time; the energy consumption prediction unit combines historical data and environmental information to provide accurate predictions for power distribution and energy scheduling; the power distribution optimization unit intelligently adjusts the power distribution through reinforcement learning algorithms to optimize resource utilization; the energy scheduling decision unit balances different energy sources according to real-time demands to ensure stable energy supply; the charge and discharge strategy unit extends the battery life and optimizes energy use; and the energy and environment adaptation unit intelligently adjusts the energy management strategy according to changes in the external environment. The cooperation of all these functions enables the new energy power management module not only to efficiently utilize energy but also to cope with complex construction environments and changes in energy demands, ensuring the high efficiency and stability of energy supply and equipment operation during the construction process.

[0118] Furthermore, based on real-time energy consumption prediction and battery status, a reinforcement learning algorithm is used to optimize the power distribution strategy, including the following steps.

[0119] Construct a multi-dimensional state space covering the state of charge of the battery, temperature distribution, charge and discharge power, and historical energy consumption data. At the same time, based on the current construction working conditions and environmental conditions, extract key characteristic indicators reflecting the dynamic operating state characteristics of the paving equipment.

[0120] Define a continuous action space covering power distribution ratio and power output. At the same time, based on battery performance constraints and equipment power requirements, establish action boundary conditions and design corresponding penalty mechanisms to ensure the feasibility of the control strategy.

[0121] Design a multi-objective reward function based on weighted summation to comprehensively evaluate energy utilization efficiency, battery life, and power response performance.

[0122] Adopt the deep deterministic policy gradient algorithm to collect empirical data through environmental interaction and iteratively optimize the network parameters of the power distribution strategy.

[0123] Establish a policy fine-tuning trigger mechanism based on performance evaluation indicators to achieve online adaptive optimization of the network parameters of the strategy, so as to improve the rapid response ability and control effect to changes in working conditions.

[0124] In summary, by constructing a multi-dimensional state space, the state of charge of the battery, temperature distribution, and historical energy consumption data can be comprehensively grasped, providing rich environmental feedback for reinforcement learning; by defining a continuous action space and constraint conditions, it is ensured that the power distribution of the system is executed within a reasonable range; by designing a multi-objective reward function, the best balance can be found among energy efficiency, battery life, and power response; by the deep deterministic policy gradient algorithm, the strategy can be continuously optimized in a complex dynamic environment to achieve efficient power distribution; by the policy fine-tuning mechanism, the changes on the construction site can be quickly responded to, ensuring continuous and efficient operation. In short, this series of optimization steps not only improve the degree of intelligence but also make the power distribution more accurate and reliable, thus greatly enhancing the overall operation efficiency and safety of new energy road paving equipment.

[0125] Furthermore, the dynamic adjustment of different energy usage strategies is achieved through the following formula.

[0126] .

[0127] Among them, P t b represents the power provided by the battery at the current moment t; P t e represents the power provided by other energy sources at the current moment t; T represents the termination time step of the optimization time range; γ is the base value of the discount factor; γt is the cumulative impact of the discount factor over time step t; α is the energy consumption error penalty factor; β is the battery state penalty factor; P t f represents the predicted energy consumption demand at the current time step t; SOC t represents the remaining battery power at the current time step t.

[0128] In summary, through the optimization implementation of the above formula, the usage strategies of different energy sources have been refined and dynamically adjusted. Various parameters such as battery power, external energy power, battery state, and energy consumption error penalty act together to form an efficient, stable, and adjustable energy management mechanism. Through reasonable time steps, discount factors, energy consumption error penalties, and battery state management, it is possible to accurately regulate the distribution of energy according to real-time data and predicted demands, improve energy utilization efficiency, and at the same time ensure the healthy state of the battery. The dynamic adjustment of this strategy not only improves the working efficiency of new energy road paving equipment but also ensures its long-term stable operation, bringing great value to energy management and equipment operation and maintenance.

[0129] Furthermore, the construction parameter collaborative control module also includes the following components.

[0130] An adaptive control unit that real-time evaluates changes in the construction state and dynamically adjusts the control strategy parameters to ensure control adaptability.

[0131] A conflict detection and coordination unit that identifies possible conflicts or inconsistencies between different construction parameters and intervenes and coordinates them.

[0132] A construction parameter execution unit that converts the optimized control instructions into specific execution actions to achieve precise control of construction equipment.

[0133] In this embodiment, the adaptive control unit is a key component to ensure the continuous matching of the construction process with the on-site state. Its main function is to real-time evaluate changes in the construction state during the construction process and dynamically adjust the control strategy parameters to ensure the adaptability of construction parameters. For example, the terrain or material characteristics of the construction site may change with weather, construction progress, or other external factors, which requires the control system to be able to capture these changes in real-time and make corresponding adjustments. The adaptive control unit continuously monitors various construction parameters (such as temperature, humidity, equipment load, etc.) and inputs them into the control algorithm, adjusting the parameter values according to the current construction environment and working conditions. This mechanism can flexibly respond to environmental changes, ensuring the stability of construction quality and the efficient operation of construction equipment without manual intervention.

[0134] In this embodiment, the conflict detection and coordination unit is mainly responsible for identifying potential conflicts or disharmonies among construction parameters, and intervening and coordinating. In actual construction, due to the mutual constraints of various parameters, if not coordinated, it is easy to cause conflicts during the construction process, which will in turn affect the construction efficiency or quality. For example, too fast paving speed may lead to uneven material laying, too high temperature may affect the bonding effect of materials, and too low paving load may cause energy waste or damage to construction equipment. The conflict detection and coordination unit monitors various parameters during the construction process in real time by introducing a conflict identification algorithm. When potential conflicts are found, it adjusts the parameters in time or takes other measures for coordination. By establishing a set of precise conflict judgment rules and correction mechanisms, this unit can effectively avoid construction quality problems caused by parameter conflicts and improve the overall stability of the construction process. At the same time, this unit can also optimize the collaborative operation between devices to ensure that the collaborative operation between multiple devices and systems can reach the optimal state and reduce construction delays caused by improper collaboration.

[0135] In this embodiment, the construction parameter execution unit is a key component that converts the optimized control instructions into specific execution actions. It issues the optimal parameter control strategy obtained by the optimization strategy generation unit and the adaptive control unit to the construction equipment through the actual instructions of the execution unit to ensure the precise operation of the construction process. The technical effect of this unit is manifested in that it can accurately control the behavior of the construction equipment according to the changes in the real-time working conditions. For example, according to the optimized paving speed and load parameters, the execution unit can adjust the running speed or load of the paver to achieve the best paving effect. During the implementation process, the construction parameter execution unit also needs to monitor the response status of the equipment in real time to ensure that the actual operation of the equipment is consistent with the instructions. If there are deviations or faults, the execution unit can feedback and adjust the control strategy to ensure the smooth progress of the construction process. By accurately controlling the execution actions of the equipment, this unit effectively improves the construction efficiency, quality and safety.

[0136] In summary, the construction parameter collaborative control module is an indispensable part of the new energy road paving equipment. It significantly improves the construction efficiency, quality and safety through the precise control and collaborative optimization of various key parameters at the construction site. The design of each component closely revolves around the actual construction requirements. From parameter coupling analysis to conflict detection, from optimization strategy generation to adaptive control, it reflects the high integration and collaborative effect among the components. This module not only shows great advantages in improving construction quality and reducing energy consumption, but also enables the construction equipment to operate stably and efficiently under different working conditions through intelligent control and dynamic adjustment.

[0137] Furthermore, the terrain adaptive execution module includes the following components.

[0138] Suspension mechanism adjustment unit, by precisely controlling the angle and tension of the suspension mechanism, adapts to terrain changes in real time to ensure the stability and uniformity of the paving equipment on uneven roads.

[0139] Paving width adjustment unit, according to terrain features and construction requirements, automatically adjusts the paving width of the paving equipment to ensure the uniformity and accuracy of road paving.

[0140] Height compensation unit, based on ground height changes, compensates for terrain undulations by adjusting the height of the paving equipment to ensure that the paving layer is flat and meets the design requirements.

[0141] Terrain adaptation execution unit, calculates and executes adjustment commands for the suspension mechanism, paving width, and height to achieve adaptive control.

[0142] Vibration control unit, by adjusting vibration parameters, ensures uniform distribution of materials during the paving process and improves road quality.

[0143] In this embodiment, the suspension mechanism adjustment unit has the following characteristics: the response time of the hydraulic control system is less than 200 ms, the flow control accuracy is ±3%, and the pressure control accuracy is ±2%; the supported suspension height adjustment range is 0 - 450 mm, the adjustment accuracy is ±5 mm, and the maximum adjustment rate is 40 mm / s; the angle adjustment range is ±15°, the angle control accuracy is ±0.5°, and the maximum angular velocity is 4° / s; the damping adjustment range is a hardness coefficient of 200 - 2000 N·s / m, adjustable in 8 levels, and the response time is less than 250 ms; it has an active anti-tipping function, and when the lateral inclination exceeds 10°, it can complete automatic attitude adjustment within 2 seconds.

[0144] In this embodiment, the paving width adjustment unit can achieve the following functions: the width adjustment range is 2.5 - 8.0 m, the adjustment accuracy is ±10 mm, and the maximum adjustment rate is 80 mm / min; multi-segment width adjustment, supports 5-segment independent control, and the width of each segment can be independently adjusted to meet the needs of complex roads; an automatic width optimization algorithm based on terrain recognition, referring to terrain prediction 10 - 15 m ahead, plans width adjustment in advance; the width synchronization control error is less than 8 mm to ensure smooth road joints; it supports preset width configuration schemes, can store 8 groups of different width configuration templates, and realizes quick switching.

[0145] In this embodiment, the height compensation unit realizes the following functions: the vertical compensation range is from -150 mm to +200 mm, the compensation accuracy is ±4 mm, and the maximum compensation rate is 20 mm / s; a feedforward-feedback composite control strategy is adopted, the feedforward control is based on terrain prediction, and the feedback control is based on real-time height measurement; slope automatic adjustment is supported, the slope range is from -8% to +8%, and the slope accuracy is ±0.2%; an adaptive PID controller is provided, which automatically adjusts the PID parameters according to the terrain complexity, the integral time range is 0.5 - 5 s, and the differential time range is 0.1 - 1 s; an anti-jump mechanism is provided, when a terrain mutation is detected, the maximum compensation rate is limited to avoid system oscillation.

[0146] In this embodiment, the terrain adaptation execution unit integrates data from different sensors, including ground height, slope, road surface unevenness information, etc., and generates control commands through an accurate calculation model to adjust the working state of the device in real time. The innovation of this unit lies in its high degree of automation and intelligence, enabling the paving equipment to automatically adjust working parameters under different terrain conditions and ensuring the smooth progress of construction. Through linkage with other modules, the terrain adaptation execution unit can comprehensively consider various construction factors (such as road surface conditions, equipment load, etc.), accurately control the suspension mechanism, paving width, and equipment height, and optimize construction performance. This unit effectively reduces the complexity of manual operation and improves the adaptability and flexibility of the construction process. Especially on complex and irregular terrains, the terrain adaptation execution unit improves the quality and construction efficiency of the paving operation through real-time dynamic adjustment, enabling the equipment to successfully complete the construction task.

[0147] In this embodiment, the vibration control unit has the following characteristics: the adjustable range of vibration frequency is 10 - 70 Hz, the frequency adjustment accuracy is ±1 Hz, and the adjustable range of amplitude is 0.1 - 2.0 mm; a vibration parameter adaptive adjustment algorithm based on material temperature and thickness, the temperature detection range is 120 - 180 °C, and the thickness detection range is 30 - 200 mm; vibration energy partition control, supporting independent vibration control of 5 regions in the width direction of the paver to avoid over-vibration or under-vibration; intelligent resonance detection is provided, when a harmful resonance frequency is detected, the system automatically adjusts the vibration parameters; preset vibration modes are supported, storing 6 groups of vibration parameter configurations for different materials to quickly adapt to different material characteristics.

[0148] In summary, through precise adjustment of multiple functions such as suspension mechanism adjustment, paving width adjustment, height compensation, terrain adaptation execution, and vibration control, the terrain adaptive execution module enables the paving equipment to adapt to complex terrain conditions in real time. Through this module, the adaptability, stability, and operation accuracy of the paving equipment on uneven roads have been comprehensively improved. By automatically adjusting various key parameters, it can efficiently and precisely complete the paving task, ensure that the road surface quality meets the design requirements, and at the same time improve the construction efficiency and the service life of the equipment. The introduction of the terrain adaptive execution module enables high-quality construction of paving operations under various terrain conditions, greatly enhancing the flexibility and economy of intelligent construction.

[0149] Furthermore, by precisely controlling the angle and tension of the suspension mechanism to adapt to terrain changes in real time, the following steps are included.

[0150] Based on the ground height change data collected in real time, use the following formula to calculate the angle that the suspension mechanism needs to be adjusted: θ(t)=arctan{[z ground (t)-z ground (t - Δt)] / d(t)}, where θ(t) represents the angle of the suspension mechanism at time t; z ground (t) represents the value of the ground height at time t; z ground (t - Δt) represents the value of the ground height at time t - Δt; d(t) represents the horizontal distance between the current position of the equipment and the previous moment t - Δt at time t.

[0151] According to the calculated suspension angle, combined with the weight of the equipment and the ground undulation, use the following formula to calculate the required suspension tension: T(t)=k1·θ(t) 2 +k2·∣z ground (t)-z ground (t - Δt)∣ / d(t)+k3·W, where T(t) represents the tension required for the suspension mechanism at time t; W represents the weight of the equipment; k1 represents the suspension mechanism response sensitivity coefficient; k2 represents the ground change sensitivity coefficient; k3 represents the influence coefficient of the equipment weight on the suspension tension.

[0152] By adjusting the suspension angle and tension in real time, dynamically control each part of the equipment to enable the equipment to operate stably under different terrain conditions.

[0153] Combined with the ground change, suspension angle, and tension, use the following formula to evaluate the stability and uniformity of the paving equipment: S(t)=k4·(1 - ∣z ground (t)-z ground(t - Δt)∣ / d(t)) + k5·θ(t) + k6·T(t), where S(t) represents the evaluation value of the stability and uniformity of the equipment at time t; k4 represents the stability and uniformity adjustment coefficient; k5 represents the coefficient of the change rate of the tension of the suspension mechanism; k6 represents the adaptive control adjustment coefficient.

[0154] In summary, by precisely controlling the angle and tension of the suspension mechanism, the paving equipment can adapt to terrain changes in real time, ensuring the smoothness and uniformity during the construction process. The adjustment of the angle and tension of the suspension mechanism not only improves the adaptability of the equipment but also guarantees the stability of the construction quality. Especially in complex terrains, it can ensure the continuous and efficient operation of the paving equipment. In addition, based on the real-time evaluation of ground changes, suspension angles, and tensions, the stability of the equipment can be effectively monitored, and the construction quality can be ensured through dynamic adjustment. These technical measures work together to enable the paving equipment to achieve precise paving operations under various terrain conditions, improving the construction efficiency and ensuring the construction quality.

[0155] Furthermore, according to the terrain characteristics and construction requirements, automatically adjust the paving width of the paving equipment, including the following steps.

[0156] Conduct real-time monitoring and numerical analysis of the lateral slope, longitudinal undulation, and subgrade width change of the road, and calculate the optimal paving width parameters to ensure uniform coverage of the target area.

[0157] Precisely adjust the displacement of the telescopic arms on both sides of the paver according to the optimal paving width parameters to achieve dynamic width adjustment.

[0158] Real-time monitor the material supply rate and adaptively adjust the process parameters according to the change of the paving width to effectively prevent material segregation and uneven distribution.

[0159] In summary, by precise real-time monitoring and dynamic adjustment, automatically adjusting the paving width of the paving equipment not only optimizes the working efficiency during the construction process but also greatly improves the accuracy and quality of road construction. First, real-time monitoring of the lateral slope, longitudinal undulation, and subgrade width change of the road enables the adjustment of the paving width to precisely respond to terrain changes, avoiding paving errors. Second, the precise adjustment of the displacement of the telescopic arms ensures the uniformity and construction accuracy of the paving width, significantly improving the degree of automation of the construction and reducing the need for manual intervention. Finally, by dynamically adjusting the material supply rate, it effectively avoids material segregation and uneven distribution caused by the change of the paving width, thus ensuring the quality and stability of the paving process.

[0160] Furthermore, based on the change of the ground height, compensate for terrain undulation by adjusting the height of the paving equipment, including the following steps.

[0161] According to the road surface elevation requirements in the construction design drawings, combined with the measured terrain data, use the preset compensation algorithm to calculate the ideal height compensation value for each position point, and comprehensively consider the settlement amount after material compaction to generate dynamic height adjustment instructions.

[0162] Precisely control the telescoping of the hydraulic cylinder through an electro-hydraulic proportional valve, drive the screed of the paver to move up and down, and achieve real-time height adjustment.

[0163] During the compensation process, continuously monitor the thickness and flatness of the paving layer, and based on the comparative analysis of multi-point measurement data, dynamically optimize the compensation parameters to ensure that the flatness of the paving surface always meets the specification requirements in both the transverse and longitudinal directions.

[0164] In summary, by combining the construction design drawings and real-time terrain data, the paving equipment can perform dynamic compensation based on the ground height changes. The implementation of this process relies on precise calculations and optimized control to ensure that the flatness and thickness of the paving layer during construction can be maintained within the design requirements. First, by using the compensation algorithm to calculate the ideal height compensation value and combining the prediction of material settlement, height adjustment instructions can be accurately generated. Next, the electro-hydraulic proportional valve precisely controls the telescoping of the hydraulic cylinder to push the screed of the paver for height adjustment, achieving real-time adaptation to terrain undulations. Finally, through multi-point measurement and real-time feedback mechanisms, the height parameters during the compensation process can be continuously optimized to ensure that the paved layer always meets the requirements.

[0165] Furthermore, the intelligent decision-making control module includes the following components.

[0166] System comprehensive state evaluation unit, based on the basic evaluation results of the intelligent perception module, evaluate the state of the construction system from a global perspective and generate the state feature vector required for decision-making.

[0167] Strategy generation unit, based on the hierarchical reinforcement learning algorithm, decompose the complex construction control problem into multiple levels of sub-tasks and generate corresponding control strategies for each level.

[0168] Action coordination unit, coordinate and integrate the control strategies at each level to form a unified control instruction sequence to ensure the connectivity between each control action.

[0169] Execution supervision and evaluation unit, supervise and evaluate the control execution effects of each module, including parameter control effect evaluation and abnormal state identification.

[0170] Global strategy optimization unit, based on the execution supervision and evaluation results, uniformly optimize and adjust the control strategies at each level to improve the overall control effect.

[0171] In this embodiment, the system comprehensive status evaluation unit includes the following functions: The dimension of the status feature vector is 24, including key indicators such as equipment status, environmental conditions, construction quality, and efficiency; A comprehensive scoring system that maps each indicator to the 0-100 score range based on the fuzzy comprehensive evaluation method; The status evaluation period is 1000 ms, which updates the system status score in real time and records the status change trend; It has an abnormal status detection function, using the isolation forest algorithm, with an abnormal detection rate greater than 90% and a false alarm rate less than 5%; The visualization of the status evaluation results supports the dashboard mode and the trend chart mode, facilitating operators to quickly understand the system status.

[0172] In this embodiment, the policy generation unit implements the following functions based on the hierarchical reinforcement learning algorithm: A three-layer policy architecture, including high-level planning (15-30 minutes), middle-level scheduling (1-5 minutes), and low-level execution (0-60 seconds); The high-level policy network uses the DDPG algorithm, with an update frequency of once every 10 minutes and a learning rate of 0.0005; The middle-level policy network uses the SAC algorithm, with an update frequency of once every 60 seconds and a learning rate of 0.001; The low-level policy network uses the TD3 algorithm, with an update frequency of once every 10 seconds and a learning rate of 0.002; An inter-layer policy coordination mechanism that ensures the consistency of each layer of policies through goal decomposition and constraint propagation, with a coordination accuracy greater than 85%.

[0173] In this embodiment, the action coordination unit has the following characteristics: An action conflict resolution mechanism based on priority sorting, setting 5 priority levels, and high-priority actions can override low-priority actions; An action smooth transition algorithm to ensure that the action change rate between adjacent control cycles does not exceed the preset threshold and avoid control jitter; Action execution timing planning, decomposing complex actions into primitive action sequences and executing them according to the optimal timing; It has an action constraint verification function to ensure that all actions meet the equipment physical limitations and safety constraints; It supports action combination optimization, forming composite actions by combining multiple basic actions to improve control efficiency.

[0174] In this embodiment, the execution supervision and evaluation unit includes the following functions: Parameter control effect evaluation, forming an 8-dimensional evaluation index vector by calculating the deviation between the target value and the actual value; Monitoring of key performance indicators (KPIs), including paving flatness, compaction degree, energy consumption efficiency, and progress compliance, etc.; Identification of abnormal execution status, based on the statistical process control (SPC) method, setting ±3σ control limits to monitor process anomalies in real time; Execution delay monitoring, monitoring the time delay from the issuance of the control instruction to the completion of execution, with a normal range of 100-800 ms; Execution effect prediction, based on the Bayesian network, predicting the long-term execution effect of the current control strategy.

[0175] In this embodiment, by analyzing the data collected by the execution supervision and evaluation unit, the global policy optimization unit can identify the deficiencies between control levels and propose optimization solutions. The core of this unit lies in optimizing the accuracy and flexibility of the overall system decision-making. Especially in complex construction environments, global optimization can coordinate among multiple tasks to ensure the optimal collaborative work of each module. The global policy optimization unit adopts advanced optimization algorithms, such as particle swarm optimization, genetic algorithms, etc., and realizes the dynamic adjustment of the strategies of each control level by solving multi-objective and multi-constraint optimization problems. This unit can optimize the system from an overall perspective, thereby enhancing the system's adaptability to external environmental changes and enabling construction tasks to proceed continuously and stably under different working conditions. The optimization process not only improves the individual efficiency of each control module but also enables the entire construction system to operate more efficiently, with lower energy consumption, and in a more collaborative manner, ultimately promoting the timely and high-quality completion of construction projects.

[0176] In summary, the various component units of the intelligent decision-making control module cooperate closely to jointly promote the development of the construction system towards intelligence and automation. From the system comprehensive state evaluation unit to the global policy optimization unit, each unit plays a crucial role in ensuring that every link in the construction process can be optimized and controlled under dynamically changing working conditions. Through technical means such as intelligent perception, hierarchical reinforcement learning, motion coordination, real-time supervision, and global optimization, the intelligent decision-making control module can achieve efficient scheduling and precise control in complex construction environments. Ultimately, this module not only improves the automation level of the construction process but also reduces manual intervention and decision-making errors while ensuring construction quality and efficiency, thereby enhancing the overall intelligence level of construction.

[0177] Furthermore, the safety monitoring module includes the following components.

[0178] The safety risk identification unit, based on predefined safety threshold parameters and risk assessment models, timely identifies potential safety hazards and abnormal states.

[0179] The intelligent fault diagnosis unit, based on preset diagnosis rules and historical data, conducts root cause analysis and precise positioning of potential safety hazards and abnormal states.

[0180] The early warning management unit, according to the risk identification results and the output of fault diagnosis, automatically generates hierarchical early warning information and accurately pushes it to relevant responsible persons.

[0181] The emergency response unit formulates standardized emergency response procedures for different types of safety incidents and provides real-time disposal guidance and implementation suggestions.

[0182] The closed-loop verification and optimization unit continuously optimizes the safety early warning and emergency response systems to improve the accuracy and response efficiency of safety management.

[0183] In this embodiment, the security risk identification unit has the following characteristics: a security risk assessment model, based on a hierarchical Bayesian network, contains 64 nodes, and the assessment accuracy is greater than 90%; the risk levels are divided into 5 levels, namely minor risk, low risk, medium risk, high risk and severe risk; the real-time risk monitoring frequency is 5Hz, and the monitoring frequency of important security parameters reaches 50Hz; it has the function of predicting the spread of security risks and can predict the potential spread path and influence range of risks in the system; it supports multi-dimensional risk assessment, including dimensions such as personnel safety, equipment safety, environmental safety and construction quality safety.

[0184] In this embodiment, the intelligent fault diagnosis unit includes the following functions: fault mode recognition based on deep learning, supports the recognition of 48 common fault types, and the recognition accuracy is greater than 92%; fault propagation analysis, based on a directed acyclic graph model, analyzes the root cause and influence path of faults; fault severity assessment, divides faults into 4 severity levels, and calculates the fault impact index (0 - 100); has the function of predictive maintenance, predicts the possibility and time of potential faults based on equipment operation data; supports the integration of an expert knowledge base, which contains more than 800 fault diagnosis rules and treatment plans.

[0185] In this embodiment, the early warning management unit realizes the following functions: hierarchical push of early warning information, divided into level 1 - 5 early warnings according to the risk level, and each level of early warning corresponds to a different push strategy; accurate positioning of early warning information, determines the early warning position through a positioning algorithm, and the positioning accuracy is better than ±2m; multi-channel early warning push, supports pushing early warnings through methods such as the device operation interface, mobile application, SMS and audible and visual alarms; early warning confirmation and tracking mechanism, requires the recipient to confirm the early warning within a specified time (within 15 minutes for level 1 early warning, within 45 minutes for level 2 early warning, within 3 hours for level 3 early warning, within 12 hours for level 4 early warning, within 24 hours for level 5 early warning); early warning statistical analysis function, conducts statistics and trend analysis on historical early warning data, and supports the identification of early warning hotspots.

[0186] In this embodiment, the emergency response unit has the following characteristics: a standardized emergency response process library, which contains the response processes for more than 150 emergency scenarios; an emergency resource scheduling function, automatically calculates the required resources and provides scheduling suggestions according to the emergency level and type; an emergency decision-making assistance system, based on a hybrid reasoning engine that combines case-based reasoning and rule-based reasoning; real-time assessment of the disposal effect, monitors and evaluates the effectiveness of emergency response through key indicators; has the function of simulating emergency drills, supports the simulation and evaluation of 15 typical emergency scenarios.

[0187] In this embodiment, the closed-loop verification and optimization unit evaluates the actual effects of safety monitoring and emergency response by collecting and analyzing data during the execution process, and proposes improvement plans. In terms of technical effects, the closed-loop verification and optimization unit can, through the feedback mechanism, compare the actual safety management data at the construction site with the preset safety standards, identify potential management loopholes or deficiencies, and provide a basis for system optimization. By analyzing the feedback of early warning information, the execution situation and results of emergency response, the early warning mechanism, diagnostic rules and emergency response plans can be continuously adjusted and improved, forming a dynamically optimized safety management closed loop. For example, if it is found that the response speed of a certain safety early warning information is slow, or there are problems with some emergency plans in actual operation, the strategy will be adjusted according to historical data and feedback to improve the response efficiency. In terms of technical effects, this closed-loop optimization mechanism effectively improves the system's adaptability and continuous improvement ability, enabling the safety monitoring module to continuously evolve during long-term operation to adapt to the increasingly complex construction environment and changing safety requirements.

[0188] In summary, the safety monitoring module forms an all-round and dynamic safety management mechanism by integrating multiple components. From safety risk identification, intelligent fault diagnosis to early warning management, emergency response and closed-loop verification and optimization, each sub-unit cooperates with each other to jointly improve the safety prevention and control ability at the construction site. In terms of technical effects, the safety monitoring module can not only identify and analyze potential safety hazards in real time, but also automatically generate emergency response plans and optimize the working efficiency of the entire system. This comprehensive intelligent safety management system significantly improves the safety during the construction process, reduces the probability of accidents, and can quickly and effectively handle emergencies when they occur, thus ensuring the safety of construction personnel and the smooth progress of construction projects.

[0189] As Figure 2 shown, this embodiment also provides a control method for a new energy road paving device adaptable to terrain, including the following steps.

[0190] Construct a digital construction scene model including terrain features, environmental parameters and equipment status to provide a data basis for subsequent decision-making and control.

[0191] Formulate initial control strategies at each level, establish a safety monitoring system, evaluate potential risks in real time and formulate emergency plans to ensure the safety and reliability of the decision-making process.

[0192] By designing a multi-objective reward function, combining historical data and current working conditions, predict the energy consumption demand and optimize the charge and discharge strategy in real time to achieve efficient management of new energy power.

[0193] By establishing a parameter coupling analysis and fuzzy decision-making mechanism, selecting the optimal parameter combination, and constructing a constraint equation system, the adaptive adjustment and coordinated control of the key construction parameters are realized.

[0194] The electro-hydraulic proportional valve is used to precisely control the suspension mechanism, telescopic boom, and hydraulic cylinder to achieve the dynamic adaptive adjustment of the paving equipment. At the same time, the material supply rate and paving layer thickness are monitored in real time, and the compensation parameters are dynamically optimized based on the measured data to ensure that the construction quality always meets the specification requirements.

[0195] In summary, the control method of the new energy road paving equipment adaptable to terrain realizes the precise control of the construction environment and equipment state through the coordinated work of multiple technical links. Through the construction of a digital construction scene model, the formulation of an initial control strategy, the optimization of a multi-objective reward function, the combination of parameter coupling analysis and fuzzy decision-making mechanism, and the application of precise control of electro-hydraulic proportional valves, the various working parameters of the equipment can be dynamically adjusted to ensure the optimal combination of construction quality, construction progress, and energy efficiency. In terms of technical effects, the entire control method not only improves the adaptability and flexibility of the equipment but also enhances the safety, reliability, and efficiency of the construction process, providing an innovative and efficient solution for the construction of new energy roads.

[0196] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control system for a new energy road paving device adaptable to terrain, characterized in that, It includes the following modules: An intelligent perception module that realizes the precise perception and recognition of terrain features and construction environment parameters, and completes the collection and feature analysis of construction condition data; A new energy power management module that realizes the intelligent optimization of battery management, energy consumption prediction, and power distribution; A construction parameter collaborative control module that realizes the adaptive adjustment and collaborative control between key construction parameters, including a parameter coupling analysis unit and an optimization strategy generation unit. Among them: the parameter coupling analysis unit identifies the mutual influence and dependence relationship between parameters through the coupling analysis of various key construction parameters at the construction site; the optimization strategy generation unit generates the optimal parameter control strategy by using a multi-objective optimization algorithm according to the output result of the parameter coupling analysis unit. The specific steps are as follows: based on the mutual influence and dependence relationship between parameters, construct multiple objective functions covering paving flatness, compaction degree, and energy consumption, and set evaluation indicators and quantization criteria for each objective function; combined with the actual engineering requirements and equipment physical limitations, establish a set of constraint conditions covering parameter value ranges, parameter change rates, and safety thresholds, and at the same time consider the coupling constraint relationship between parameters to construct a complete constraint equation set; through integrating expert experience and historical data analysis, dynamically evaluate the importance of objectives under different construction conditions to form an adaptive weight adjustment mechanism; use the non-dominated sorting genetic algorithm III to solve the multi-objective optimization problem, and continuously approximate the Pareto optimal solution set through population evolution iteration. At the same time, introduce crowding degree calculation to maintain the diversity of the solution set to ensure that a set of uniformly distributed non-dominated solutions can be obtained; based on the fuzzy decision theory, comprehensively evaluate the candidate solutions on the Pareto front, and select the parameter combination most suitable for the current construction needs by establishing a decision matrix and combining the current working condition characteristics to form a specific control strategy to achieve the optimal trade-off between multiple objectives; A terrain adaptive execution module that realizes the adaptive adjustment of highway paving equipment under different terrain conditions; An intelligent decision-making control module that formulates and supervises the execution of the optimal control strategy for the overall construction process through hierarchical reinforcement learning; A safety monitoring module that ensures the prevention and emergency response of potential risks during the construction process; A human-machine interaction module that provides an intuitive visual interface and intelligent operation suggestions; The new energy power management module includes the following components: A battery management unit that monitors the battery's power, temperature, and health status in real time to ensure the safe and efficient operation of the battery and optimize the charging and discharging strategies; An energy consumption prediction unit that uses historical data and environmental information to predict future energy consumption requirements; A power distribution optimization unit that optimizes the power distribution strategy by using a reinforcement learning algorithm based on real-time energy consumption prediction and battery status to achieve the optimal utilization of electricity and resources; An energy scheduling decision-making unit that dynamically adjusts the usage strategies of different energies according to the prediction results and current demands to balance the load and improve efficiency; A charging and discharging strategy unit that intelligently adjusts the charging and discharging strategies according to the feedback of the battery management unit; An energy environment adaptation unit that adjusts the energy consumption management and battery working mode in real time based on the environmental data provided by the intelligent perception module; The terrain adaptive execution module includes the following components: The suspension mechanism adjustment unit adapts to terrain changes in real time by precisely controlling the angle and tension of the suspension mechanism; The paving width adjustment unit automatically adjusts the paving width of the paving equipment according to terrain features and construction requirements; The height compensation unit compensates for terrain undulations by adjusting the height of the paving equipment based on ground height changes; The terrain adaptation execution unit calculates and executes adjustment commands for the suspension mechanism, paving width, and height to achieve adaptive control; The vibration control unit ensures uniform distribution of materials during the paving process by adjusting vibration parameters.

2. The control system of the new energy road paving equipment adaptable to terrain according to claim 1, characterized in that, The intelligent perception module includes the following components: The environment perception unit collects environmental parameters of the construction site through multi-source sensors; The terrain scanning unit is used to perform three-dimensional scanning and modeling of the construction area to achieve high-precision digital expression of terrain features; The working condition monitoring unit collects data on the operating state and working parameter of the construction equipment using vibration, pressure, and displacement sensors; The data preprocessing unit performs noise reduction, standardization, and feature extraction on the collected raw data; The feature recognition unit performs pattern recognition and feature analysis on the preprocessed data and outputs key construction parameters; The data storage unit classifies, stores, and manages the processed perception data, supporting historical data query and in-depth mining.

3. The control system of the new energy road paving equipment adaptable to terrain according to claim 1, characterized in that Based on real-time energy consumption prediction and battery status, the power distribution strategy is optimized using a reinforcement learning algorithm, including the following steps: Construct a multi-dimensional state space covering the state of charge of the battery, temperature distribution, charge and discharge power, and historical energy consumption data. At the same time, based on the current construction working condition and environmental conditions, extract key feature indicators reflecting the dynamic operating state characteristics of the paving equipment; Define a continuous action space covering power distribution ratio and power output. At the same time, based on battery performance constraints and equipment power requirements, establish action boundary conditions and design corresponding penalty mechanisms; Design a multi-objective reward function based on weighted summation to comprehensively evaluate energy utilization efficiency, battery life, and power response performance; Adopt the deep deterministic policy gradient algorithm to collect experience data through environmental interaction and iteratively optimize the network parameters of the power distribution strategy; Establish a strategy fine-tuning trigger mechanism based on performance evaluation indicators to achieve online adaptive optimization of the network parameters of the strategy.

4. The control system of the new energy road paving equipment adaptable to terrain according to claim 1, characterized in that The construction parameter collaborative control module also includes the following components: The adaptive control unit evaluates changes in the construction state in real time and dynamically adjusts the control strategy parameters to ensure control adaptability; The conflict detection and coordination unit identifies conflicts or inconsistencies between different construction parameters and intervenes and coordinates; The construction parameter execution unit converts the optimized control instructions into specific execution actions to achieve precise control of the construction equipment.

5. The control system of the new energy road paving equipment adaptable to terrain according to claim 1, characterized in that, The intelligent decision-making control module includes the following components: The system comprehensive state evaluation unit evaluates the state of the construction system from a global perspective based on the basic evaluation results of the intelligent perception module and generates the state feature vector required for decision-making; The strategy generation unit decomposes complex construction control problems into multiple levels of sub-tasks based on the hierarchical reinforcement learning algorithm and generates corresponding control strategies for each level; The motion coordination unit coordinates and integrates control strategies at all levels to form a unified control instruction sequence; The execution supervision and evaluation unit supervises and evaluates the control execution effects of each module, including parameter control effect evaluation and abnormal state identification; The global strategy optimization unit uniformly optimizes and adjusts control strategies at all levels based on the execution supervision and evaluation results.

6. The control system of the new energy road paving equipment adaptable to terrain according to claim 1, characterized in that, The safety monitoring module includes the following components: The safety risk identification unit timely identifies potential safety hazards and abnormal states based on predefined safety threshold parameters and risk assessment models; The intelligent fault diagnosis unit conducts root cause analysis and precise positioning of potential safety hazards and abnormal states based on preset diagnosis rules and historical data; The early warning management unit automatically generates hierarchical early warning information and accurately pushes it to relevant responsible persons according to the risk identification results and the output of fault diagnosis; The emergency response unit formulates standardized emergency response procedures for different types of safety incidents, provides real-time handling guidance and implementation suggestions; The closed-loop verification and optimization unit continuously optimizes the safety early warning and emergency response system to improve the accuracy and response efficiency of safety management.

7. The control method of the new energy road paving equipment adaptable to terrain is realized based on the control system of the new energy road paving equipment adaptable to terrain according to any one of claims 1-6, and is characterized in that It includes the following steps: Construct a digital construction scenario model including terrain features, environmental parameters, and equipment status to provide a data basis for subsequent decision-making and control; Formulate initial control strategies at all levels, establish a safety monitoring system, and evaluate potential risks in real time and formulate emergency plans to ensure the safety and reliability of the decision-making process; By designing a multi-objective reward function, combining historical data and current working conditions, predict the energy consumption demand and optimize the charge and discharge strategy in real time to achieve efficient management of new energy power; By establishing a parameter coupling analysis and fuzzy decision-making mechanism, select the optimal parameter combination and construct a constraint equation set to achieve adaptive adjustment and coordinated control of key construction parameters; Precisely control the suspension mechanism, telescopic boom, and hydraulic cylinder using electro-hydraulic proportional valves to achieve dynamic adaptive adjustment of the paving equipment; at the same time, monitor the material supply rate and paving layer thickness in real time, and dynamically optimize compensation parameters based on the measured data to ensure that the construction quality always meets the specification requirements.

Images