Intelligent monitoring method for continuous compaction of railroad bed

Abstract

The invention relates to the technical field of railway engineering, and discloses an intelligent monitoring method for continuous compaction of a railway roadbed, which comprises the following steps: step 1, setting a test section and preparing for data acquisition: dividing a test section area and installing intelligent continuous compaction equipment on a road roller, acquiring a plurality of construction parameters such as soil compaction degree, rolling times, road roller pressure, vibration frequency and environment temperature and humidity; and 2, data acquisition and transmission: acquiring the construction parameters in real time, and transmitting the data to a cloud data platform through a wireless network for storage and analysis. By means of the intelligent continuous compaction system, the quality uniformity and accuracy in the railway roadbed compaction process are improved, and the problems of pressure leakage and overpressure are avoided; the construction efficiency is improved, and the construction period is shortened; the traceability of construction quality is enhanced, and the management level is improved; manual intervention is reduced, and personal errors are reduced; data support and technical reference are provided for later maintenance and similar projects, and the method has high popularization value.

Description

Technical Field

[0001] The invention relates to the technical field of railway engineering, and in particular to an intelligent monitoring method for continuous compaction of railway roadbed. Background Art

[0002] With the rapid development of railway construction in my country, railway subgrade filling technology has gradually become a key link in ensuring the safety and stability of railway operations. The traditional railway subgrade filling process uses conventional roller equipment for compaction, and the compaction degree and uniformity mainly depend on the experience of the operator and the working status of the equipment. However, with the expansion of the scale of railway construction and higher requirements for construction quality, traditional manual operation methods and equipment control methods can no longer meet the requirements of modern railway construction for construction accuracy and efficiency. Therefore, more and more research and engineering practices have begun to develop in the direction of intelligence and efficiency, especially the introduction of intelligent continuous compaction technology, which has gradually become an important means to improve the quality of railway subgrade construction.

[0003] In the prior art, conventional compaction methods face a series of problems. Traditional rollers mainly rely on manual adjustment and operation, and the construction quality is easily affected by the operator's experience and equipment performance, resulting in problems such as underpressure, overpressure or uneven compaction during the compaction process. In addition, the existing roadbed compaction detection is carried out after the compaction is completed, and the results are often random and accidental, lacking real-time and controllability. Therefore, it is difficult to strictly control the construction quality under traditional methods, and the construction cycle is long and the efficiency is low. In order to effectively solve these problems, there is an urgent need for an intelligent control method that can monitor and automatically adjust the compaction process in real time, thereby improving construction quality, shortening construction period and reducing human errors. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent monitoring method for continuous compaction of railway roadbed, which solves the problems of uneven compaction quality, low construction efficiency and inaccurate quality control caused by reliance on manual operation and traditional equipment control in the prior art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a railway roadbed continuous compaction intelligent monitoring method, comprising the following steps:

[0006] Step 1: Test section setting and data collection preparation: By demarcating the test section area and installing intelligent continuous compaction equipment on the roller, multiple construction parameters such as soil compaction, number of rolling passes, roller pressure, vibration frequency, and ambient temperature and humidity are obtained;

[0007] Step 2: Data collection and transmission: collect the above construction parameters in real time and transmit the data to the cloud data platform through wireless network for storage and analysis;

[0008] Step 3: Data analysis and modeling: Based on the collected data, a multivariate linear regression or machine learning method is used to establish a relationship model between roadbed compaction and construction parameters;

[0009] Step 4: Real-time compaction control and optimization: According to the established compaction prediction model, the rolling parameters of the roller are adjusted in real time to ensure that the compaction of each layer of roadbed filler meets the design requirements;

[0010] Step 5: Construction quality monitoring and feedback: real-time detection and feedback of the compaction degree of each layer, generation of construction quality reports, and alarm prompts and adjustments for unqualified areas;

[0011] Step 6: Result analysis and optimization: conduct post-analysis of the data during the construction process, adjust the construction parameters and optimize the model according to the construction situation.

[0012] Preferably, the intelligent continuous compaction equipment includes a vibration sensor, a temperature and humidity sensor, a pressure sensor and a GPS positioning system, and the sensors are used to monitor multiple environmental and mechanical parameters during the construction process.

[0013] Preferably, the data transmission is performed via a wireless network or Bluetooth, and the parameters are uploaded to a cloud data platform in real time for storage, processing and remote viewing.

[0014] Preferably, the data analysis step uses a machine learning model, including a support vector machine, a random forest or a deep learning algorithm, to improve the accuracy and robustness of compaction prediction.

[0015] Preferably, the real-time feedback during the construction process includes displaying the construction progress and compaction distribution through a visual graphic interface, and marking qualified and unqualified areas with colors.

[0016] Preferably, the real-time control and optimization step automatically adjusts the working parameters of the roller, including vibration frequency, number of rolling passes and roller pressure, through an intelligent system to achieve the best compaction effect.

[0017] Preferably, the construction quality monitoring is performed by combining regular automatic detection with manual inspection to ensure that the compaction degree of each layer of roadbed filler meets the design standard.

[0018] Preferably, the construction quality feedback mechanism includes the generation of a construction quality report and early warning reminders for unqualified areas to ensure immediate adjustments during the construction process.

[0019] Preferably, the adjustment of the construction parameters is remotely controlled via a cloud platform, thereby achieving information sharing and data interaction between the construction site and background monitoring personnel.

[0020] Preferably, the intelligent system is able to continuously optimize construction parameters and prediction models based on historical construction data.

[0021] The present invention provides an intelligent monitoring method for continuous compaction of railway roadbed. It has the following beneficial effects:

[0022] 1. The present invention realizes real-time monitoring and precise control of the compaction process through intelligent continuous compaction equipment, thereby effectively avoiding the problems of underpressure and overpressure in traditional compaction methods. The intelligent equipment can continuously monitor and adjust the working status of the compaction equipment to ensure that the compaction degree of each layer of roadbed is uniform and meets the design requirements. Through this technology, the distribution of compaction degree is more balanced, which improves the overall quality of roadbed filling and avoids the problems of later settlement and cracks caused by uneven compaction.

[0023] 2. The present invention adopts real-time data collection and automatic analysis technology, which can adjust construction parameters according to real-time feedback during the construction process, reducing the frequent manual inspection and adjustment in traditional methods, greatly improving construction efficiency, and avoiding rework and repeated operations by accurately controlling the compaction process, thereby effectively shortening the construction period, accelerating the project progress, and promoting the overall improvement of construction efficiency.

[0024] 3. The present invention can record and archive all relevant data of the compaction process in real time during the entire construction process through the intelligent monitoring system. These data not only provide a sufficient basis for the acceptance and monitoring of construction quality, but also serve as an important reference in later maintenance and repair. Through this system, management personnel can grasp the construction progress and quality status in real time, improve the transparency and decision-making efficiency of on-site management, and ensure the traceability of construction quality.

[0025] 4. The present invention reduces human intervention during the construction process by introducing an intelligent monitoring system. The adjustment and detection of all compaction parameters are automatically completed by intelligent equipment, which significantly reduces human errors. This technology effectively improves the accuracy of the construction process and ensures the consistency and quality reliability of the compaction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] Example:

[0029] Please see attached Figure 1 The embodiment of the present invention provides a method for intelligently monitoring continuous compaction of railway roadbed, comprising the following steps:

[0030] Step 1: Test section setting and data collection preparation: By demarcating the test section area and installing intelligent continuous compaction equipment on the roller, multiple construction parameters such as soil compaction, number of rolling passes, roller pressure, vibration frequency, and ambient temperature and humidity are obtained;

[0031] In this embodiment, step 1 involves preparing for data collection by selecting an appropriate test section. This process includes demarcating the construction area, laying out the test section, and installing smart devices, etc., in order to provide a reliable experimental data basis for subsequent data collection and analysis.

[0032] As an option, the selection of the test section should be based on the representativeness of the terrain, soil quality and construction environment. Specifically, a representative area should be demarcated in the actual construction area, and its length is usually not less than 30 meters. It should be divided into several different areas, such as light area, medium area and heavy area, according to the soil characteristics of different construction areas, the type of roadbed filling materials and the adaptability of compaction equipment. Different construction standards and parameters are set for each area according to its soil compaction, filling material type and construction equipment requirements.

[0033] It should be noted that in some embodiments, the test section may adopt different construction control strategies according to the soil type, the particle size distribution of the roadbed filler and the filler type. For example, the light area may use fillers with smaller particle sizes and require lower compaction; the medium area may use fillers with medium particle sizes and require stricter compaction; and the heavy area may use fillers with larger particles or chemically improved soil, requiring higher compaction and uniformity.

[0034] In one possible implementation, the selection and division of the construction area should ensure representativeness, especially in terms of soil type and environmental conditions. For example, soil compaction behavior may be different under different climate and humidity conditions, and the selection of the test section should fully consider these variables.

[0035] Specifically, the layout of the test section usually includes the setting of multiple data collection points. At least three collection points are required for each area, and the locations of these collection points should be reasonably arranged according to the needs of the project to ensure that the data collection in each area is highly representative. The selection of data collection points should avoid local deviations, especially in terms of filler distribution and construction equipment configuration, to avoid overly concentrated data collection points leading to inaccurate analysis results.

[0036] In some embodiments, the location of data collection points should not only take into account differences in soil types, but also include the travel path of construction machinery and equipment, such as rollers. In order to fully understand the compaction conditions of different areas during the construction process, the collection points should be distributed in the front, middle, and rear of the construction machinery to ensure that the data obtained during the compaction process covers the entire process.

[0037] The construction preparation stage of the test section also includes the installation of intelligent equipment. Intelligent compaction equipment usually includes but is not limited to pressure sensors, vibration sensors, temperature and humidity sensors, and GPS positioning devices. Specifically, the vibration sensor is used to monitor the vibration frequency and amplitude of the roller in order to analyze the reaction of the soil; the temperature and humidity sensor is used to detect the impact of ambient temperature and humidity on soil compaction; the pressure sensor is used to monitor the pressure applied by the roller; the GPS positioning device is used to record the location of the construction point and the construction path in real time. These sensors upload real-time data to the cloud data platform through wireless communication modules to ensure that data during the construction process can be accurately collected and stored.

[0038] As an option, all installed sensors and equipment should be connected to the data acquisition system by wire or wireless to ensure real-time transmission and integrity of data. It is understandable that the layout and installation location of the sensors need to be flexibly adjusted according to the specific characteristics of the test section. For example, more sensors are set at the front of the roller to detect the compaction of the initial fill in real time; while sensors are set at the rear of the roller to monitor the data changes after compaction.

[0039] In some embodiments, the data acquisition system should have high-precision, low-latency transmission capabilities to ensure that the collected data can be uploaded to the cloud platform in real time. The wireless network can use technologies such as Wi-Fi, Bluetooth or LTE to ensure stable data transmission under the complex environment of the construction site. The cloud platform will receive sensor data from the construction site in real time and perform preliminary storage, backup and processing.

[0040] In this application, the installation location, sensing accuracy and data transmission frequency of all sensors and equipment should be verified by preliminary experiments to ensure that they can fully meet the needs of construction quality monitoring. For example, in some construction environments with high precision requirements, it may be necessary to use higher-precision sensors, such as millimeter-level positioning GPS devices or high-frequency vibration sensors, to improve data accuracy and reliability.

[0041] Specifically, the data acquisition system in this embodiment should also support multiple communication protocols to ensure efficient connection between the construction site equipment and the cloud platform. The cloud platform processes the uploaded data through advanced data analysis algorithms, calculates various key parameters in the construction process, such as the compaction degree of the filler, vibration intensity and mechanical pressure, and analyzes the data in real time to provide a basis for subsequent construction control.

[0042] For example, after installation, the intelligent compaction system will automatically adjust the operating parameters of the roller, such as vibration frequency, number of rolling passes, driving speed, etc., according to the actual collection of test section data, and target the soil type and construction environment conditions in each area to ensure that the compaction degree meets the expected standards.

[0043] In a possible implementation, the data acquisition system should also have a data cache function. During the data acquisition and upload process, if a temporary network failure occurs, the system can temporarily store the data in a local storage device and upload it again after the network is restored to ensure the integrity and security of the data.

[0044] In summary, in this embodiment, the key to step 1 is to reasonably select the test section, lay out the data collection points and install high-precision intelligent equipment to ensure the smooth progress of subsequent data collection work. These steps provide a reliable technical basis for subsequent data analysis and construction quality control.

[0045] Step 2: Data collection and transmission: collect the above construction data in real time and transmit the data to the cloud data platform through wireless network for storage and analysis;

[0046] In this embodiment, step 2 involves the study of the filling data model, the main purpose of which is to organize and analyze the collected data from different regions, and to construct a mathematical model of the filling compaction process based on these data, thereby providing a theoretical basis for subsequent compaction process optimization and construction quality monitoring.

[0047] In this process, the filling data collected in step 1, including data on compaction degree, vibration frequency, pressure applied by the roller, etc. in different areas, are first sorted and classified. Specifically, the data is divided into light area, medium area and heavy area, and several data collection points are set in each area to record information such as compaction degree at different time points, working status of the roller and physical properties of the soil on site.

[0048] As an option, data collection should cover all factors that may affect the compaction process, including soil type, ambient moisture, temperature, etc. These factors have a significant impact on the compaction effect of the soil, so their influence must be considered in the data model.

[0049] Specifically, data collection first involves real-time measurement, including soil compaction detection, equipment status monitoring, sensor data upload, etc. Taking vibration frequency as an example, during the operation of a road roller, the vibration frequency of the equipment directly affects the compaction effect of the soil. In mild areas, the vibration frequency is usually low, while in severe areas, the vibration frequency needs to be appropriately increased to ensure that the soil achieves the expected compaction effect. Therefore, when collecting data, special attention should be paid to recording the vibration frequency in different areas and the corresponding soil compaction.

[0050] It should be noted that in order to ensure the accuracy and representativeness of the data, the collected data is not only surface data, but is obtained through comprehensive monitoring at multiple levels and angles. For example, soil compaction can be calculated by checking the actual compaction of each layer, while the pressure and vibration data recorded by the sensor can be used to further analyze whether the compaction effect is uniform.

[0051] On the basis of data collation, a certain data processing method is used to construct a data model. The core idea of ​​the data model is to find out the relationship between different compaction states and various factors through statistical analysis of the collected data, and then establish a mathematical model. These mathematical models can be regression analysis, fitting curves, neural networks and other methods. Common processing methods include least squares method, linear regression method, support vector machine (SVM), etc.

[0052] Specifically, first, by statistically analyzing data from different regions, we can obtain the relationship between compaction and parameters such as the pressure applied by the roller and the vibration frequency. For example, in a light area, the compaction may be linearly related to the applied pressure, while in a heavy area, the compaction may be nonlinearly related to the applied pressure and the vibration frequency. In this case, regression analysis can help establish a specific mathematical model, making parameter adjustments during construction more precise.

[0053] As an option, the establishment of the data model can be further optimized through experimental verification. For example, by comparing the compaction effects of different experimental sections, the model can be modified to further improve the accuracy and applicability of the model. In some embodiments, machine learning methods, such as decision trees, random forests, neural networks and other algorithms, can more accurately predict the compaction effect of the soil and provide guidance for adjustments during the construction process.

[0054] In this application, the research on data model is not just a simple arrangement of data, but through multi-level and multi-dimensional analysis, it deeply explores the key factors that affect the compaction effect, and provides strong theoretical support for the subsequent construction process control. For example, through model calculation, the optimal compaction range of soil in each area under different vibration frequencies can be obtained, thereby helping construction personnel to adjust the construction plan in actual operation to ensure that the compaction effect meets the expected standards.

[0055] In one possible implementation, the data model should also have the function of real-time feedback. For example, through online data analysis, construction personnel can instantly understand the compaction status of each area and adjust the operating parameters of the construction equipment, such as vibration frequency, number of rolling passes, etc., according to the results predicted by the model, so as to optimize the construction process and improve the uniformity and accuracy of the compaction effect.

[0056] For example, when a univariate linear regression equation is used, a regression model can be established by statistically analyzing the relationship between the compaction degree (Y axis) of the collection point and the continuous compaction V-CV value (X axis). The accuracy of this model can be further verified by error analysis. In the actual construction process, based on the real-time calculation of the model, construction personnel can be guided to adjust the construction equipment parameters to achieve the best compaction effect.

[0057] In some cases, in order to further optimize the filling process, the established filling data model can also be integrated with the existing construction control system, and the construction parameters can be adjusted in real time through linkage with intelligent equipment and construction machinery. For example, when the system predicts that a certain section of the roadbed may have overpressure or underpressure, the system will issue an early warning and correct the problem in the construction process in real time by adjusting equipment parameters or operating methods.

[0058] It is understandable that the filling data model is not only a prediction tool for soil compaction, but also a comprehensive evaluation tool that covers various information such as soil type, construction equipment, environmental factors, etc. In some embodiments, the ultimate goal of the data model is to achieve full dynamic control to ensure that the compaction process of the railway subgrade can be efficient, accurate and uniform from beginning to end.

[0059] In summary, step 2 in this embodiment mainly includes the analysis of collected data, the construction of mathematical models, and the application of these models in the actual construction process. By establishing an effective filling data model, it can not only provide a scientific basis for the construction process, but also adjust the construction strategy in real time to improve the compaction effect and construction efficiency.

[0060] Step 3: Data analysis and modeling: Based on the collected data, a multivariate linear regression or machine learning method is used to establish a relationship model between roadbed compaction and construction parameters;

[0061] In this embodiment, step S3 mainly involves the study of real-time detection technology of the filling and rolling process, which aims to ensure that the quality of each construction stage meets the standards by continuously monitoring the compaction situation during the construction process. Specifically, the core of this step is to use intelligent sensors and real-time data acquisition systems to detect the rolling quality of each stage, and to provide real-time feedback on abnormal conditions during the compaction process, thereby achieving dynamic process control and avoiding the occurrence of pressure leakage and overpressure.

[0062] First, as an option, the detection of the rolling process depends on the installation and commissioning of continuous compaction equipment. The equipment includes but is not limited to pressure sensors, vibration sensors, temperature and humidity sensors, etc., which are used to collect key data in the construction process in real time. The pressure sensor is mainly used to monitor the pressure applied to the soil, the vibration sensor is used to measure the vibration amplitude and frequency of the roller, and the temperature and humidity sensor can be used to evaluate the impact of environmental conditions on the compaction effect. All sensors are connected to the cloud platform through a data transmission system to upload and process real-time monitoring data.

[0063] Specifically, during the construction process, the sensor will collect data from each area in real time according to the set cycle. For example, in the light area, the sensor can measure the applied pressure and vibration frequency every 5 minutes; in the medium area, as the rolling depth increases, the sensor sampling frequency can be appropriately increased to capture more detailed data changes. At the same time, the real-time detection system also needs to track the compaction changes in each area to ensure that the compaction of each area meets the design standards.

[0064] In this application, the deployment location of sensors is crucial. To ensure the representativeness of the data, sensors should be arranged reasonably to avoid being concentrated in one part, which would cause data distortion. Specifically, sensors should be installed in the front, middle and rear of the roller to fully monitor various parameters during the compaction process and ensure that the construction quality is not affected by local imbalance.

[0065] For example, during the compaction process, the data collected by the sensor will be fed back to the construction personnel's display terminal in real time. The display terminal presents the status of the compaction area in an intuitive way. For example, qualified areas are displayed in green and unqualified areas are displayed in red. By monitoring these data, construction personnel can promptly discover possible problems in the compaction process. For example, when the compaction degree of a certain area does not meet the requirements, the system will issue an early warning signal to prompt the construction personnel to make adjustments to avoid continuing unqualified rolling operations.

[0066] In one possible implementation, the detection of the rolling process does not rely solely on the data from a single sensor, but also requires data integration through multi-sensor fusion technology. For example, the combination of temperature and humidity sensors and vibration sensors can effectively evaluate the impact of changes in the construction environment on the compaction effect, thereby adjusting the operating parameters of the construction equipment. Especially in rainy seasons or when humidity is high, the compaction effect of the soil may be different, so it is necessary to monitor environmental changes in real time through temperature and humidity sensors and adjust the operating parameters of the equipment when necessary.

[0067] It is understandable that all sensors and monitoring equipment must maintain high precision and high stability during the construction process to ensure the accuracy of the data. To this end, the system should have the function of abnormal data elimination and fault diagnosis to ensure that the collected data is free of interference or errors. For example, when a sensor fails or the data is abnormal, the system should immediately alarm and switch to a backup sensor or automatically correct the data.

[0068] Specifically, data processing during the rolling process is not limited to data collection, but also requires real-time data processing through advanced data analysis algorithms. For example, the system can use fast Fourier transform (FFT) to analyze the vibration frequency to determine the degree of soil compaction. If the vibration frequency does not match the predetermined range, it may indicate that there is uneven compaction in a certain area. The system will infer this data and provide feedback to the construction personnel to make necessary adjustments.

[0069] As an option, the detection of the rolling process can also be combined with the status data of the construction machinery for linkage control. For example, information such as the engine status, driving speed and rolling depth of the roller can be integrated with the sensor data to provide a more comprehensive construction quality assessment. For example, when the system detects that the rolling depth of the roller is not enough or the driving speed is too fast, it will prompt the construction personnel to make adjustments to prevent fluctuations in rolling quality due to improper equipment parameters.

[0070] It should be pointed out that real-time monitoring of the filling and rolling process can not only ensure the construction quality, but also provide traceable data support for each link in the construction process. For example, during the construction process, the system will record the time, parameters and compaction data of each rolling for later analysis and quality traceability. In addition, data accumulation can also provide a reference basis for subsequent engineering optimization. Based on the analysis of historical data, construction personnel can more accurately predict and adjust construction parameters to improve the efficiency and quality of subsequent construction.

[0071] In summary, in this embodiment, step 3 uses intelligent sensors, real-time monitoring systems and data analysis technology to detect and control the entire filling and rolling process. This technical means can ensure that the compaction degree of each stage meets the design requirements, and provide real-time data support for construction personnel to help them adjust construction parameters in a timely manner, thereby ensuring construction quality and avoiding pressure leakage and overpressure.

[0072] Step 4: Real-time compaction control and optimization: According to the established compaction prediction model, the rolling parameters of the roller are adjusted in real time to ensure that the compaction of each layer of roadbed filler meets the design requirements;

[0073] In this embodiment, step 4 involves comprehensive evaluation of the compaction process through data analysis and result feedback technology, and real-time adjustment and optimization of problems in the construction process. Specifically, this step evaluates the compaction effect by real-time analysis of the collected compaction data, and feeds back the analysis results to the construction personnel so that the construction parameters can be adjusted in time to ensure that the compaction degree of the roadbed fill meets the design requirements.

[0074] In this embodiment, first, the compaction data collected in real time by the data acquisition system mentioned in step S2, including parameters such as vibration frequency, pressure, and humidity, are uploaded to the data analysis system. The data analysis system performs multi-dimensional analysis on these data to determine the degree of compaction and uniformity of the soil, as well as whether there is a pressure leakage or overpressure phenomenon. Specifically, the analysis system uses statistical methods and numerical modeling algorithms to process the data and identify problem areas in the compaction process.

[0075] As an option, the data analysis system can use common data processing methods such as regression analysis and cluster analysis to comprehensively evaluate each data point in combination with actual engineering needs. For example, the system can use regression analysis to obtain a correlation model between compaction degree and compaction equipment operating parameters such as pressure and vibration frequency. This model can be used to predict the optimal compaction parameters under different construction conditions, thereby providing guidance for subsequent construction.

[0076] Specifically, in one possible implementation, the system will compare the collected compaction data with the design standards and compare it with historical data to predict the compaction effect of the soil under current conditions. If the analysis results show that the compaction of a construction area does not meet the requirements, the system will trigger an alarm and feedback to the construction personnel, prompting the need to re-compact the area.

[0077] It should be noted that the data analysis system is not limited to providing feedback on the current compaction process, but can also optimize the construction plan based on historical construction data. For example, in some areas, the system can predict the compaction effect under certain soil or environmental conditions based on historical construction data, and then adjust the construction strategy in advance. In this way, the system can achieve dynamic self-optimization to adapt to different soil and environmental conditions, further improving construction efficiency and quality.

[0078] For example, when the analysis results show that a certain area has obvious uneven compaction or over-compaction, the system can display real-time feedback information through the control panel, such as "the compaction degree of area A is low, and the number of rolling passes needs to be increased" or "the compaction degree of area B is too high, and the rolling pressure needs to be adjusted." Based on this feedback information, construction personnel can respond quickly and adjust construction parameters to avoid project quality problems.

[0079] In addition, the data analysis system can also conduct longitudinal comparative analysis of the compaction effects at different stages of the entire construction process to determine whether there are systematic quality problems. For example, by comparing construction data under different filler types, different rolling methods, and different climatic conditions, it can analyze which factors have the greatest impact on compaction, thereby providing more scientific and reasonable parameter settings for subsequent construction.

[0080] It is understood that in step S4, in addition to analyzing the real-time compaction effect of the current construction area, this data can also be compared with the prediction model before construction. If it is found that the actual construction deviates greatly from the prediction model, the system will automatically analyze the cause and give adjustment suggestions. This intelligent feedback mechanism based on the combination of historical data and real-time data helps to maximize the efficiency and quality of the compaction process.

[0081] In some embodiments, the data analysis system can also cooperate with artificial intelligence technology for self-learning. Specifically, the system can continuously update the model based on the operation history and feedback results of the construction personnel, thereby improving the system's adaptability to different soil types, environments and equipment conditions. Over time, the system can gradually optimize the construction plan, reduce manual intervention, and improve the degree of automation and accuracy of construction.

[0082] In this application, the compaction process data analysis and result feedback are not limited to immediate adjustments at the construction site, but can also provide data support for the later evaluation and quality traceability of the project. By saving all data and feedback information during the analysis process, the construction unit can conduct data retrospective analysis after the completion of the project and make a final evaluation of the project quality, ensuring that the construction quality of each link can be traced and avoiding quality risks.

[0083] In summary, in this embodiment, step 4 ensures real-time monitoring and adjustment of the compaction process by multi-dimensional analysis of real-time data, combined with historical construction data and real-time feedback mechanism. This step not only helps to improve construction quality and avoid quality problems such as pressure leakage and overpressure, but also provides data support for subsequent construction, helping construction units optimize construction plans and improve construction efficiency.

[0084] Step 5: Construction quality monitoring and feedback: real-time detection and feedback of the compaction degree of each layer, generation of construction quality reports, and alarm prompts and adjustments for unqualified areas;

[0085] In this embodiment, step 5 mainly involves quality verification of the compaction effect during the construction process and generating a corresponding construction quality report. The core of this step is to comprehensively evaluate the data collected in the previous steps and the analysis results to ensure that the construction quality meets the design requirements, and provide technical basis and decision-making support for the construction unit, quality supervision department and other relevant parties in the form of a report.

[0086] Specifically, in this embodiment, first, the compaction data collected in real time during the construction process, including compaction degree, pressure, vibration frequency, etc., will enter the quality verification stage after analysis and processing in step S4. The key task of this stage is to compare the analysis results with the predetermined quality standards to confirm whether each construction area meets the designed compaction standards.

[0087] As an option, the quality verification system will check the compaction of each construction section, compare the design requirements with the actual data, and determine whether there is insufficient compaction or overcompaction. For example, when the compaction of a section of roadbed does not meet the design requirements, the system will mark the section as "not up to standard" and prompt the construction personnel to take remedial measures.

[0088] In specific implementations, the quality verification process can be combined with different filler types, soil qualities, and construction conditions for segmented acceptance. In some embodiments, the system can classify and verify different filler groups, such as group A and group B fillers, to ensure that each type of filler can be constructed according to its specific compaction requirements. Especially under complex geological conditions, it may be necessary to verify different layers and types of soil separately to ensure that the compaction of each layer during construction meets the design specifications.

[0089] It should be noted that in this embodiment, the quality verification process is not only an evaluation of a single parameter, but also includes a comprehensive analysis of multiple parameters of the entire compaction process. For example, a comprehensive analysis of multiple parameters such as compaction degree, compaction uniformity, rolling times, vibration frequency, etc. helps to more comprehensively evaluate the construction quality and discover potential quality problems. Through this multi-dimensional quality verification, deficiencies in the construction process can be more accurately identified to avoid problems such as underpressure and overpressure.

[0090] For example, the quality verification system not only verifies through static compaction data, but also dynamically monitors the compaction effect during the construction process. For example, the system can display the compaction distribution of the construction area in real time, and identify the quality status of different areas through color coding. For areas that meet the standards, the system will display them in green; for areas that do not meet the standards, they will display them in red or yellow. This intuitive feedback helps construction personnel to identify problems in a timely manner, adjust construction plans, and improve construction quality.

[0091] In addition, during the quality verification process, the system can also generate a construction quality report and record it automatically. The report will include the distribution of compaction, construction data in different areas, quality verification results, etc., and provide detailed construction data support. The generation of the report not only helps the construction unit to evaluate the current construction quality, but also provides a basis for subsequent quality acceptance. The report may also include specific problems and improvement measures for each construction section, helping the construction unit to trace and analyze quality in the later stages of the project.

[0092] It is understandable that through this automated report generation method, construction units can significantly reduce manual intervention and improve work efficiency. Construction quality reports can also share data with other project management systems, such as construction progress management systems, equipment management systems, etc., to provide more comprehensive data support for the overall management of the project.

[0093] In some embodiments, the quality report is not limited to the analysis of compaction, but can also record in detail the equipment operation status, personnel operation records, environmental factors such as weather, etc. during the construction process, and form a comprehensive report. Through these comprehensive data, the construction unit can better understand the various factors that may affect the quality during the construction process and make improvements in the future construction process.

[0094] It should be noted that the generated construction quality report not only has instant reference value on site, but also helps project managers to supervise the whole process. By continuously recording, archiving and tracing the data of the construction process, project managers can continuously evaluate the construction quality and discover potential problems in time, thereby avoiding risks that affect the progress and quality of the project.

[0095] In summary, step 5 provides the construction unit with scientific and accurate quality assessment results by verifying the quality of compaction data and construction process. Through real-time quality feedback, automatically generated quality reports and multi-dimensional data analysis, it ensures that the construction quality meets the design requirements and provides a reliable basis for quality traceability and subsequent optimization. This step not only improves the transparency and controllability of the construction process, but also improves the overall quality of the project.

[0096] Step 6: Result analysis and optimization: conduct post-analysis on the data during the construction process, adjust the construction parameters and optimize the model according to the construction situation to improve the accuracy and efficiency of subsequent construction.

[0097] In this embodiment, step 6 involves real-time feedback and adjustment of the compaction quality to ensure continuous optimization and monitoring of the compaction process.

[0098] Specifically, during the compaction process, the intelligent continuous compaction system collects compaction data from each measuring point in real time through sensors, mainly including key parameters such as compaction degree, compaction times, and compaction uniformity. These data are transmitted to the central control system, and the compaction quality distribution diagram is displayed in real time through data analysis, which can intuitively reflect the current quality of the compaction. The graphical interface uses color marking, with qualified areas displayed in green and unqualified areas displayed in red or other warning colors, so that operators can make timely adjustments.

[0099] In this application, during this process, the central control system not only provides real-time feedback data, but also automatically adjusts the working parameters of the compactor according to preset standards. For example, when it is found that the compaction degree of a certain compaction area is insufficient, the system will automatically adjust the vibration frequency, travel speed or rolling times of the roller to ensure that the compaction degree meets the standard and avoid the occurrence of under-compaction or over-compaction. As an option, the system can also automatically select the most suitable rolling parameters according to geological conditions and different soil types to adapt to different construction environments and soil requirements.

[0100] In one possible implementation, the control system also includes a data storage module that can store detailed compaction data for each construction area and generate a construction log to provide a data basis for quality inspection and management in the later stage of construction. For example, the relevant data of each compaction process will be recorded and archived in the form of a report for later inspection and analysis. With these data, the construction unit can control the construction process more accurately and improve the overall construction quality.

[0101] In this application, the system is not only a monitoring tool for existing construction, but also plays a role in optimizing construction methods. It can adjust construction strategies based on real-time data to achieve continuous improvement. For example, during the rolling process, if the system detects that the soil in certain areas is loose, the intelligent device can increase the number of rolling times or change the rolling method to ensure the uniformity of each layer and achieve the required compaction degree.

[0102] In summary, the key to step 6 is to ensure the real-time optimization and precise execution of the compaction process through the feedback and adjustment functions of the intelligent control system, thereby greatly improving the construction quality, reducing manual intervention, improving efficiency, reducing human errors, and ensuring the long-term stability and reliability of roadbed construction.

[0103] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent monitoring of continuous compaction of railway roadbed, characterized in that: The following steps are involved: Step 1: Test section setting and data collection preparation: By demarcating the test section area and installing intelligent continuous compaction equipment on the roller, multiple construction parameters such as soil compaction, number of rolling passes, roller pressure, vibration frequency, and ambient temperature and humidity are obtained; Step 2: Data collection and transmission: collect the above construction parameters in real time and transmit the data to the cloud data platform through wireless network for storage and analysis; Step 3: Data analysis and modeling: Based on the collected parameters, a multivariate linear regression or machine learning method is used to establish a relationship model between roadbed compaction and construction parameters; Step 4: Real-time compaction control and optimization: According to the established compaction prediction model, the rolling parameters of the roller are adjusted in real time to ensure that the compaction of each layer of roadbed filler meets the design requirements; Step 5: Construction quality monitoring and feedback: real-time detection and feedback of the compaction degree of each layer, generation of construction quality reports, and alarm prompts and adjustments for unqualified areas; Step 6: Result analysis and optimization: conduct post-analysis of the data during the construction process, adjust the construction parameters and optimize the model according to the construction situation.

2. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The intelligent continuous compaction equipment includes a vibration sensor, a temperature and humidity sensor, a pressure sensor and a GPS positioning system, and the sensors are used to monitor multiple environmental and mechanical parameters during the construction process.

3. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The data transmission is carried out via wireless network or Bluetooth, and the data is uploaded to the cloud data platform in real time for storage, processing and remote viewing.

4. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The data analysis step uses machine learning models, including support vector machines, random forests or deep learning algorithms, to improve the accuracy and robustness of compaction predictions.

5. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The real-time feedback during the construction process includes displaying the construction progress and compaction distribution through a visual graphical interface, and marking qualified and unqualified areas with colors.

6. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The real-time control and optimization step automatically adjusts the working parameters of the roller, including vibration frequency, number of rolling passes and roller pressure, through an intelligent system to achieve the best compaction effect.

7. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The construction quality monitoring is carried out by combining regular automatic detection and manual inspection to ensure that the compaction degree of each layer of roadbed filler meets the design standard.

8. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The construction quality feedback mechanism includes the generation of construction quality reports and early warning reminders for unqualified areas to ensure immediate adjustments during the construction process.

9. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 1, characterized in that: The adjustment of the construction parameters is remotely controlled through a cloud platform, realizing information sharing and data interaction between the construction site and background monitoring personnel.

10. The method for intelligent monitoring of continuous compaction of railway roadbed according to claim 6, characterized in that: The intelligent system can continuously optimize construction parameters and prediction models based on historical construction data, and gradually improve construction accuracy.

Images