Fair-faced concrete pouring quality monitoring system based on unmanned construction

Abstract

The invention discloses a bare concrete pouring quality monitoring system based on unmanned construction, and the system achieves the no-dead-corner data collection of a construction area, and guarantees the full-coverage monitoring of key quality parameters. Stable data transmission in a complex environment is maintained through dynamic routing optimization; the data interruption time is reduced by means of an automatic fault switching mechanism; finally, a complete closed loop from data acquisition to intelligent analysis is formed, real-time and reliable monitoring guarantee is provided for the casting quality of the bare concrete, the data transmission delay and packet loss rate are reduced through dynamic path optimization, and meanwhile, continuous transmission of monitoring data can still be maintained by utilizing a standby path mechanism when a node fails, so that the monitoring efficiency is improved. And a stable and reliable data basis is provided for subsequent quality analysis.

Description

Technical Field

[0001] This application relates to the field of civil engineering technology, and in particular to a quality monitoring system for fair-faced concrete pouring based on unmanned construction. Background Technology

[0002] Fair-faced concrete pouring is a crucial construction step in building engineering, widely used in infrastructure projects such as high-rise buildings, bridges, and roads. Ensuring the quality of concrete pouring directly impacts the stability and safety of the structure. Therefore, concrete quality control and real-time monitoring of the construction process have become essential requirements in the construction industry. With the continuous development of automation technology, more and more unmanned construction equipment is being applied to construction sites, especially in the concrete pouring process. The use of unmanned construction equipment and intelligent monitoring systems significantly improves construction efficiency and precision.

[0003] However, current traditional methods for monitoring the quality of fair-faced concrete pouring largely rely on manual observation and conventional testing methods. This approach is not only inefficient but also susceptible to human error, making it difficult to achieve comprehensive, real-time monitoring of the pouring process. Existing monitoring systems typically employ single quality inspection methods, lacking effective data integration and intelligent analysis, resulting in poor accuracy and real-time performance of monitoring results. Furthermore, the complex environment of construction sites makes signal transmission vulnerable to interference from various external factors, and system recovery in the event of equipment failure usually depends on manual intervention, leading to low recovery efficiency. Summary of the Invention

[0004] The main objective of this application is to provide a quality monitoring system for unmanned construction of fair-faced concrete pouring, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, this application provides the following technical solution: A quality monitoring system for fair-faced concrete pouring based on unmanned construction is characterized by comprising a data acquisition module, a self-organizing network routing module, a data fusion and compensation module, a fault repair module, a data storage and analysis module, and a report generation module. The data acquisition module deploys multiple sensors and image acquisition nodes at the construction site to cover and acquire multi-source data from different locations, heights and areas within the construction scope, and is equipped with signal enhancement equipment to enhance the signal of the acquired data. The self-organizing network routing module enables each sensor node to automatically select the optimal transmission path based on the actual communication environment by setting up wireless self-organizing network technology. The data fusion compensation module combines multi-source data collected by sensors and processes it using intelligent data fusion algorithms to integrate various types of environmental data. The fault repair module monitors the working status of each sensor and communication network in real time and automatically activates the repair mechanism when signal loss or equipment failure occurs. The signal recognition module identifies abnormal construction areas by analyzing signal images; The data storage and analysis module stores the collected and analyzed data. The report generation module is used to feed back the collected and analyzed results to the visualization terminal and generate a visualization report.

[0006] Preferably, the data acquisition module includes a data acquisition unit and a signal enhancement unit; The data acquisition unit is responsible for deploying multiple sensors and image acquisition nodes at the construction site. The sensors provide comprehensive coverage of different locations, heights, and areas at the construction site. The image acquisition nodes are used to monitor the visual data of the construction site in real time to assist the sensor data in quality assessment. All acquired data is transmitted to the back-end data processing system through both wireless and wired communication methods. The signal enhancement unit is responsible for improving the signal strength and transmission stability of the data transmitted by the sensor and image acquisition node.

[0007] Preferably, the self-organizing network routing module includes a network topology management unit and a routing optimization unit; The network topology management unit automatically constructs the network topology based on changes in the construction site environment and the real-time status of sensor nodes, and dynamically adjusts it according to the location of sensor nodes, signal quality, and network load. The routing optimization unit evaluates the quality of each communication path and automatically selects the path with the strongest signal, lowest latency, and balanced load for data transmission. If a node fails or loses signal, it automatically selects an alternative path.

[0008] Preferably, the data fusion compensation module includes a preprocessing unit and a compensation unit; The preprocessing unit is responsible for preprocessing multiple raw data, including data cleaning, noise reduction and standardization, and synchronizing all preprocessed data in time. The compensation unit, through the application of intelligent data fusion algorithms, fuses data from different sensors to generate a comprehensive environmental data model.

[0009] Preferably, the fault repair module includes a fault monitoring unit and a switching unit; The fault monitoring unit monitors the working status of each sensor and communication network in real time, and detects whether there are abnormalities such as signal loss, delay or equipment failure during signal transmission. When the switching unit detects a device malfunction, it switches to a backup sensor node or backup communication path to ensure continuous system operation.

[0010] Preferably, the signal recognition module includes a signal pattern analysis unit and a tagging unit; The signal pattern analysis unit performs in-depth analysis on the preprocessed data, extracts the patterns and features representing the construction status in the image, and extracts key feature information through algorithms; The labeling unit applies machine learning and deep learning algorithms to extract key feature information for data analysis and identify abnormal areas that may occur during construction.

[0011] Preferably, the data storage and analysis module includes a management unit and a processing unit; The management unit stores the collected and analyzed data, and performs data backup and data lifecycle management; The processing unit analyzes and processes the stored data, using big data analytics and machine learning algorithms to determine the value of the saved data.

[0012] Preferably, the report generation module includes an extraction unit and a visualization unit; The extraction unit is responsible for extracting relevant collected data and analysis results from the data storage and analysis module, and then processing and formatting them uniformly. The visualization unit presents the extracted and organized data in the form of charts, graphs, and text, generating a visualization report.

[0013] Compared with the prior art, the beneficial effects of the present invention are: 1. This application achieves data collection without blind spots in the construction area, ensuring full coverage monitoring of key quality parameters; it maintains stable data transmission in complex environments through dynamic routing optimization; it reduces data interruption time with the help of an automatic fault switching mechanism; and finally forms a complete closed loop from data collection to intelligent analysis, providing real-time and reliable monitoring and guarantee for the quality of fair-faced concrete pouring.

[0014] 2. This application achieves stable acquisition and efficient transmission of multi-source heterogeneous data at the construction site, solving the data loss problem caused by signal interference in traditional monitoring systems. For example, it can still maintain the complete upload of sensor data in the electromagnetic interference environment generated by tower crane operation. At the same time, the reliability of quality assessment is improved through cross-validation of visual data and sensor data.

[0015] 3. This application effectively solves the problem of network topology instability caused by equipment movement and electromagnetic interference at the construction site. It reduces data transmission latency and packet loss rate through dynamic path optimization, and at the same time uses a backup path mechanism to ensure that the continuous transmission of monitoring data can still be maintained when a node fails, providing a stable and reliable data foundation for subsequent quality analysis. Attached Figure Description

[0016] Figure 1 This is the system flowchart for this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," and "third" in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Example 1: Please refer to Figure 1 A quality monitoring system for fair-faced concrete pouring based on unmanned construction is characterized by comprising a data acquisition module, a self-organizing network routing module, a data fusion and compensation module, a fault repair module, a signal recognition module, a data storage and analysis module, and a report generation module. The data acquisition module deploys multiple sensors and image acquisition nodes at the construction site to cover and acquire multi-source data from different locations, heights and areas within the construction scope, and is equipped with signal enhancement equipment to enhance the signal of the acquired data. The self-organizing network routing module enables each sensor node to automatically select the optimal transmission path based on the actual communication environment by setting up wireless self-organizing network technology. The data fusion compensation module combines multi-source data collected by sensors and processes it using intelligent data fusion algorithms to integrate various types of environmental data. The fault repair module monitors the working status of each sensor and communication network in real time and automatically activates the repair mechanism when signal loss or equipment failure occurs. The signal recognition module identifies abnormal construction areas by analyzing signal images; The data storage and analysis module stores the collected and analyzed data. The report generation module is used to feed back the collected and analyzed results to the visualization terminal and generate a visualization report.

[0021] In this embodiment: In the prior art, the quality monitoring of fair-faced concrete pouring mainly relies on manual observation and traditional detection methods, which suffers from low efficiency and susceptibility to human interference. Existing systems mostly use single detection methods, lack the ability to integrate multi-source data, and are unable to comprehensively reflect the construction status. The construction site environment is complex, signal transmission is easily interfered with, and equipment failures rely on manual recovery, resulting in insufficient real-time monitoring and reliability. In large bridge construction scenarios, due to the wide construction area and dense equipment, traditional monitoring systems struggle to achieve synchronous data acquisition across multiple areas, signal transmission paths are easily affected by obstructions, and backup solutions cannot be quickly switched when equipment fails, leading to missing monitoring data during critical construction stages.

[0022] To address the aforementioned issues, the first step is to resolve the problem of incomplete multi-source data acquisition, considering how to deploy multiple sensors in complex environments and enhance signal quality. To address the challenge of unstable signal transmission, a network architecture capable of automatically optimizing pathways needs to be designed. To handle data interruptions caused by equipment failures, a real-time monitoring and automatic switching mechanism must be established. By integrating multi-dimensional data acquisition, intelligent path selection, and fault self-healing functions, a monitoring system covering the entire data lifecycle can be formed, ultimately achieving precise quality control in unmanned construction scenarios.

[0023] Therefore, this application proposes a system comprising a data acquisition module, a self-organizing network routing module, a data fusion compensation module, a fault repair module, a signal identification module, a data storage and analysis module, and a report generation module. The data acquisition module deploys multiple sensors and image acquisition nodes at the construction site to cover different locations, heights, and areas within the construction scope and collect multi-source data, configuring signal enhancement equipment to amplify the acquired data. The self-organizing network routing module, through the implementation of wireless self-organizing network technology, enables each sensor node to automatically select the optimal transmission path based on the actual communication environment. The data fusion compensation module combines multi-source data collected by sensors and applies intelligent data fusion algorithms to integrate various environmental data. The fault repair module monitors the working status of each sensor and communication network in real time, automatically initiating a repair mechanism when signal loss or equipment failure occurs. The signal identification module analyzes signal images to mark abnormal construction areas. The data storage and analysis module stores the acquired and analyzed data. The report generation module feeds back the acquisition and analysis results to a visualization terminal and generates a visual report.

[0024] The data acquisition module refers to a data acquisition system that achieves full spatial coverage through multi-node deployment. Specifically, it can employ a combination of vibration sensors, temperature and humidity sensors, and high-definition cameras, using a hybrid wired and wireless network for data transmission. This module addresses the issue of insufficient coverage from a single sensor by complementing spatial dimensions and data types.

[0025] The self-organizing network routing module refers to a network architecture that dynamically optimizes data transmission paths. Specifically, it can adopt a mesh networking protocol based on link quality assessment, dynamically adjusting the transmission path by monitoring signal strength, latency, and node load in real time. This module avoids the impact of metal structures blocking wireless signals in the construction environment through adaptive path selection.

[0026] The data fusion and compensation module is a unit that integrates and processes heterogeneous data from multiple sources. Specifically, it can use a combination of time series alignment algorithms and Kalman filtering to perform spatiotemporal calibration and noise filtering on sensor data. This module improves the accuracy of multi-source data correlation analysis by eliminating spatiotemporal biases in the data.

[0027] The fault recovery module refers to the automatic recovery mechanism in case of equipment failure. Specifically, it can employ heartbeat packet monitoring and redundant node switching strategies. When a node is detected to be offline or data is abnormal, a backup node is automatically activated and the communication link is rebuilt. This module ensures the system's continuous operation capability in the event of equipment failure through redundancy design.

[0028] The system deploys sensor nodes three-dimensionally in the pouring area through a data acquisition module. For example, pressure sensors are installed at key locations such as formwork support points and rebar skeleton nodes, while temperature and humidity sensors are set up along the concrete flow path. Simultaneously, multi-angle cameras capture the pouring process. Signal enhancement equipment can be configured on tower cranes or mobile platforms, using adaptive power adjustment to improve signal quality in edge areas. The self-organizing network routing module automatically switches data transmission to relay drone nodes based on real-time environmental changes, such as when the concrete pump truck moves, causing local signal attenuation. The data fusion and compensation module aligns the timestamps of vibration data and image data, establishing a correlation model between pouring density and surface bubble distribution. The fault repair module automatically calls adjacent cameras and adjusts analysis algorithm parameters when a camera's image is interrupted due to cement slurry contamination. The data storage and analysis module establishes a full-cycle database for the construction process, and the report generation module highlights abnormal areas in red on the 3D construction drawing and associates them with corresponding sensor data change curves.

[0029] Traditional systems use fixed cabling to transmit data, which cannot adapt to dynamically changing construction environments. This solution, however, achieves dynamic topology adjustment through self-organizing network routing. Existing technologies rely on manual troubleshooting of equipment faults; this solution achieves minute-level fault recovery through heartbeat monitoring and node switching. Conventional monitoring systems only store raw data; this solution establishes a traceable analytical model through multi-source data fusion, significantly improving the accuracy of anomaly detection.

[0030] Through the above technical solutions, this application achieves data collection without blind spots in the construction area, ensuring full coverage monitoring of key quality parameters; maintains stable data transmission in complex environments through dynamic routing optimization; reduces data interruption time with the help of an automatic fault switching mechanism; and ultimately forms a complete closed loop from data collection to intelligent analysis, providing real-time and reliable monitoring and assurance for the quality of fair-faced concrete pouring.

[0031] Example 2: Please refer to Figure 1 The data acquisition module includes a data acquisition unit and a signal enhancement unit; The data acquisition unit is responsible for deploying multiple sensors and image acquisition nodes at the construction site. The sensors provide comprehensive coverage of different locations, heights, and areas at the construction site. The image acquisition nodes are used to monitor the visual data of the construction site in real time to assist the sensor data in quality assessment. All acquired data is transmitted to the back-end data processing system through both wireless and wired communication methods. The signal enhancement unit is responsible for improving the signal strength and transmission stability of the data transmitted by the sensor and image acquisition node.

[0032] In this embodiment: This application further proposes a data acquisition module including a data acquisition unit and a signal enhancement unit; the data acquisition unit is responsible for deploying multiple sensors and image acquisition nodes at the construction site. The sensors provide comprehensive coverage of different locations, heights, and areas of the construction site. The image acquisition nodes are used to monitor the visual data of the construction site in real time to assist in the quality assessment of the sensor data. All acquired data is transmitted to the back-end data processing system through both wireless and wired communication methods; the signal enhancement unit is responsible for improving the signal strength and transmission stability of the data transmitted by the sensors and image acquisition nodes.

[0033] The data acquisition unit refers to the structure of a data collection network built through multi-dimensional sensing devices. Specifically, it can be implemented by deploying a combination of vibration sensors, temperature sensors, and high-definition cameras. Sensors are installed at different elevations of the template support system according to a grid distribution rule, while image acquisition nodes are arranged at the top and lateral observation points of the construction area, forming a three-dimensional data acquisition coverage. The signal enhancement unit refers to auxiliary devices used to optimize data transmission quality. Specifically, it can be implemented by using wireless signal repeaters and fiber optic signal amplifiers working together. Distributed signal enhancement nodes are deployed on the construction site to compensate for the power of the wireless transmission link and adjust the impedance of the wired transmission channel.

[0034] The data acquisition unit sets up a sensor array in the concrete pouring area. For example, strain sensors are installed at formwork joints to monitor deformation, temperature sensors are placed at key nodes in the concrete flow path, and a panoramic camera is mounted above the hoisting equipment's trajectory. All sensor nodes transmit data in parallel via a dual-channel system of wireless networking and fiber optic transmission. For instance, vibration data is transmitted via the LoRa wireless protocol, and image data is transmitted via gigabit fiber optics. The signal enhancement unit adds relay nodes in areas where wireless signals attenuate. For example, directional antennas are deployed in areas with dense steel structures to enhance signal penetration, and photoelectric converters are inserted into long-distance wired transmission links to improve signal integrity.

[0035] Traditional concrete pouring monitoring systems typically employ only a single communication method. For example, relying solely on wireless transmission makes the signal susceptible to interference from construction machinery, while using only wired cabling limits the flexibility of sensor deployment. This solution utilizes a dual-communication redundancy transmission mechanism, which retains the flexibility of wireless deployment while ensuring high-bandwidth transmission of critical data through a wired channel. Furthermore, dynamic signal enhancement technology eliminates transmission blind spots in complex environments.

[0036] Through the above technical solutions, this application has achieved stable acquisition and efficient transmission of multi-source heterogeneous data at the construction site, and solved the problem of data loss caused by signal interference in traditional monitoring systems. For example, it can still maintain the complete upload of sensor data in the electromagnetic interference environment generated by tower crane operation. At the same time, the reliability of quality assessment is improved by cross-validation of visual data and sensor data.

[0037] Example 3: Please refer to Figure 1 The self-organizing network routing module includes a network topology management unit and a routing optimization unit; The network topology management unit automatically constructs the network topology based on changes in the construction site environment and the real-time status of sensor nodes, and dynamically adjusts it according to the location of sensor nodes, signal quality, and network load. The routing optimization unit evaluates the quality of each communication path and automatically selects the path with the strongest signal, lowest latency, and balanced load for data transmission. If a node fails or loses signal, it automatically selects an alternative path.

[0038] In this embodiment: This application further proposes an ad hoc network routing module including a network topology management unit and a routing optimization unit; the network topology management unit automatically constructs the network topology according to the environmental changes at the construction site and the real-time status of the sensor nodes, and dynamically adjusts it according to the location of the sensor nodes, signal quality and network load; the routing optimization unit evaluates the quality of each communication path and automatically selects the path with the strongest signal, the least delay and the balanced load for data transmission. If a node fails or loses signal, an alternative path is automatically selected.

[0039] The network topology management unit is a component that dynamically adjusts the network structure based on the location of sensor nodes, signal quality, and network load. It can be implemented using distributed network protocols or adaptive topology algorithms. Its function is to adapt to the complex environmental changes at the construction site in real time, ensuring network coverage integrity and communication stability. The routing optimization unit is a component that selects the optimal transmission path based on path quality assessment results. It can be implemented using link quality assessment models or dynamic routing protocols. Its function is to reduce data transmission latency and avoid network congestion. Backup paths refer to pre-configured alternative communication links, which can be implemented using redundant nodes or backup channels. Their function is to maintain data transmission continuity when the primary path fails.

[0040] The network topology management unit dynamically adjusts the connectivity between nodes by continuously monitoring the location offset, signal attenuation, and network load fluctuations of sensor nodes. For example, when the movement of large construction equipment causes signal blockage, the communication links between nodes are reallocated to maintain network connectivity. The routing optimization unit uses a weighted evaluation algorithm to select the transmission path with the best overall performance based on real-time collected path signal strength, transmission delay, and node load data. For example, it prioritizes paths with signal strength above a threshold and load rate below a set value. When a node is detected to be offline or a link is interrupted, a pre-established backup path is immediately activated, such as through multi-hop relay between adjacent nodes to complete data transmission.

[0041] Traditional wireless sensor networks employ fixed topologies and static routing strategies, which cannot adapt to the dynamically changing communication environment of construction sites. This makes data transmission susceptible to factors such as equipment movement and electromagnetic interference. This solution significantly improves network adaptability in complex scenarios through dynamic topology adjustment and intelligent path selection, while also preventing data interruptions caused by single points of failure through a backup path mechanism.

[0042] Through the above technical solutions, this application effectively solves the problem of network topology instability caused by equipment movement and electromagnetic interference at the construction site. It reduces data transmission latency and packet loss rate through dynamic path optimization, and at the same time uses a backup path mechanism to ensure that the continuous transmission of monitoring data can still be maintained when a node fails, providing a stable and reliable data foundation for subsequent quality analysis.

[0043] Example 4: Please refer to Figure 1 The data fusion compensation module includes a preprocessing unit and a compensation unit; The preprocessing unit is responsible for preprocessing multiple raw data, including data cleaning, noise reduction and standardization, and synchronizing all preprocessed data in time. The compensation unit, through the application of intelligent data fusion algorithms, fuses data from different sensors to generate a comprehensive environmental data model.

[0044] In this embodiment: This application further proposes a data fusion compensation module including a preprocessing unit and a compensation unit; the preprocessing unit is responsible for preprocessing multiple raw data, including data cleaning, noise reduction and standardization, and synchronizing all preprocessed data in time; the compensation unit applies an intelligent data fusion algorithm to fuse data from different sensors to generate a comprehensive environmental data model.

[0045] Data cleaning refers to removing outliers and invalid data through rule-based filtering or algorithmic identification. This can be achieved using threshold judgment or outlier detection algorithms, eliminating erroneous data generated during sensor acquisition due to environmental interference or equipment errors. Noise reduction involves suppressing high-frequency interference or random fluctuations in the acquired signal. This can be achieved using wavelet transform or Kalman filtering algorithms, improving the signal-to-noise ratio. Standardization involves converting sensor data of different dimensions or magnitudes into a unified benchmark. This can be achieved using Z-score normalization or max-min scaling methods, eliminating scale differences between multi-source data. Time synchronization involves aligning the timestamps of data acquired from different sensors. This can be achieved using network time protocols or interpolation compensation methods, ensuring the temporal compatibility of multi-source data. Intelligent data fusion algorithms integrate heterogeneous multi-source data through mathematical models. This can be achieved using Kalman filtering, Bayesian inference, or deep neural network methods, establishing a data model reflecting the overall state of the construction environment.

[0046] The preprocessing unit first cleans the raw data from different sensors, for example, by automatically filtering outomas exceeding thresholds by setting reasonable ranges for temperature or vibration parameters. Then, digital filtering algorithms are used to eliminate electromagnetic interference noise in the signals, and data of different dimensions such as pressure and humidity are converted into standardized values. All preprocessed data are synchronized at the millisecond level through timestamp correction, ensuring precise correspondence between vibration monitoring and image acquisition on the timeline. The compensation unit inputs the preprocessed standardized data into a trained fusion model, for example, using convolutional neural networks to extract spatial correlation features from data from different sensors, ultimately outputting a comprehensive data model containing multi-dimensional information such as temperature, humidity, and vibration, providing a unified data benchmark for subsequent quality assessment.

[0047] The specific steps are as follows: Data cleaning: X = {x1, x2, x3, ..., xi}, where xi represents the i-th data point. A threshold of Y is set. For each data point xi, an outlier is considered if xi < Ymin or xi > Ymax. The formula is as follows:

[0048] in The data is cleaned; if any data point is an outlier, it is represented by null. Denoising: Let the original signal be x(t), and the denoised signal be... The mathematical expression is:

[0049] Where K(t) is the Kalman gain, x(t) is the predicted value at the previous time step, and x(t) is the measured value at the current time step. standardization:

[0050] Time synchronization:

[0051] Where Ts is the synchronized timestamp, t1 and t2 are the original timestamps, and xi(Ts) is the synchronized data; Intelligent data fusion:

[0052] Where wi is the weight of each sensor data. This indicates the contribution of each data source, which can be adjusted by the user. Comprehensive environmental model:

[0053] in, For each sensor data after fusion and compensation, Xmod represents the overall state of the entire construction environment; Traditional monitoring systems lack effective integration of multi-source data. Data from different sensors exhibits temporal misalignment and format differences, leading to biased analysis results. This solution eliminates data heterogeneity through standardized preprocessing, ensures data correlation through time synchronization mechanisms, and utilizes intelligent algorithms to achieve deep fusion of multi-dimensional data, thus solving the problems of data isolation and integration difficulties in traditional methods.

[0054] Through the above technical solution, this application effectively solves the problem of fusion error caused by large noise interference and inconsistent formats of multi-source data at the construction site, improves the integrity and consistency of environmental monitoring data, and provides a high-precision data foundation for concrete pouring quality assessment.

[0055] Example 5: Please refer to Figure 1 The fault repair module includes a fault monitoring unit and a switching unit; The fault monitoring unit monitors the working status of each sensor and communication network in real time, and detects whether there are abnormalities such as signal loss, delay or equipment failure during signal transmission. When the switching unit detects a device malfunction, it switches to a backup sensor node or backup communication path to ensure continuous system operation.

[0056] In this embodiment: This application further proposes a fault repair module including a fault monitoring unit and a switching unit; the fault monitoring unit monitors the working status of each sensor and communication network in real time, and detects whether there are abnormalities such as loss, delay or equipment failure during signal transmission; when the switching unit detects an equipment abnormality, it switches to a backup sensor node or backup communication path to ensure the continuous operation of the system.

[0057] The fault monitoring unit is a module that analyzes and detects the operating status of equipment through real-time data streams. Specifically, it can be implemented using a heartbeat detection mechanism or anomaly signal threshold judgment algorithm. For example, it can determine whether the equipment is online by periodically receiving sensor status messages. The switching unit is a control module used to switch redundant resources when an anomaly is detected. Specifically, it can be implemented using a dual-machine hot standby architecture or a dynamic routing switching protocol. For example, it can achieve rapid switching by pre-configuring a list of backup node addresses.

[0058] The fault monitoring unit continuously receives operational status data from sensors and the communication network, such as determining whether signal loss exists by parsing the integrity verification results of transmitted data packets. When a device response timeout or communication link quality falls below a preset threshold is detected, the path switching function of the switching unit is triggered. The switching unit, based on a preset backup resource mapping table, automatically assigns the data acquisition task of the faulty node to adjacent sensors, while simultaneously redirecting communication traffic to a backup wireless channel, thereby maintaining the continuity of data acquisition.

[0059] Traditional systems rely on manual troubleshooting and switching to backup equipment when equipment fails, requiring workflow interruptions for maintenance. This solution, through automated status monitoring and path switching mechanisms, can complete fault switching within milliseconds. For example, it can activate a backup node within 200 milliseconds after detecting a node's disconnection, avoiding the response delays caused by manual intervention.

[0060] Through the above technical solution, this application effectively solves the problem of monitoring interruption caused by equipment failure at the construction site, ensuring the continuous collection of concrete pouring quality data. When a vibration sensor fails, the system can automatically switch to a backup sensor in an adjacent area, ensuring uninterrupted monitoring of the pouring density and preventing potential pouring quality problems due to data loss.

[0061] Example 6: Please refer to Figure 1 The signal recognition module includes a signal pattern analysis unit and a tagging unit; The signal pattern analysis unit performs in-depth analysis on the preprocessed data, extracts the patterns and features representing the construction status in the image, and extracts key feature information through algorithms; The labeling unit applies machine learning and deep learning algorithms to extract key feature information for data analysis and identify abnormal areas that may occur during construction.

[0062] In this embodiment: This application further proposes a signal recognition module including a signal pattern analysis unit and a labeling unit; the signal pattern analysis unit performs in-depth analysis on the preprocessed data, extracts the patterns and features representing the construction state in the image, and extracts key feature information through algorithms; the labeling unit applies machine learning and deep learning algorithms to perform data analysis on the key feature information extracted by the algorithm, and identifies abnormal areas that may occur during the construction process.

[0063] The signal pattern analysis unit refers to a device that extracts features from image data using computer vision technology. Specifically, it can be implemented using edge detection algorithms or convolutional neural networks to identify the pouring status from visual information such as concrete surface texture and color changes. The labeling unit is a module that determines anomalies based on a data classification model. Specifically, it can be implemented using support vector machines or deep residual networks. By training data, it establishes a correlation model between pouring quality and image features, thereby automatically labeling defective areas such as bubbles and cracks.

[0064] The preprocessed image data is first input into the signal pattern analysis unit, which uses feature extraction algorithms to identify key indicators such as the uniformity and density of the concrete surface. For example, the OpenCV library is used for image grayscale processing, combined with the Canny operator to detect edge contour features. Subsequently, the labeling unit loads a pre-trained neural network model, inputs the extracted feature vectors into the classifier to calculate the anomaly probability, and automatically generates anomaly coordinate labels when local features deviate from the normal threshold and overlays them onto the original image.

[0065] Traditional methods rely on manual visual inspection of concrete surface conditions, which suffers from subjective judgment bias and inefficiency. Existing image recognition technologies mostly employ single threshold segmentation methods, which are difficult to adapt to the complex lighting conditions and differences in concrete materials at construction sites. This solution combines multi-layer feature extraction with machine learning to effectively distinguish normal pouring textures from real defect features, reducing the misjudgment rate caused by environmental interference.

[0066] Through the above technical solutions, this application achieves automated inspection of concrete surface quality, solving the problems of low efficiency and easy omission of minute defects by manual inspection. The abnormal area marking function can directly guide construction personnel to quickly locate repair positions and prevent the expansion of potential quality hazards. The classification model combined with deep learning can continuously optimize the recognition accuracy and adapt to the differences in material properties of different engineering projects.

[0067] Example 7: Please refer to Figure 1 The data storage and analysis module includes a management unit and a processing unit; The management unit stores the collected and analyzed data, and performs data backup and data lifecycle management; The processing unit analyzes and processes the stored data, using big data analytics and machine learning algorithms to determine the value of the saved data.

[0068] In this embodiment: This application further proposes a data storage and analysis module including a management unit and a processing unit; the management unit stores the collected and analyzed data, and performs data backup and data lifecycle management; the processing unit analyzes and processes the stored data, and analyzes the value of the stored data through big data analysis and machine learning algorithms.

[0069] The management unit refers to the component that structures and stores collected data and analysis results. Specifically, it can be implemented using a distributed storage system combined with database management software. By setting data classification rules and storage cycle strategies, automatic data archiving and backup can be achieved. The processing unit refers to the component that performs computational analysis on the stored data. Specifically, it can use Hadoop or Spark frameworks to build a big data processing platform, combined with TensorFlow or PyTorch machine learning frameworks to build analytical models, enabling in-depth mining of data value.

[0070] The management unit first associates and stores the raw data collected by the sensors with the analysis results output by the video recognition module, for example, establishing a mapping relationship between concrete temperature data and the image features of the corresponding area. Data backup is achieved by setting up redundant storage nodes, such as using RAID technology or cloud storage services. Data lifecycle management automatically deletes expired data through preset rules, such as retaining detailed data from the most recent 30 days and compressing and storing historical data. The processing unit extracts features from the stored structured data, such as identifying abnormal temperature patterns during concrete pouring through clustering algorithms, then predicting quality trends through regression models, and finally outputting analysis results that can support decision-making.

[0071] Traditional data storage methods typically rely on a single database to store raw data, lacking classification management and automated backup mechanisms, resulting in low data retrieval efficiency and the risk of data loss. Existing analytical methods largely depend on manual statistics or simple threshold judgments, failing to handle the complex relationships between multi-source heterogeneous data. This solution combines structured storage with intelligent analysis to achieve automated management of the entire data lifecycle and uses machine learning algorithms to uncover potential quality correlation patterns that are difficult to detect using traditional methods.

[0072] Through the above technical solution, this application solves the problems of low data utilization and limited analytical dimensions in traditional monitoring systems, and realizes systematic storage and intelligent analysis of construction process data. Data classification storage and backup mechanisms reduce the risk of data loss, and machine learning algorithms improve the accuracy of anomaly detection, thereby providing more comprehensive data support for quality assessment.

[0073] Example 8: Please refer to Figure 1 The report generation module includes an extraction unit and a visualization unit; The extraction unit is responsible for extracting relevant collected data and analysis results from the data storage and analysis module, and then processing and formatting them uniformly. The visualization unit presents the extracted and organized data in the form of charts, graphs, and text, generating a visualization report.

[0074] In this embodiment: This application further proposes a report generation module including an extraction unit and a visualization unit; the extraction unit is responsible for extracting relevant collected data and analysis results from the data storage and analysis module and performing unified processing and formatting; the visualization unit presents the extracted and organized data in the form of charts, graphs and text and generates a visualization report.

[0075] The extraction unit refers to the component that retrieves raw data and analysis results from the data storage and analysis module. This can be achieved using data transformation interfaces or standardized processing algorithms, ensuring the integrity and consistency of the input data through data cleaning and format conversion. The visualization unit refers to the component that transforms structured data into visual elements. This can be achieved using chart rendering engines or interactive visualization tools, transforming complex information into intuitive graphical representations through multi-dimensional data mapping techniques.

[0076] The extraction unit connects to the data storage and analysis module via a data interface, automatically capturing sensor data, image recognition results, and analysis conclusions generated during concrete pouring. It then uses data conversion rules to uniformly encode and format heterogeneous data, eliminating data redundancy and format conflicts. The processed standardized data is transmitted to the visualization unit, which transforms key indicators into dynamic charts such as line graphs and heat maps based on preset templates. Simultaneously, it combines these with text descriptions to generate a comprehensive report containing information such as construction quality trends and the location of abnormal areas.

[0077] Existing systems typically rely on manual data processing and report compilation, resulting in low efficiency and inconsistent formatting. This solution automates data extraction and standardized processing workflows, combined with intelligent visualization rendering technology, achieving end-to-end automation from data collection to report generation, significantly reducing manual intervention.

[0078] Through the above technical solution, this application can automatically integrate multi-source heterogeneous data and generate standardized reports, solving the technical problems of long data processing time and limited report formats in traditional methods. The generated reports intuitively present the construction quality status through a combination of charts and text, providing real-time decision support for on-site personnel, while avoiding data omissions or formatting errors that may be introduced by manual processing.

[0079] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0080] The specific embodiments of the invention have been described in detail above, but they are only examples, and this application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this application. Therefore, all equivalent changes, modifications, and improvements made without departing from the spirit and principles of this application should be covered within the scope of this application.

Claims

1. A quality monitoring system for unmanned construction of fair-faced concrete pouring, characterized in that: It includes a data acquisition module, an ad hoc network routing module, a data fusion and compensation module, a fault repair module, a signal identification module, a data storage and analysis module, and a report generation module; The data acquisition module deploys multiple sensors and image acquisition nodes at the construction site to cover and acquire multi-source data from different locations, heights and areas within the construction scope, and is equipped with signal enhancement equipment to enhance the signal of the acquired data. The self-organizing network routing module enables each sensor node to automatically select the optimal transmission path based on the actual communication environment by setting up wireless self-organizing network technology. The data fusion compensation module combines multi-source data collected by sensors and processes it using intelligent data fusion algorithms to integrate various types of environmental data. The fault repair module monitors the working status of each sensor and communication network in real time and automatically activates the repair mechanism when signal loss or equipment failure occurs. The signal recognition module identifies abnormal construction areas by analyzing signal images; The data storage and analysis module stores the collected and analyzed data. The report generation module is used to feed back the collected and analyzed results to the visualization terminal and generate a visualization report.

2. The quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 1, characterized in that, The data acquisition module includes a data acquisition unit and a signal enhancement unit; The data acquisition unit is responsible for deploying multiple sensors and image acquisition nodes at the construction site. The sensors provide comprehensive coverage of different locations, heights, and areas at the construction site. The image acquisition nodes are used to monitor the visual data of the construction site in real time to assist the sensor data in quality assessment. All acquired data is transmitted to the back-end data processing system through both wireless and wired communication methods. The signal enhancement unit is responsible for improving the signal strength and transmission stability of the data transmitted by the sensor and image acquisition node.

3. The quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 2, characterized in that, The self-organizing network routing module includes a network topology management unit and a routing optimization unit; The network topology management unit automatically constructs the network topology based on changes in the construction site environment and the real-time status of sensor nodes, and dynamically adjusts it according to the location of sensor nodes, signal quality, and network load. The routing optimization unit evaluates the quality of each communication path and automatically selects the path with the strongest signal, lowest latency, and balanced load for data transmission. If a node fails or loses signal, it automatically selects an alternative path.

4. The quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 3, characterized in that, The data fusion compensation module includes a preprocessing unit and a compensation unit; The preprocessing unit is responsible for preprocessing multiple raw data, including data cleaning, noise reduction and standardization, and synchronizing all preprocessed data in time. The compensation unit, through the application of intelligent data fusion algorithms, fuses data from different sensors to generate a comprehensive environmental data model.

5. A quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 4, characterized in that, The fault repair module includes a fault monitoring unit and a switching unit; The fault monitoring unit monitors the working status of each sensor and communication network in real time, and detects whether there are abnormalities such as signal loss, delay or equipment failure during signal transmission. When the switching unit detects a device malfunction, it switches to a backup sensor node or backup communication path to ensure continuous system operation.

6. The quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 5, characterized in that, The signal recognition module includes a signal pattern analysis unit and a tagging unit; The signal pattern analysis unit performs in-depth analysis on the preprocessed data, extracts the patterns and features representing the construction status in the image, and extracts key feature information through algorithms; The labeling unit applies machine learning and deep learning algorithms to extract key feature information for data analysis and identify abnormal areas that may occur during construction.

7. A quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 6, characterized in that, The data storage and analysis module includes a management unit and a processing unit; The management unit stores the collected and analyzed data, and performs data backup and data lifecycle management; The processing unit analyzes and processes the stored data, using big data analytics and machine learning algorithms to determine the value of the saved data.

8. A quality monitoring system for unmanned construction of fair-faced concrete pouring according to claim 7, characterized in that, The report generation module includes an extraction unit and a visualization unit; The extraction unit is responsible for extracting relevant collected data and analysis results from the data storage and analysis module, and then processing and formatting them uniformly. The visualization unit presents the extracted and organized data in the form of charts, graphs, and text, generating a visualization report.

Images