Cloud control engineering quality monitoring system

Abstract

The invention discloses a cloud control engineering quality monitoring system, which relates to the technical field of engineering management, and comprehensively captures dynamic information of a structure through collaborative operation of five core modules, a data acquisition link, deployment of various sensors and combination of timing and trigger sampling strategies. The transmission module constructs a hybrid network, ensures safe and stable transmission of data, establishes a multi-parameter comprehensive quality evaluation formula on data analysis modeling, trains influence coefficients through historical data, breaks through the limitation of traditional fixed weights, realizes dynamic adaptive evaluation, integrates multi-parameter cooperative influence, and enhances risk identification capability; the quality trend prediction formula is based on the current evaluation value and parameter change, deduces the quality state in real time, fuses multi-parameter analysis and data driving self-adaption, effectively captures the progressive evolution of the quality, avoids hysteresis evaluation, realizes prediction, early warning and intervention closed-loop management, accurately evaluates and predicts the project quality, and reduces the risk and cost.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering management, and in particular to a cloud-controlled engineering quality monitoring system. Background Art

[0002] As infrastructure construction continues to expand and project complexity continues to rise, project quality monitoring, a key component in ensuring project safety and performance, is becoming increasingly important. Traditional methods of project quality monitoring rely primarily on manual inspections, spot checks, and decentralized monitoring equipment, a model that presents numerous limitations.

[0003] From the perspective of monitoring timeliness, subtle changes in engineering structures during construction or operation cannot be detected in real time. Traditional monitoring equipment often operates independently, with data stored in separate devices and lacking effective interconnection. This makes data integration difficult and prevents the formation of a complete and systematic engineering quality information system.

[0004] With the rise of concepts like smart cities and digital twins, the engineering construction sector is placing higher demands on intelligent, integrated, and remote quality monitoring systems. Traditional monitoring models cannot meet the demands for real-time remote monitoring, multi-source data fusion and analysis, and big data-based quality prediction and early warning. To address these challenges, we propose a cloud-controlled engineering quality monitoring system. Summary of the Invention

[0005] The purpose of the present invention is to provide a cloud-controlled engineering quality monitoring system to solve the problem that the traditional monitoring mode proposed in the above background technology cannot meet the requirements of real-time remote monitoring and multi-source data fusion analysis.

[0006] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions:

[0007] The present invention provides a cloud-controlled engineering quality monitoring system, which includes the following modules:

[0008] S101, a data acquisition module, the data acquisition module is used to collect engineering quality related data in real time through various sensors distributed at different positions of the engineering structure, the data including but not limited to stress data, strain data, temperature data, humidity data and displacement data;

[0009] S102, a data transmission module, the data transmission module is used to securely transmit the data collected by the data collection module to a subsequent processing unit;

[0010] S103, a cloud computing processing module, wherein the cloud computing processing module is used to perform preliminary processing on the received data, including data cleaning, format conversion, and data storage;

[0011] S104, a data analysis and modeling module, which is used to perform in-depth analysis and modeling on the data preliminarily processed by the cloud computing processing module, and to establish a multi-parameter comprehensive quality assessment formula based on the data preliminarily processed by the cloud computing processing module:

[0012]

[0013] Among them, Q is the comprehensive evaluation value of engineering quality, n is the number of parameters involved in the evaluation, and w i is the weight coefficient of the i-th parameter, and x i is the actual measured value of the i-th parameter, f i (x i ) is the quality evaluation function of the i-th parameter, which is defined according to the characteristics of different parameters and engineering quality standards;

[0014] And the quality trend prediction formula:

[0015]

[0016] Among them, Q t+1 is the project quality prediction value at time t+1, Q t is the engineering quality assessment value at time t, m is the number of parameters that affect the engineering quality trend, k j is the influence coefficient of the jth parameter on the quality trend, Δx j,t is the change of the jth parameter at time t;

[0017] S105, monitoring and early warning module, the monitoring and early warning module is used to, based on the analysis and prediction results of the data analysis and modeling module, when the comprehensive evaluation value Q of the project quality is lower than the preset quality threshold, or the quality trend prediction value Q is lower than the preset quality threshold, t+1 When the project quality shows a trend of deterioration, an early warning message of the corresponding level will be issued.

[0018] Preferably, the sensors in the data acquisition module include fiber grating, piezoelectric, thermocouple and laser displacement sensors.

[0019] Preferably, the data transmission module adopts a combination of wireless and wired transmission technologies, and ensures the security and stability of data transmission through data encryption and error correction mechanisms.

[0020] Preferably, the cloud computing processing module adopts a distributed storage architecture to store data in multiple cloud server nodes, and uses the parallel computing capabilities of cloud computing to speed up data cleaning and format conversion. The processed data is used for subsequent analysis and modeling.

[0021] Preferably, the weight coefficient w in the data analysis modeling module iand influence coefficient k j It is trained by using historical engineering data and machine learning algorithms such as neural networks, decision trees or support vector machines. The algorithms can explore the potential relationships in the data.

[0022] Preferably, the quality assessment function f in the data analysis modeling module i (x i ) adopts piecewise function form, divides the intervals according to the engineering quality standards of different parameters, and each interval corresponds to a different evaluation value calculation method.

[0023] Preferably, the monitoring and early warning module divides the early warning levels into level one, level two and level three warnings according to the difference between the comprehensive evaluation value Q of the project quality and the preset quality threshold and the degree of deterioration of the quality trend prediction value. Different levels of early warnings are distinguished by different sound and light alarm frequencies, SMS contents and system pop-up window colors.

[0024] Preferably, a user interaction module is included, where users can view engineering quality-related data, assessment results and warning information, manage and adjust system parameter settings and sensor configurations, adjust weight coefficients and sensor sampling frequencies, and have data query and export functions.

[0025] Preferably, a data backup and recovery module is included to regularly back up the data in the cloud computing processing module and store it in an off-site data center. When data loss or damage occurs in the system, the data can be quickly restored and the restored data can be verified.

[0026] Preferably, the system has a self-diagnosis function, which monitors the operating status of each module in real time. By embedding monitoring programs and sensors in each module, it collects CPU usage and data transmission rate parameters. When a fault or abnormality is detected, it automatically records the fault information and issues a maintenance warning.

[0027] Compared with the existing technology, one or more of the above technical solutions have the following beneficial effects:

[0028] The cloud-controlled engineering quality monitoring system of the present invention achieves intelligent engineering quality monitoring through the coordinated operation of five core modules. In the data acquisition phase, multiple sensors are deployed at key locations, combining timed and triggered sampling strategies to comprehensively capture structural dynamic information. The transmission module constructs a hybrid network to ensure secure and stable data transmission. In data analysis and modeling, a multi-parameter comprehensive quality assessment formula is established. Influence coefficients are trained using historical data, breaking through the limitations of traditional fixed weights and enabling dynamic adaptive assessment. This reduces computational complexity while integrating the synergistic influence of multiple parameters and enhancing risk identification capabilities. The quality trend prediction formula deduces quality status in real time based on current assessment values ​​and parameter changes. This integrates multi-parameter coupling analysis and data-driven adaptation to effectively capture the gradual evolution of quality and avoid lagging assessments. A multi-level monitoring and early warning mechanism improves response efficiency. The user interaction module enables visualization and convenient operation, while data backup, recovery, and self-diagnosis functions ensure stable system operation. Through innovative algorithms, the system achieves closed-loop management of prediction, early warning, and intervention, accurately assessing and predicting engineering quality, reducing risks and costs, meeting diverse engineering monitoring needs, and providing strong support for engineering quality assurance. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0030] Figure 1 This is a system module structure diagram of a cloud-controlled engineering quality monitoring system proposed according to one embodiment of the present invention;

[0031] Figure 2 This is an overall architecture diagram of a cloud-controlled engineering quality monitoring system proposed according to one embodiment of the present invention;

[0032] Figure 3 This is a diagram of the data acquisition and transmission module architecture proposed according to one embodiment of the present invention;

[0033] Figure 4 This is a diagram of a cloud computing processing and distributed storage architecture proposed according to one embodiment of the present invention;

[0034] Figure 5 This is a diagram of the data analysis modeling and early warning mechanism architecture proposed according to one embodiment of the present invention;

[0035] Figure 6 It is a diagram of the user interaction and system maintenance module architecture proposed according to one embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings 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 in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0037] See also Figures 1-6 ,The present invention provides a cloud-controlled engineering quality monitoring system, which is mainly composed of five core modules: data acquisition, transmission, processing, analysis and early warning;

[0038] In the data acquisition module, sensor deployment and selection are crucial. A variety of sensor types are strategically deployed in key locations of engineering structures, such as bridge piers, building beams, and tunnel linings. Fiber Bragg grating (FBG) sensors utilize wavelength demodulation technology. These sensors can be attached to concrete surfaces or embedded within steel structures to accurately capture minute strains and temperature changes in engineering structures under various environments and loads, making them ideal for long-term, stable monitoring of projects. Piezoelectric sensors are installed in vibration-sensitive areas, such as machinery pile foundations and equipment bases. When these areas are subjected to impact loads or vibration, piezoelectric sensors respond rapidly, providing crucial data for analyzing the stress state of engineering structures under dynamic conditions. Thermocouple sensors are deployed in large-volume concrete pouring areas. They monitor real-time temperature changes due to hydration heat within the concrete, providing a basis for temperature control during construction. Laser displacement sensors are used to monitor displacement parameters such as bridge deflection and building settlement. A sensor bracket is fixed beneath the structure being measured, and a laser beam is emitted to a reflective target. The reflection time of the laser beam is measured to accurately calculate displacement. This non-contact measurement method is characterized by high precision and high stability, and can accurately reflect the displacement changes of engineering structures in real time.

[0039] Data collection utilizes a combination of timed and triggered sampling. Timed sampling collects sensor data at preset intervals, ensuring data continuity and integrity. Triggered sampling, on the other hand, is activated under specific conditions. When stress changes suddenly and exceeds a certain percentage, high-frequency sampling is automatically initiated to capture the dynamic changes of the engineering structure under special operating conditions and avoid missing important data.

[0040] The data transmission module establishes a hybrid transmission network. To adapt to diverse engineering environments and data transmission requirements, the module utilizes a combination of wireless and wired transmission technologies. Short-range wireless transmission is suitable for scenarios with densely deployed sensor nodes. The communication distance between nodes can be adjusted based on actual conditions, effectively achieving low-power aggregation of sensor data. LoRa technology is suitable for open areas in the wild, such as bridge crossings over rivers. It offers the advantages of long-distance transmission, low power consumption, and multi-channel concurrency. 4G / 5G communication modules are used for remote data backhaul. Ethernet, with its high transmission rate and excellent stability, meets the needs for rapid transmission of large amounts of data between devices within monitoring stations. Fiber optic communication is suitable for long-distance, high-reliability transmission scenarios, especially in environments with strong electromagnetic interference. Its advantages include high bandwidth, low attenuation, and strong anti-interference capabilities, ensuring data accuracy and stability over long distances.

[0041] To ensure data security and integrity during transmission, the transport layer uses advanced encryption algorithms to encrypt data payloads, preventing data theft or tampering during transmission. When errors are detected, they are promptly corrected, ensuring an extremely low bit error rate.

[0042] The cloud computing processing module uses a rules engine to screen and filter the collected data, removing outliers. It also uses a sliding average method to smooth the data and reduce the impact of noise on subsequent analysis. Because different sensor types may use different data formats, to facilitate subsequent unified analysis and processing, this multi-source sensor data needs to be converted into a unified storage format. This reduces data storage space usage and improves data read and write efficiency. Different storage methods are used based on the data type and characteristics.

[0043] The data analysis and modeling module establishes a multi-parameter comprehensive quality assessment formula based on the data initially processed by the cloud computing processing module:

[0044]

[0045] Among them, Q is the comprehensive evaluation value of engineering quality, n is the number of parameters involved in the evaluation, and w i is the weight coefficient of the i-th parameter, and x i is the actual measured value of the i-th parameter, f i (x i) is the quality assessment function of the i-th parameter, which is defined according to the characteristics of different parameters and engineering quality standards, quantifies the impact of the dynamic evolution of parameters on quality, conforms to the law of engineering structure performance degradation over time, can be adapted to different engineering types, materials and environments, solves the mechanical defects of traditional fixed-weight models, improves the versatility of the model, integrates the synergistic influence of multiple parameters, avoids the one-sidedness of single-indicator evaluation, enhances risk identification capabilities, realizes short-term quality trend prediction, can adjust construction or maintenance measures in advance, and provides core technical support for intelligent monitoring.

[0046] Simultaneously establish the quality trend prediction formula:

[0047]

[0048] Q t+1 is the project quality prediction value at time t+1, Q t is the engineering quality assessment value at time t, m is the number of parameters that affect the engineering quality trend, k j is the influence coefficient of the jth parameter on the quality trend, Δx j,t is the change of the jth parameter at time t; based on the current quality evaluation value Q t Dynamic change of parameters Δx j,t , real-time deduction of the quality status Q at the next moment t+1 , capturing the gradual evolution of engineering quality and avoiding lagging evaluation.

[0049] Integrate the real-time changes of multiple parameters such as stress, displacement, temperature, etc., and use the influence coefficient k j Quantify the contribution of each parameter to the quality trend, identify potential risks under the synergistic effect of multiple factors, and solve the one-sidedness of single parameter prediction.

[0050] Influence coefficient k j Trained with historical engineering data, it automatically adapts to different project types, material properties, and environmental conditions, eliminating the need for manually pre-set fixed weights. This improves the model's adaptability and prediction accuracy for complex working conditions. It supports high-frequency real-time computation, meeting the real-time requirements of engineering monitoring systems. By predicting quality trends, it triggers early warnings and guides intervention measures, providing proactive prevention and reducing project quality risks and maintenance costs. Through dynamic modeling, multi-parameter fusion, and data adaptation, it enables the foresight of project quality evolution.

[0051] At the same time, in order to timely discover project quality problems and take corresponding measures, the monitoring and early warning module adopts a multi-level early warning mechanism. According to the degree of deterioration of the comprehensive evaluation value Q of project quality and the quality trend prediction value, the warning levels are divided into level one warning (red), level two warning (orange) and level three warning (yellow).

[0052] Level 1 Alert (Red): When the project quality assessment value (Q) falls below a lower threshold, or the quality trend forecast indicates a rate of deterioration exceeding a higher threshold, a Level 1 alert is triggered. At this point, the on-site audible and visual alarms emit a high-intensity alarm and flash red lights, drawing the attention of on-site personnel. Simultaneously, the system sends a text message containing a link to real-time data to relevant personnel, such as the project manager and chief engineer, and a pop-up window with alert details appears on the system interface, ensuring timely notification of the alert. A Level 2 alert is triggered when the project quality assessment value (Q) falls within a certain range, or the quality trend forecast indicates a medium rate of deterioration. The audible and visual alarms' alarm frequency decreases, and a text message alert reads, "Attention, parameter abnormalities." A pop-up window with a flashing orange border reminds personnel to pay attention to the project quality issue. Level 3 Alert (Yellow): When the project quality assessment value (Q) falls within another range, or the quality trend forecast indicates a lower rate of deterioration, a Level 3 alert is triggered. In this case, only a steady yellow warning light appears on the system interface, and a warning log text message is sent to on-duty personnel, reminding them to continuously monitor project quality.

[0053] To improve early warning response efficiency and decision-making accuracy, the monitoring and early warning module is integrated with the BIM management platform. When an early warning is triggered, the system automatically locates the 3D model of the project component, highlights the location of the abnormal measurement point within the model, and simultaneously retrieves the monitoring curve and relevant construction logs for the area over the past 24 hours. This allows relevant personnel to intuitively understand the specific location and historical changes of project quality issues, providing strong support for rapid decision-making.

[0054] To facilitate system operation and management, the user interaction module intuitively displays project quality data in the form of real-time curves and heat maps. It also supports multi-project split-screen monitoring, allowing users to view the monitoring status of multiple projects simultaneously. The mobile app supports offline map loading, allowing users to view the geographic location of the project site even without an internet connection. By scanning a QR code, users can quickly view sensor locations and related information. Furthermore, users can use gestures to zoom in and out to view historical data, and system parameters can be remotely configured.

[0055] The data backup and recovery module is designed to ensure data security and reliability and prevent data loss from impacting the system. It uses a regular backup method and the system monitors data read status in real time. If it detects multiple consecutive data read failures, it is considered data loss and automatically triggers the recovery process to restore the system to normal operation as soon as possible.

[0056] To promptly detect faults and anomalies in each system module and ensure stable operation, a health monitoring program is embedded in each module. The data acquisition module checks sensor signal strength hourly. When the signal strength falls below a set threshold, the sensor is flagged as faulty, alerting maintenance personnel to promptly perform repairs. CPU utilization and memory usage are monitored in real time. When CPU utilization exceeds a certain threshold for a sustained period, or when memory usage exceeds 90%, an alert is triggered, prompting maintenance personnel to optimize or upgrade the system. Self-diagnosis results are transmitted to the maintenance terminal via a dedicated channel.

[0057] During the bridge construction phase, thermocouple sensors were deployed at the bridge's support beam precast yard to monitor temperature changes during concrete curing in real time. If the temperature difference within the concrete exceeds a certain threshold, a level 2 warning is triggered. The system promptly prompts construction personnel to adjust steam curing parameters, such as increasing or decreasing the steam supply, to control the temperature difference within the concrete and avoid quality issues such as cracks caused by excessive temperature stress. During the operational phase, fiber Bragg grating sensors were installed on the cables of the cable-stayed bridge, while laser displacement sensors monitored beam deflection. Using the quality trend prediction formulas within the data analysis and modeling module, cable stress changes and beam displacement are monitored and predicted in real time. If an abnormal stress increase in a cable is predicted in advance, the system triggers a corresponding level of warning, prompting personnel to promptly inspect and maintain the cable to prevent fracture due to excessive stress, thereby ensuring the structural safety of the bridge. By integrating multiple technologies and enabling collaborative operation between modules, the system achieves intelligent, automated, and highly reliable engineering quality monitoring, meeting the monitoring needs of diverse engineering scenarios and providing strong support for project quality assurance.

[0058] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A cloud-controlled engineering quality monitoring system, characterized in that: It includes the following modules: S101, a data acquisition module, wherein the data acquisition module is used to collect engineering quality-related data in real time through various sensors distributed at different locations of the engineering structure, the data including but not limited to stress data, strain data, temperature data, humidity data and displacement data; S102, a data transmission module, the data transmission module is used to securely transmit the data collected by the data collection module to a subsequent processing unit; S103, a cloud computing processing module, wherein the cloud computing processing module is used to perform preliminary processing on the received data, including data cleaning, format conversion, and data storage; S104, a data analysis and modeling module, which is used to perform in-depth analysis and modeling on the data preliminarily processed by the cloud computing processing module, and to establish a multi-parameter comprehensive quality assessment formula based on the processed data: Among them, Q is the comprehensive evaluation value of engineering quality, n is the number of parameters involved in the evaluation, and w i is the weight coefficient of the i-th parameter, and x i is the actual measured value of the i-th parameter, f i (x i ) is the quality evaluation function of the i-th parameter, which is defined according to the characteristics of different parameters and engineering quality standards; And the quality trend prediction formula: Among them, Q t+1 is the project quality prediction value at time t+1, Q t is the engineering quality assessment value at time t, m is the number of parameters that affect the engineering quality trend, k j is the influence coefficient of the jth parameter on the quality trend, Δx j,t is the change of the jth parameter at time t; S105, monitoring and early warning module, the monitoring and early warning module is used to, based on the analysis and prediction results of the data analysis and modeling module, when the comprehensive evaluation value Q of the project quality is lower than the preset quality threshold, or the quality trend prediction value Q is lower than the preset quality threshold, t+1 When the project quality shows a trend of deterioration, an early warning message of the corresponding level will be issued.

2. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The sensors in the data acquisition module include fiber grating, piezoelectric, thermocouple and laser displacement sensor.

3. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The data transmission module adopts a combination of wireless and wired transmission technologies, and ensures the security and stability of data transmission through data encryption and error correction mechanisms.

4. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The cloud computing processing module adopts a distributed storage architecture to store data on multiple cloud server nodes, and uses the parallel computing capabilities of cloud computing to speed up data cleaning and format conversion. The processed data is used for subsequent analysis and modeling.

5. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The weight coefficient w in the data analysis modeling module i and influence coefficient k j It is trained by using historical engineering data and machine learning algorithms such as neural networks, decision trees or support vector machines. The algorithms can explore the potential relationships in the data.

6. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The quality assessment function f in the data analysis modeling module i (x i ) adopts piecewise function form, divides the intervals according to the engineering quality standards of different parameters, and each interval corresponds to a different evaluation value calculation method.

7. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The monitoring and early warning module divides the early warning levels into level one, level two and level three warnings according to the difference between the comprehensive evaluation value Q of the project quality and the preset quality threshold and the degree of deterioration of the quality trend prediction value. Different levels of warnings are distinguished by different sound and light alarm frequencies, SMS content and system pop-up window colors.

8. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: It includes a user interaction module, where users can view engineering quality-related data, assessment results and early warning information, manage and adjust the system's parameter settings and sensor configurations, adjust weight coefficients and sensor sampling frequencies, and have data query and export functions.

9. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: It includes a data backup and recovery module, which regularly backs up the data in the cloud computing processing module and stores it in an off-site data center. When data loss or damage occurs in the system, it can quickly restore the data and verify the restored data.

10. The cloud-controlled engineering quality monitoring system according to claim 1, characterized in that: The system has a self-diagnosis function and monitors the operating status of each module in real time. By embedding monitoring programs and sensors in each module, it collects CPU usage and data transmission rate parameters. When a fault or abnormality is detected, it automatically records the fault information and issues a maintenance warning.

Images