A pouring environment monitoring system and method

Abstract

This invention discloses a pouring environment monitoring system and method, relating to the field of pouring monitoring. The pouring environment monitoring system includes: a management module, serving as a central interactive platform, providing interaction permissions for each functional module after identity verification; an environmental scanning module, used to deploy sensors within the pouring area to periodically scan the pouring environment in real time and collect regional status data; and an evaluation unit, used to analyze and process temperature information within the area based on the regional status data provided by the environmental scanning module, extracting temperature index, pollution index, and concrete solidification index. It can quickly adjust to dynamic environmental conditions, making the prediction of future pouring anomaly coefficients more accurate. This not only improves the safety of the construction process but also provides a scientific basis for construction quality control, enhancing the accuracy and effectiveness of decision-making, and improving the safety and emergency response efficiency of the construction process.

Description

Technical Field

[0001] This invention relates to the field of pouring monitoring technology, specifically to a pouring environment monitoring system and method. Background Technology

[0002] Construction projects involve a large number of materials and processes. Concrete pouring is a critical step, and its quality directly affects the structural safety and durability of buildings. Environmental factors, such as temperature, humidity, and pollutants, can significantly affect the curing process and final strength of concrete. Therefore, real-time monitoring of these factors has become particularly important. With the continuous improvement of safety standards and quality requirements in the construction industry, traditional methods of monitoring the pouring process are no longer sufficient to meet the needs of modern engineering. Building advanced monitoring systems to achieve real-time environmental monitoring and data analysis has become an important means to ensure construction quality and safety.

[0003] Existing technologies often rely on simple data recording and analysis, lacking deep learning and intelligent prediction capabilities. They typically depend on manual monitoring or fixed-frequency data collection, failing to provide real-time feedback on environmental changes. They lack integrated analysis of temperature fluctuations, pollutant concentrations, and concrete hardening speed, and can only respond passively to anomalies. They lack flexible alarm mechanisms and fail to fully consider the impact of various environmental factors. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a pouring environment monitoring system and method, which can effectively solve the problems of the existing technology.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] This invention discloses a pouring environment monitoring system, comprising:

[0009] The management module, acting as a central interactive platform, grants interaction permissions to various functional modules after identity verification.

[0010] The environmental scanning module is used to deploy sensors within the pouring area to periodically scan the pouring environment in real time and collect regional status data.

[0011] The evaluation unit is used to analyze and process the temperature information within the area based on the regional status data provided by the environmental scanning module, and to extract the temperature index, pollution index and concrete curing index.

[0012] The feature construction module is used to identify features such as temperature fluctuations, pollutant concentration change rates, and concrete hardening speed, forming a multi-dimensional feature set for input prediction models.

[0013] The model building module is used to build a prediction model based on the feature set built by the feature building module and using deep learning algorithms. The model is trained based on historical temperature index, pollution index and concrete solidification property characteristics to predict the pouring anomaly coefficient within a specified period.

[0014] The anomaly output module is used to extract the prediction model trained by the model building module. It takes the current real-time temperature index, pollution index and concrete solidification property characteristics as input, analyzes the impact of temperature and pollution status in the pouring area on concrete drying, and predicts the pouring anomaly coefficient within a specified future period.

[0015] The alarm response module is used to trigger a real-time alarm when the abnormal coefficient submitted by the abnormal output module exceeds the preset calibration threshold, and to transmit the warning information to the management terminal to remind or link the mechanical equipment to directly start and stop.

[0016] Furthermore, the evaluation unit is further equipped with sub-modules, including: a material evaluation module, a temperature evaluation module, and a contamination evaluation module, wherein:

[0017] The materials evaluation module is used to extract temperature data from raw data and generate temperature indices based on preset temperature indicators.

[0018] The temperature assessment module is used to extract the concentration data of harmful substances, dust and chemical pollutants in the air from the environmental sensor, and normalize them according to the set standards to generate a pollution index.

[0019] The pollution assessment module is used to evaluate the concrete setting index during the pouring process. By monitoring the temperature, humidity and hardening rate of the concrete interior and surface in real time, it outputs comprehensive concrete setting property parameters.

[0020] Furthermore, the feature construction module is interconnected with a data fusion module via a wireless network. The data fusion module is used to preprocess, clean, and fuse the raw data of the evaluation unit, interpolate and repair missing data, and provide warnings for abnormal data, thereby forming a high-quality dataset for the input of the prediction model.

[0021] Furthermore, the process of multidimensional feature recognition performed by the feature construction module includes:

[0022] The temperature index time series data is processed by time domain analysis, and the root mean square error of the temperature change rate within a set time window is calculated. When the fluctuation amplitude of three consecutive windows exceeds the historical threshold for the same period, it is marked as an abnormal temperature fluctuation event.

[0023] A multi-pollutant coupled analysis model is established for the pollution index. The sliding window difference algorithm is used to calculate the concentration gradient changes of harmful substances, dust and chemical pollutants in the air. When the rate of change of any pollutant exceeds the preset safety curve, the corresponding concentration change rate feature vector is generated.

[0024] Based on synchronous monitoring data from sensors inside and on the surface of concrete, a three-dimensional mapping table of temperature, humidity and hardening rate is established. By comparing the deviation between the real-time hardening rate and the theoretical curvature of the material, the hardening acceleration factor is calculated. When the deviation exceeds the material specification value, a hardening anomaly indicator is triggered.

[0025] The aforementioned fluctuation characteristics, rate of change characteristics, and hardening anomaly markers are timestamped and then normalized to generate a multidimensional feature matrix containing time correlations, which serves as the standardized input for the prediction model.

[0026] Furthermore, the model building module is interconnected with an input management module via a wireless network. The input management module is used to check whether the integrity and timeliness of the data submitted to the model building module meet the preset integrity threshold and timeliness threshold, and to cache abnormal inputs when sudden data fluctuations reach the preset fluctuation threshold.

[0027] Furthermore, the expression for the predictive model's working logic in the exception output module is as follows:

[0028] ;

[0029] In the formula, The predicted value of the pouring anomaly coefficient, representing the future time unit Δ. ( () represents the Sigmoid activation function, which maps the output to the (0,1) interval. Representing the Feature weight coefficients for each historical time node The number representing historical time points. Representing a historical moment Temperature index, Environmental factor correction coefficient representing the temperature index. Represents the reference temperature value. Representing a historical moment The pollution index Environmental factor correction coefficients representing pollution index Represents the baseline pollution value. Represents the derivative of the concrete hardening rate. Environmental factor correction coefficient representing the derivative of concrete hardening rate.

[0030] Furthermore, the alarm response module is interconnected with a configuration module via a wireless network. The configuration module is used to preset alarm thresholds for the alarm response module at multiple levels and to trigger alarm policies for corresponding levels based on the abnormal coefficient values ​​output by the abnormal output module. The alarm policies include sound, SMS, and email.

[0031] Furthermore, the environment scanning module is interconnected with the management module and the evaluation unit via a wireless network, the feature construction module is interconnected with the evaluation unit and the model construction module via a wireless network, and the anomaly output module is interconnected with the model construction module and the alarm response module via a wireless network.

[0032] A method for monitoring the pouring environment includes the following steps:

[0033] Step 1: Verify user identity on the central interactive platform and define user interaction permissions;

[0034] Step 2: Deploy sensors within the pouring area to periodically scan the pouring environment in real time and collect regional status data related to temperature, contaminants, and concrete solidification.

[0035] Step 3: Analyze the collected regional status data and extract the temperature index, pollution index, and concrete curing index;

[0036] Step 4: Identify the characteristics of temperature fluctuations, pollutant concentration change rates, and concrete hardening speed to form a multi-dimensional feature set;

[0037] Step 5: Using deep learning algorithms, train the constructed feature set based on historical temperature index, pollution index, and concrete solidification properties to generate a prediction model for anomaly coefficients.

[0038] Step 6: Using the trained prediction model, take the current temperature index, pollution index and concrete solidification properties as inputs to predict the pouring anomaly coefficient within a specified future period.

[0039] Step 7: When the predicted pouring anomaly coefficient exceeds the preset calibration threshold, the system automatically triggers a real-time alarm and sends a warning message to the management terminal or links the mechanical equipment to start and stop.

[0040] Step 8: Based on the anomaly coefficient value and according to the multi-level preset alarm thresholds, trigger the corresponding alarm strategy and send alarm notifications via sound, SMS and email.

[0041] Furthermore, the sensors in step 2 include: a DS18B20 temperature sensor, deployed inside and on the surface of the pouring area, for periodically collecting environmental and internal concrete temperature data; a PM2008M laser dust sensor, deployed at airflow nodes in the pouring area, for real-time detection of PM2.5 and PM10 particle concentrations; a MQ-135 chemical pollutant detection module, integrated at the edge of the pouring area, for monitoring the concentrations of ammonia, sulfides, and benzene volatiles; a DHT22 temperature and humidity composite sensor, embedded in the concrete surface and supporting structure, for synchronously collecting humidity and temperature change data; and a PZT-5A piezoelectric hardening monitoring sensor, pre-embedded in key nodes inside the concrete, for inferring the hardening rate by detecting the rate of change of sound wave propagation speed.

[0042] (III) Beneficial Effects

[0043] Compared with known prior art, the technical solution provided by this invention has the following beneficial effects:

[0044] 1. A predictive model is built using deep learning algorithms. Based on historical data, a model that can capture complex nonlinear relationships is trained. Compared with traditional statistical modeling methods, it has higher accuracy and adaptability. It can quickly adjust to dynamic environmental conditions, making the prediction of future pouring anomaly coefficients more accurate. This not only improves the safety of the construction process, but also provides a scientific basis for construction quality control.

[0045] 2. Through the deployment of multiple sensors, it is possible to comprehensively and in real time monitor the temperature, pollutant concentration and concrete solidification state in the pouring environment, and provide the ability to perform correlation analysis on multiple key indicators, ensuring a comprehensive understanding of the real-time status of the pouring environment, thereby improving the accuracy and effectiveness of decision-making.

[0046] 3. By integrating real-time alarm and automated response mechanisms, the system can automatically trigger alarms and link mechanical equipment to carry out corresponding processing when the detected abnormal coefficient exceeds the preset threshold. The real-time response capability greatly improves the safety of the construction process and the efficiency of emergency handling, reduces the need for manual intervention, and reduces the risks caused by human factors. Through the design of multi-level alarm strategies, the system can also flexibly adjust response measures according to the degree of abnormality, further improving the system's intelligence level and practicality. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0048] Figure 1 This is a schematic diagram of the framework of the present invention;

[0049] Figure 2 This is a schematic diagram of the evaluation unit in this invention.

[0050] The numbers in the diagram represent: 1. Management module; 2. Environmental scanning module; 3. Evaluation unit; 31. Material evaluation module; 32. Temperature evaluation module; 33. Pollution evaluation module; 4. Feature construction module; 5. Model construction module; 6. Anomaly output module; 7. Alarm response module; 8. Data fusion module; 9. Input management module; 10. Configuration module. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0052] The present invention will be further described below with reference to embodiments.

[0053] ① Example 1

[0054] This embodiment provides a pouring environment monitoring system, such as... Figures 1-2 As shown, it includes:

[0055] Management Module 1, as the central interactive platform, provides interaction permissions to various functional modules after identity verification;

[0056] Environmental scanning module 2 is used to deploy sensors in the pouring area to periodically scan the pouring environment in real time and collect regional status data;

[0057] Assessment unit 3 is used to analyze and process temperature information within the area based on the regional status data provided by environmental scanning module 2, and extract temperature index, pollution index, and concrete solidification index. Assessment unit 3 has sub-modules deployed below it, including: material assessment module 31, temperature assessment module 32, and pollution assessment module 33, wherein:

[0058] Material evaluation module 31 is used to extract temperature data from raw data and generate temperature indexes according to preset temperature index classification.

[0059] Temperature assessment module 32 is used to extract the concentration data of harmful substances, dust and chemical pollutants in the air from the environmental sensor, normalize them according to the set standard, and generate a pollution index.

[0060] The pollution assessment module 33 is used to assess the concrete setting index during the pouring process. By monitoring the temperature, humidity and hardening rate of the concrete interior and surface in real time, it outputs the comprehensive setting property parameters of the concrete.

[0061] Feature construction module 4 is used to identify temperature fluctuations, pollutant concentration change rates, and concrete hardening speed characteristics to form a multi-dimensional feature set for input prediction model; Feature construction module 4 is connected to data fusion module 8 via wireless network; Data fusion module 8 is used to preprocess, clean and fuse the raw data of evaluation unit 3, interpolate and repair missing data, and provide warning prompts for abnormal data to form a high-quality dataset for input prediction model.

[0062] Model building module 5 is used to build a prediction model based on the feature set built by feature building module 4 using deep learning algorithms. It is trained based on historical temperature index, pollution index and concrete solidification property characteristics to predict the pouring anomaly coefficient within a specified period. Model building module 5 is connected to input management module 9 via wireless network. Input management module 9 is used to check whether the integrity and timeliness of the data submitted to model building module 5 meet the preset integrity threshold and timeliness threshold, and to cache abnormal inputs when sudden data fluctuations reach the preset fluctuation threshold.

[0063] The abnormal output module 6 is used to extract the prediction model trained by the model building module 5, input the current real-time temperature index, pollution index and concrete solidification property characteristics, analyze the influence of temperature and pollution status in the pouring area on concrete drying, and predict the pouring abnormality coefficient within a specified period in the future.

[0064] The expression for the predictive model's working logic in the exception output module 6 is as follows:

[0065] ;

[0066] In the formula, The predicted value of the pouring anomaly coefficient, representing the future time unit Δ. This represents the Sigmoid activation function, which maps the output to the (0,1) interval. Representing the Feature weight coefficients for each historical time node The number representing historical time points. Representing a historical moment Temperature index, Environmental factor correction coefficient representing the temperature index. Represents the reference temperature value. Representing a historical moment The pollution index Environmental factor correction coefficients representing pollution index Represents the baseline pollution value. Represents the derivative of the concrete hardening rate. Environmental factor correction coefficient representing the derivative of concrete hardening rate;

[0067] The alarm response module 7 is used to trigger a real-time alarm when the abnormal coefficient submitted by the abnormal output module 6 exceeds the preset calibration threshold, and to transmit the warning information to the management terminal to remind or link the mechanical equipment to directly start and stop. The alarm response module 7 is connected to the configuration module 10 through a wireless network. The configuration module 10 is used to preset the alarm threshold of the alarm response module 7 at multiple levels. According to the abnormal coefficient value output by the abnormal output module 6, the alarm policy of the corresponding level is triggered. The alarm policies include: sound, SMS and email.

[0068] The environmental scanning module 2 is interconnected with the management module 1 and the evaluation unit 3 via a wireless network. The feature construction module 4 is interconnected with the evaluation unit 3 and the model construction module 5 via a wireless network. The anomaly output module 6 is interconnected with the model construction module 5 and the alarm response module 7 via a wireless network.

[0069] Compared with existing technologies, the system achieves identity verification and access control through a central interactive platform and multi-level modular design, improving system security and flexibility. The deployed sensors can perform periodic real-time scanning to ensure comprehensive monitoring of the pouring environment. By extracting and analyzing environmental data, it can generate comprehensive temperature index, pollution index and concrete solidification index, providing a scientific basis for construction quality.

[0070] In addition, the system uses deep learning methods to build a predictive model, which can not only monitor the current status, but also predict the future pouring anomaly coefficient, effectively preventing potential risks. The real-time alarm function, combined with multi-level alarm strategies, ensures that relevant personnel can respond in a timely manner, improving the safety and reliability of the construction process.

[0071] ② Example 2

[0072] At other levels, this embodiment also provides another optimization mechanism based on Embodiment 1, specifically a method for monitoring the pouring environment, including the following steps:

[0073] Step 1: Verify user identity on the central interactive platform and define user interaction permissions;

[0074] Step 2: Deploy sensors within the pouring area to periodically scan the pouring environment in real time and collect regional status data related to temperature, contaminants, and concrete solidification.

[0075] Step 3: Analyze the collected regional status data and extract the temperature index, pollution index, and concrete curing index;

[0076] Step 4: Identify the characteristics of temperature fluctuations, pollutant concentration change rates, and concrete hardening speed to form a multi-dimensional feature set;

[0077] Step 5: Using deep learning algorithms, train the constructed feature set based on historical temperature index, pollution index, and concrete solidification properties to generate a prediction model for anomaly coefficients.

[0078] Step 6: Using the trained prediction model, take the current temperature index, pollution index and concrete solidification properties as inputs to predict the pouring anomaly coefficient within a specified future period.

[0079] Step 7: When the predicted pouring anomaly coefficient exceeds the preset calibration threshold, the system automatically triggers a real-time alarm and sends a warning message to the management terminal or links the mechanical equipment to start and stop.

[0080] Step 8: Based on the anomaly coefficient value and according to the multi-level preset alarm thresholds, trigger the corresponding alarm strategy and send alarm notifications via sound, SMS, and email.

[0081] The sensors in step 2 include: a DS18B20 temperature sensor, deployed inside and on the surface of the pouring area, used to periodically collect ambient and internal concrete temperature data; a PM2008M laser dust sensor, deployed at air circulation nodes in the pouring area, used to detect PM2.5 and PM10 particle concentrations in real time; a MQ-135 chemical pollutant detection module, integrated at the edge of the pouring area, used to monitor the concentrations of ammonia, sulfides, and benzene volatiles; a DHT22 temperature and humidity composite sensor, embedded in the concrete surface and supporting structure, used to simultaneously collect humidity and temperature change data; and a PZT-5A piezoelectric hardening monitoring sensor, pre-embedded in key nodes inside the concrete, used to infer the hardening rate by detecting the rate of change of sound wave propagation speed.

[0082] ③ Example 3

[0083] This embodiment provides a process for performing multidimensional feature recognition, including:

[0084] The temperature index time series data is processed by time domain analysis, and the root mean square error of the temperature change rate within a set time window is calculated. When the fluctuation amplitude of three consecutive windows exceeds the historical threshold for the same period, it is marked as an abnormal temperature fluctuation event.

[0085] A multi-pollutant coupled analysis model is established for the pollution index. The sliding window difference algorithm is used to calculate the concentration gradient changes of harmful substances, dust and chemical pollutants in the air. When the rate of change of any pollutant exceeds the preset safety curve, the corresponding concentration change rate feature vector is generated.

[0086] Based on synchronous monitoring data from sensors inside and on the surface of concrete, a three-dimensional mapping table of temperature, humidity and hardening rate is established. By comparing the deviation between the real-time hardening rate and the theoretical curvature of the material, the hardening acceleration factor is calculated. When the deviation exceeds the material specification value, a hardening anomaly indicator is triggered.

[0087] The aforementioned fluctuation characteristics, rate of change characteristics, and hardening anomaly markers are timestamped and then normalized to generate a multidimensional feature matrix containing time correlations, which serves as the standardized input for the prediction model.

[0088] Compared with existing technologies, the multi-dimensional feature recognition process significantly improves the monitoring and analysis capabilities of the pouring environment. The use of time-domain analysis and root mean square error to calculate the temperature change rate improves the accuracy of identifying abnormal temperature fluctuation events. Secondly, a multi-pollutant coupled analysis model is constructed for pollution indicators, which can monitor and analyze the concentration changes of multiple pollutants in real time, ensuring environmental safety.

[0089] By simultaneously monitoring the temperature, humidity, and hardening rate of concrete, establishing a three-dimensional mapping table, and calculating deviations, a more accurate assessment of the hardening state is provided. The generated multi-dimensional feature matrix, which includes time correlations, provides standardized input for the prediction model, improving the accuracy and reliability of predictions. This integrated monitoring and analysis method effectively reduces potential risks and enhances the intelligence level of the construction process.

[0090] Working Principle: When the system of this invention is installed, the management module 1 verifies the identity and assigns role permissions; the environmental scanning module 2 deploys sensors in the pouring area to periodically collect environmental status data; the material evaluation module 31 extracts and classifies to generate a temperature index; the temperature evaluation module 32 normalizes to generate a pollution index; the pollution evaluation module 33 evaluates the concrete solidification index; the data fusion module 8 preprocesses, cleans, interpolates, and performs anomaly alerts on the raw data to form a high-quality multidimensional feature set; the feature construction module 4 then extracts multidimensional features from these data to identify temperature fluctuations, pollutant changes, and concrete hardening characteristics; the model construction module 5 builds a prediction model using deep learning methods to train the prediction ability of pouring anomaly coefficients; the anomaly output module 6 inputs real-time data into the model to predict future pouring anomaly coefficients; if the predicted anomaly coefficient exceeds a preset threshold, the alarm response module 7 will trigger an alarm through the wireless network and notify the management; at the same time, the configuration module 10 implements a multi-level alarm strategy; and the input management module 9 monitors the data of the model construction module 5 to check its integrity and timeliness, ensuring the stability of the data input to the model.

[0091] This invention has the advantages of efficient real-time monitoring, accurate data analysis, and intelligent early warning. By deploying sensors to collect data on temperature, pollution, and concrete solidification status, the system uses deep learning technology to build a predictive model, which can identify abnormal situations in the pouring process in advance and trigger alarms. Through multi-dimensional feature recognition and anomaly monitoring mechanisms, it helps to ensure the safety and quality of concrete construction, reduce construction risks, and improve resource utilization efficiency. The modular design of the overall system gives it good scalability and flexibility, adapting to the needs of different construction environments.

[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A pouring environment monitoring system, characterized in that, include: The management module (1), as a central interactive platform, provides interactive permissions for each functional module after identity verification; The environmental scanning module (2) is used to deploy sensors in the pouring area to periodically scan the pouring environment in real time and collect regional status data. The evaluation unit (3) is used to analyze and process the regional status data information within the region based on the regional status data provided by the environmental scanning module (2), and extract the temperature index, pollution index and concrete solidification index. The feature construction module (4) is used to identify temperature fluctuations, pollutant concentration change rates, and concrete hardening speed characteristics to form a multi-dimensional feature set for input prediction models; The model building module (5) is used to build a prediction model based on the feature set built by the feature building module (4) using deep learning algorithms. The model is trained based on the historical temperature index, pollution index and concrete solidification property characteristics to predict the pouring anomaly coefficient within a specified period. The abnormal output module (6) is used to extract the prediction model trained by the model building module (5), input the current real-time temperature index, pollution index and concrete solidification property characteristics, analyze the influence of temperature and pollution status in the pouring area on concrete drying, and predict the pouring abnormal coefficient within a specified period in the future. The alarm response module (7) is used to trigger a real-time alarm when the abnormal coefficient submitted by the abnormal output module (6) exceeds the preset calibration threshold, and to transmit the warning information to the management terminal to remind or link the mechanical equipment to start and stop directly. The assessment unit (3) has sub-modules deployed below it, including: a material assessment module (31), a temperature assessment module (32), and a pollution assessment module (33), wherein: The material evaluation module (31) is used to evaluate the concrete solidification index during the pouring process. By monitoring the temperature, humidity and hardening rate of the concrete inside and on the surface in real time, it outputs the comprehensive solidification property parameters of the concrete. Temperature assessment module (32) is used to extract temperature data from raw data and generate temperature index according to preset temperature index classification; The pollution assessment module (33) is used to extract the concentration data of harmful substances, dust and chemical pollutants in the air from the environmental sensor, normalize them according to the set standards, and generate a pollution index. The process of multidimensional feature recognition performed by the feature construction module (4) includes: The temperature index time series data is processed by time domain analysis, and the root mean square error of the temperature change rate within a set time window is calculated. When the fluctuation amplitude of three consecutive windows exceeds the historical threshold for the same period, it is marked as an abnormal temperature fluctuation event. A multi-pollutant coupled analysis model is established for the pollution index. The sliding window difference algorithm is used to calculate the concentration gradient changes of harmful substances, dust and chemical pollutants in the air. When the rate of change of any pollutant exceeds the preset safety curve, the corresponding concentration change rate feature vector is generated. Based on synchronous monitoring data from sensors inside and on the surface of concrete, a three-dimensional mapping table of temperature, humidity and hardening rate is established. By comparing the deviation between the real-time hardening rate and the theoretical curvature of the material, the hardening acceleration factor is calculated. When the deviation exceeds the material specification value, a hardening anomaly indicator is triggered. The aforementioned fluctuation characteristics, rate of change characteristics, and hardening anomaly markers are timestamped and then normalized to generate a multidimensional feature matrix containing time correlations, which serves as the standardized input for the prediction model. The expression for the predictive model's working logic in the exception output module (6) is as follows: In the formula, The predicted value of the pouring anomaly coefficient, representing the future time unit Δ. ( () represents the Sigmoid activation function, which maps the output to the (0,1) interval. Representing the Feature weight coefficients for each historical time node The number representing historical time points. Representing a historical moment Temperature index, Environmental factor correction coefficient representing the temperature index. Represents the reference temperature value. Representing a historical moment The pollution index Environmental factor correction coefficients representing pollution index Represents the baseline pollution value. Represents the derivative of the concrete hardening rate. Environmental factor correction coefficient representing the derivative of concrete hardening rate.

2. The pouring environment monitoring system according to claim 1, characterized in that, The feature construction module (4) is connected to the data fusion module (8) via a wireless network. The data fusion module (8) is used to preprocess, clean and fuse the original data of the evaluation unit (3), interpolate and repair missing data, and provide warning prompts for abnormal data to form a high-quality dataset for the input of the prediction model.

3. The pouring environment monitoring system according to claim 1, characterized in that, The model building module (5) is connected to the input management module (9) via a wireless network. The input management module (9) is used to check whether the integrity and timeliness of the data submitted to the model building module (5) meet the preset integrity threshold and timeliness threshold, and to cache abnormal inputs when sudden data fluctuations reach the preset fluctuation threshold.

4. The pouring environment monitoring system according to claim 1, characterized in that, The alarm response module (7) is connected to the configuration module (10) via a wireless network. The configuration module (10) is used to preset the alarm threshold of the alarm response module (7) at multiple levels. Based on the abnormal coefficient value output by the abnormal output module (6), the alarm strategy of the corresponding level is triggered. The alarm strategy includes sound, SMS and email.

5. The pouring environment monitoring system according to claim 1, characterized in that, The environmental scanning module (2) is interconnected with the management module (1) and the evaluation unit (3) via a wireless network. The feature construction module (4) is interconnected with the evaluation unit (3) and the model construction module (5) via a wireless network. The abnormal output module (6) is interconnected with the model construction module (5) and the alarm response module (7) via a wireless network.

6. A method for monitoring the pouring environment, said method being an implementation method of a pouring environment monitoring system based on any one of claims 1-5, characterized in that, Includes the following steps: Step 1: Verify user identity on the central interactive platform and define user interaction permissions; Step 2: Deploy sensors within the pouring area to periodically scan the pouring environment in real time and collect regional status data related to temperature, contaminants, and concrete solidification. Step 3: Analyze the collected regional status data and extract the temperature index, pollution index, and concrete curing index; Step 4: Identify the characteristics of temperature fluctuations, pollutant concentration change rates, and concrete hardening speed to form a multi-dimensional feature set; Step 5: Using deep learning algorithms, train the constructed feature set based on historical temperature index, pollution index, and concrete solidification properties to generate a prediction model for anomaly coefficients. Step 6: Using the trained prediction model, take the current temperature index, pollution index and concrete solidification properties as inputs to predict the pouring anomaly coefficient within a specified future period. Step 7: When the predicted pouring anomaly coefficient exceeds the preset calibration threshold, the system automatically triggers a real-time alarm and sends a warning message to the management terminal or links the mechanical equipment to start and stop. Step 8: Based on the anomaly coefficient value and according to the multi-level preset alarm thresholds, trigger the corresponding alarm strategy and send alarm notifications via sound, SMS and email.

7. The method for monitoring the pouring environment according to claim 6, characterized in that, The sensors in step 2 include: a DS18B20 temperature sensor, deployed inside and on the surface of the pouring area, for periodically collecting environmental and internal concrete temperature data; a PM2008M laser dust sensor, deployed at air circulation nodes in the pouring area, for real-time detection of PM2.5 and PM10 particle concentrations; a MQ-135 chemical pollutant detection module, integrated at the edge of the pouring area, for monitoring the concentrations of ammonia, sulfides, and benzene volatiles; a DHT22 temperature and humidity composite sensor, embedded in the concrete surface and supporting structure, for synchronously collecting humidity and temperature change data; and a PZT-5A piezoelectric hardening monitoring sensor, pre-embedded in key nodes inside the concrete, for inferring the hardening rate by detecting the rate of change of sound wave propagation speed.

Images