Concrete transportation monitoring method and system

Abstract

The invention relates to the technical field of concrete transportation monitoring, and discloses a concrete transportation monitoring method and system, and the method comprises the following steps: S1, data collection: obtaining concrete state data and environment data in real time through a data collection module, the data acquisition module comprises a temperature sensor, a humidity sensor, a vibration sensor, a light sensor and a high-definition camera device; s2, data fusion and preprocessing; s3, data transmission and cloud storage; s4, cloud data analysis; and S5, performing anomaly detection and early warning response. By means of various sensors and high-definition camera devices in the data acquisition module, state data and environment data of concrete are obtained in real time, multi-dimensional information monitoring is achieved, the edge calculation module conducts data preprocessing, data transmission delay is remarkably reduced, the real-time performance of the system is improved, whole-course non-blind-area monitoring of the concrete transportation process is achieved, and real-time monitoring of the concrete transportation process is achieved. And data accuracy and reliability are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete transportation monitoring, and specifically provides a concrete transportation monitoring method and system. Background Art

[0002] Concrete is one of the main building materials widely used in construction projects, and its quality is closely related to the state during transportation. With the increase in urban construction and large-scale engineering projects, the importance of the concrete transportation link has become increasingly prominent. During the transportation of concrete, changes in factors such as temperature, humidity, and vibration may cause quality problems such as layering, segregation, and abnormal solidification of concrete, which in turn affect the construction quality and project progress. Therefore, real-time monitoring, abnormal detection, and intelligent regulation of the concrete transportation state are of great significance for ensuring the quality of concrete.

[0003] Currently, traditional concrete transportation monitoring mainly relies on manual observation and single-parameter detection. Some technical solutions achieve simple monitoring of the concrete transportation process through GPS positioning and basic temperature and humidity sensors, but there are still many limitations. For example, the data monitoring accuracy of single sensors is relatively low, and multi-dimensional information fusion cannot be achieved, resulting in one-sided and inaccurate data. In addition, the existing monitoring methods do not achieve systematic intelligent response. When the concrete state is abnormal, rapid warning and automatic regulation cannot be achieved, increasing the risk of deterioration of the concrete quality during transportation.

[0004] In the existing technology, although some solutions introduce remote monitoring and sensor technology, the following problems still exist: full-range blind-spot-free monitoring of the concrete transportation process and rapid response to abnormal states cannot be achieved. Specifically, the existing methods lack multi-dimensional information acquisition and data fusion technology, and cannot effectively combine multi-parameter data such as temperature, humidity, and vibration for comprehensive monitoring. At the same time, in the abnormal state, the system response speed is slow, and the warning mechanism and intelligent regulation cannot be triggered in time, resulting in the inability to effectively guarantee the concrete quality. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the present invention provides a concrete transportation monitoring method and system, which solves the problems existing in the existing solutions that introduce remote monitoring and sensor technology, but still cannot achieve full-range blind-spot-free monitoring of the concrete transportation process and rapid response to abnormal states.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A concrete transportation monitoring method, including the following steps: Step S1: Data acquisition. Real-time concrete state data and environmental data are obtained through a data acquisition module, which includes a temperature sensor, a humidity sensor, a vibration sensor, a light sensor, and a high-definition camera device. Step S2: Data fusion and preprocessing. The collected data is transmitted to an edge computing module, and the data is processed through a multi-sensor data fusion algorithm, and abnormal screening and compression are performed. Step S3: Data transmission and cloud storage. The preprocessed data is transmitted to a cloud server through a wireless network and stored in a time series database. Step S4: Cloud data analysis. Through a cloud analysis module, the state of the concrete is predicted in real time based on a deep learning model, and a state evaluation report is generated. Step S5: Abnormal detection and early warning response. According to the analysis results and preset thresholds, data anomalies are detected, the alarm module is triggered, and alarm information is sent to the construction person in charge. Step S6: Action regulation. The action execution module is triggered, and operations such as temperature regulation, vibration compensation, or light compensation are performed according to the type of anomaly. Step S7: Feedback and remote management. The monitoring data, abnormal early warning information, and action execution results are fed back to the terminal management module to achieve data visualization monitoring and remote control.

[0007] Preferably, the data fusion is realized through an extended Kalman filter algorithm, which specifically includes: Setting a system state equation and an observation equation, and using the Kalman gain to optimize and fuse the data, and outputting a fused state vector.

[0008] Preferably, the data preprocessing includes: Performing multi-sensor data fusion on temperature, humidity, and vibration data, and processing it using an extended Kalman filter algorithm.

[0009] Preferably, the abnormal detection is realized through the 3σ criterion, specifically: Setting the data mean μ and the standard deviation σ, and judging whether the data X i satisfies |X i -μ|>3σ.

[0010] Preferably, the data compression adopts a sliding window averaging method, and the data compression calculation formula is: where W is the sliding window size.

[0011] Preferably, the action execution module includes: A dropping device for cooling the concrete when the temperature is abnormal; A heating device for heating concrete when the temperature is lower than the set value; A supplementary lighting device for providing lighting compensation when the light is insufficient; A vibration control device for performing shock absorption compensation when the vibration of the tank body is too large.

[0012] Preferably, the alarm module automatically triggers multiple alarm methods according to the abnormal level, including: SMS notification, automatic voice call, APP push, and start of a remote liaison meeting.

[0013] Preferably, the terminal management module includes: A real-time monitoring interface for displaying sensor data, image monitoring results, and vehicle position information; An alarm information display module for viewing abnormal warning information and solutions; A control instruction module for sending action regulation instructions to the action execution module.

[0014] Preferably, the cloud analysis module dynamically updates the model parameters through historical data, enabling the deep learning model to achieve adaptive optimization.

[0015] A concrete transportation monitoring system, including: A data acquisition module, including a temperature sensor, a humidity sensor, a vibration sensor, a light sensor, and a high-definition camera device, for real-time acquisition of concrete state data and transportation environment data; An edge computing module, connected to the data acquisition module, for performing fusion, anomaly detection, and compression processing on the acquired data; a cloud analysis module, connected to the edge computing module, for receiving data and performing concrete state prediction and anomaly analysis based on a deep learning model; An action execution module, connected to the cloud analysis module, for performing actions such as temperature regulation, vibration compensation, and light compensation; an alarm module, connected to the cloud analysis module, for sending various forms of alarm notifications during anomaly detection; A terminal management module, connected to the cloud analysis module and the action execution module, for real-time monitoring, viewing alarm information, and sending remote control instructions.

[0016] The present invention provides a concrete transportation monitoring method and system. It has the following beneficial effects: 1. The present invention uses a variety of sensors and high-definition imaging devices in the data acquisition module to obtain the status data and environmental data of concrete in real time, realizing multi-dimensional information monitoring. By combining the extended Kalman filter algorithm to fuse the sensor data, it ensures the high precision and consistency of the data, overcomes the problems of large errors and one-sided monitoring of a single sensor. The edge computing module performs data preprocessing, significantly reducing data transmission latency and improving the real-time performance of the system, achieving full-range blind-spot-free monitoring during the concrete transportation process and ensuring the accuracy and reliability of the data.

[0017] 2. The present invention uses the 3σ criterion and the abnormal threshold determination algorithm to perform real-time abnormal detection on data such as temperature, humidity, and vibration, quickly identifying changes in the concrete state and abnormal vibrations of the tank body. Once an abnormal situation is detected, the system automatically triggers multiple warning mechanisms through the alarm module, including SMS notification, automatic voice call, and APP push, ensuring that relevant personnel receive information in a timely manner. The action execution module performs temperature regulation, vibration compensation, or light compensation according to the type of abnormality, realizing the intelligent response and automatic adjustment of the system, effectively shortening the abnormal response time, ensuring the safety and stability of the concrete transportation process, and avoiding the deterioration of concrete quality.

[0018] 3. The present invention uses a CNN-LSTM hybrid model to perform in-depth learning analysis on the concrete status data, extracting image features and time series features, realizing trend prediction and quality assessment of the concrete state. The cloud analysis module adaptively optimizes the model through historical data, continuously improving the prediction accuracy and the robustness of the system. Based on the prediction results, the system can identify potential quality risks in advance and take preventive measures, achieving precise prediction and dynamic control of the concrete state, significantly reducing the quality risks during transportation, and improving the quality of concrete construction.

[0019] 4. The present invention has edge computing and cloud collaboration: The data is initially fused and compressed by the edge computing module, effectively reducing the data transmission volume, reducing the risk of network latency and data loss. The sliding window averaging method is used to compress the sensor data to ensure the efficiency and real-time performance of data transmission. The data is transmitted to the cloud server through a wireless network (4G / 5G) and stored in a time series database, providing efficient data management and calling capabilities, significantly improving the data transmission and storage efficiency, and ensuring the real-time performance and stability of the system.

[0020] 5. The action execution module of the present invention integrates a dropping device, a heating device, a supplementary lighting device, and a vibration control device, which can perform automated responses according to abnormal situations to regulate the concrete state. The terminal management module realizes functions such as data visualization monitoring, alarm information display, and remote control. The construction party can view the concrete state in real time through the terminal and send remote control instructions, improving the automation and intelligence level of concrete transportation and enhancing the management convenience and response efficiency of the construction party.

[0021] 6. Through real-time monitoring and status prediction, the system of the present invention can dynamically adjust the state of concrete during transportation, reduce material waste caused by out-of-control state, and has intelligent early warning and response functions, effectively reducing quality defects of concrete caused by abnormal temperature, excessive vibration, etc., reducing rework costs, improving the resource utilization rate and construction efficiency during the concrete transportation process, and reducing material waste and construction costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is the flowchart of the method of the present invention; Figure 2 is the schematic diagram of the main framework of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0024] Embodiment 1: Please refer to the attached Figure 1 , the embodiment of the present invention provides a concrete transportation monitoring method, including the following steps: Step S1: Data collection, real-time acquisition of concrete state data and environmental data through a data collection module, and the data collection module includes a temperature sensor, a humidity sensor, a vibration sensor, a light sensor, and a high-definition camera device; Step S2: Data fusion and preprocessing, transmitting the collected data to an edge computing module, processing the data through a multi-sensor data fusion algorithm, and performing abnormal screening and compression; Step S3: Data transmission and cloud storage, transmitting the preprocessed data to a cloud server through a wireless network and storing it in a time series database; Step S4: Cloud data analysis, through a cloud analysis module, performing real-time prediction on the state of concrete based on a deep learning model and generating a state evaluation report; Step S5: Abnormal detection and early warning response, detecting data anomalies according to the analysis results and preset thresholds, triggering an alarm module, and sending an alarm message to the construction person in charge; Step S6: Action regulation, triggering an action execution module, and performing operations such as temperature regulation, vibration compensation, or light compensation according to the type of anomaly; Step S7: Feedback and Remote Management. The monitoring data, abnormal warning information, and action execution results are fed back to the terminal management module to achieve visual data monitoring and remote control.

[0025] Data fusion is achieved through the extended Kalman filter algorithm, specifically including: Setting the system state equation and observation equation, and using the Kalman gain to optimize and fuse the data, and outputting the fused state vector.

[0026] Data preprocessing includes: Performing multi-sensor data fusion on temperature, humidity, and vibration data, and using the extended Kalman filter algorithm for processing.

[0027] Abnormal detection is achieved through the 3σ criterion, specifically: Setting the data mean μ and standard deviation σ, and judging whether the data X i satisfies |X i - μ| > 3σ.

[0028] Data compression uses the sliding window averaging method, and the data compression calculation formula is: where W is the sliding window size.

[0029] The action execution module includes: A dropping device for cooling the concrete when the temperature is abnormal; A heating device for heating the concrete when the temperature is lower than the set value; A supplementary lighting device for providing lighting compensation when the light is insufficient; A vibration control device for performing shock absorption compensation when the vibration of the tank body is too large.

[0030] The alarm module automatically triggers multiple alarm methods according to the abnormal level, including: SMS notification, automatic voice call, APP push, and initiation of a remote liaison meeting.

[0031] The terminal management module includes: A real-time monitoring interface for displaying sensor data, image monitoring results, and vehicle position information; An alarm information display module for viewing abnormal warning information and solutions; A control instruction module for sending action regulation instructions to the action execution module.

[0032] The cloud analysis module dynamically updates the model parameters through historical data, enabling the deep learning model to achieve adaptive optimization.

[0033] Step S1: Data Acquisition This step is the starting link of the concrete transportation monitoring method. The data acquisition module obtains real-time data on the concrete state and external environment, providing basic data support for subsequent data processing, analysis, and regulation. The data acquisition module not only needs to achieve multi-dimensional information acquisition but also ensure the real-time and accuracy of the acquired data to enable effective monitoring in a complex transportation environment. In view of the characteristics of temperature, humidity, vibration, light, and concrete state changes during the concrete transportation process, the data acquisition module realizes comprehensive coverage and high-precision acquisition of information by deploying a variety of sensors and high-definition camera devices.

[0034] In this embodiment, the data acquisition module includes a temperature sensor, a humidity sensor, a vibration sensor, a light sensor, and a high-definition camera device. The sensors are distributed inside and outside the concrete tank body, and the acquired real-time data includes temperature, humidity, vibration amplitude, light intensity, and concrete state images.

[0035] Specifically, the temperature sensors are arranged on the inner and outer walls of the concrete tank body, respectively, for detecting the real-time temperature T of the concrete inside the tank in and the external environment temperature T out in °C. As an option, a high-precision thermocouple sensor can be selected, with a temperature detection range of -20°C to 60°C and an accuracy of up to ±0.5°C.

[0036] It should be noted that the internal temperature of the tank has a direct impact on the setting state of the concrete, so the acquisition of the temperature data inside the tank is particularly important.

[0037] The humidity sensor is used to monitor the air humidity H outside the tank body, and the acquired data is expressed in relative humidity (RH%). Exemplarily, a capacitive humidity sensor can be selected, with a humidity range of 0% to 100% and an accuracy of up to ±2%. In a possible implementation, the humidity data can be combined with the temperature data to evaluate the setting rate of the concrete.

[0038] The vibration sensor is used to detect the vibration data V(t) generated by the concrete tank body during transportation, with the unit of m / s 2 . As an option, an accelerometer sensor can be arranged at key positions of the tank body (such as bearing points) to continuously monitor the change of vibration amplitude during transportation.

[0039] It should be noted that excessive vibration of the tank body may cause the stratification or segregation of the concrete. The real-time acquisition and analysis of vibration data can provide a basic basis for the detection of abnormal states.

[0040] The light sensor is used to detect the light intensity L inside the tank body iIn units of lx (lux). Specifically, the light sensor is used in conjunction with the high-definition camera device to ensure that the brightness parameters of the camera device can be automatically adjusted in low-light conditions, thus ensuring that the captured concrete state images are clear and usable.

[0041] In a possible implementation, a photoresistor sensor can be selected, with a light range of 0 - 2000 lx.

[0042] The high-definition camera device is installed inside the concrete tank to collect real-time state images I(t) of the concrete. As an option, the camera device supports a resolution of 1920×1080 and a frame rate of up to 30 fps, ensuring the continuity and accuracy of the image data.

[0043] Specifically, the high-definition camera device can not only capture the overall state of the concrete, but also monitor the slump and layering of the concrete. The image data will be used for feature extraction in subsequent deep learning analysis. It should be noted that when the internal lighting conditions of the tank are poor, the fill light device can be automatically triggered by the light sensor to improve the image acquisition quality.

[0044] In some embodiments, to ensure the real-time and continuous nature of the collected data, the data acquisition module can be set to a sampling frequency of 1 Hz, that is, data is collected once per second, forming time series data: D raw (t) = {T in (t), T out (t), H(t), V(t), L i (t), I(t)}, t ∈ [0, T] where t is time, and D raw (t) is the set of sensor and image data collected.

[0045] In a possible implementation, the data acquisition module transmits the collected sensor data to the edge computing module via the I2C or CAN bus protocol. Specifically, the I2C protocol is suitable for short-distance and low-speed data transmission, and the CAN bus is suitable for long-distance multi-device communication. Users can choose according to actual needs.

[0046] Exemplarily, to improve the reliability of data acquisition, the sensor data can also be calibrated by combining the average value of multiple measurements during the acquisition process. The specific calculation formula is: where, X avg is the calibrated average value, n is the number of sampling times, and X i is the data collected for the i-th time.

[0047] It is understandable that the data obtained by the data acquisition module will directly affect the subsequent data fusion and analysis results. Therefore, through reasonable sensor layout and high-precision data acquisition equipment, the integrity and accuracy of the data can be ensured.

[0048] It should be noted that in some specific transportation scenarios, the data acquisition module can add the following functions: Add a GPS module to obtain the vehicle's location information and driving route in real time, facilitating the tracking and scheduling of the transportation process.

[0049] Add an acceleration gyroscope to monitor the tilt angle and rotation state of the tank body, further enhancing the comprehensiveness of transportation status monitoring.

[0050] Add a data redundancy mechanism, set up two sets of main and backup sensor systems. When the main sensor fails, the backup system automatically takes over the data acquisition task to ensure that the monitoring does not interrupt.

[0051] Step S2: Data fusion and preprocessing Data fusion and preprocessing is a crucial step in the method for monitoring concrete transportation implemented by the present invention. The purpose of this step is to process the multi-dimensional raw data obtained by the data acquisition module, including operations such as data fusion, anomaly detection, and data compression. Through the edge computing module, real-time calculations and preliminary analyses are performed, which can not only reduce data redundancy and noise interference but also ensure the efficiency and accuracy of data transmission, providing high-quality data support for subsequent cloud data analysis.

[0052] In this embodiment, the edge computing module receives the raw data D raw (t) collected from temperature, humidity, vibration, light sensors, and high-definition camera devices and performs fusion and preprocessing according to the following steps.

[0053] Specifically, first, the edge computing module fuses the multi-sensor data and realizes the non-linear fusion of the data through the Extended Kalman Filter (EKF) algorithm to ensure the accuracy and consistency of the data from each sensor. As an option, the following mathematical model is used for data fusion: The state equation of the system is: x k = Ax k-1 + Bu k + w k The observation equation of the system is: z k = Hx k + v k Where: x k is the system state vector, including Ti n(t), T out (t), H(t), V(t), L i (t); z k is the observation vector; A is the state transition matrix, describing the change relationship of the system state; B is the control matrix, describing the influence of external inputs; H is the observation matrix; w k and u k are the process noise and observation noise respectively, satisfying the Gaussian distribution assumption In a possible implementation, the edge computing module uses the Kalman gain K k to fuse and optimize the data, and the calculation formula is: K k = P k H T (HP k H T + R) -1 Where: K k is the Kalman gain; P k is the covariance matrix of state estimation; R is the covariance matrix of observation noise.

[0054] Exemplarily, through the above extended Kalman filtering algorithm, the edge computing module fuses the data of multiple sensors and outputs a high-confidence data set X fusion (t).

[0055] It should be noted that due to the large amount of data and high real-time requirements of the image data collected by the high-definition camera device, preliminary compression and key frame screening are mainly performed in this step to reduce the transmission load of redundant data. As an option, a frame rate downsampling method based on time intervals can be used to retain only the key image frames within a specific time interval.

[0056] Secondly, the edge computing module performs anomaly detection on the fused data. Exemplarily, the temperature data T in (t) and the vibration data V(t) are screened for outliers through the 3σ criterion. The specific screening steps are as follows: Let the mean of the data be μ and the standard deviation be σ, then the decision formula for abnormal data is: Where: X i is a single data point collected; δ i= 1 indicates data anomaly.

[0057] In a possible implementation, the abnormal data will be marked and recorded, and at the same time uploaded to the cloud through the edge computing module for further processing. As an option, in order to reduce the data transmission volume, the edge computing module performs data compression on the fused data. In this embodiment, the sliding window averaging method is used to compress the continuous data, and the calculation formula is: Where: X comp (t) is the compressed data; W is the size of the sliding window; X k is the original data point within the window It can be understood that through the sliding window averaging method, the edge computing module can effectively reduce the data jitter and redundancy, while retaining the main trend characteristics of the data, ensuring that the data transmitted to the cloud is efficient and representative.

[0058] In some embodiments, to improve the data processing efficiency, the edge computing module can use the parallel computing method to independently process and fuse the data of different sensors. Specifically, the edge computing module uses the multi-threading technology to parallel process the data of sensors such as temperature, humidity, and vibration, and then unify and fuse the processing results.

[0059] It should be noted that data fusion and preprocessing are the basic links for subsequent data transmission and cloud analysis. The core purpose is to reduce data redundancy, improve data quality, and ensure real-time data transmission at the edge. Therefore, in this embodiment, efficient fusion algorithms, anomaly detection mechanisms, and compression methods are adopted to achieve the preliminary optimization processing of multi-dimensional data.

[0060] Step S3: Data Transmission and Cloud Storage Data transmission and cloud storage are important links in implementing the concrete transportation monitoring method in the present invention. The main task of this step is to efficiently and reliably transmit the data processed by the edge computing module to the cloud server, and store and manage it in the cloud, providing the necessary data support for subsequent data analysis and status prediction. To ensure the stability and real-time nature of data transmission, this step combines the wireless network transmission technology and the time series database storage structure, and optimizes the data transmission performance and storage efficiency through reasonable protocol selection and data management mechanisms.

[0061] In this embodiment, wireless communication technology is used for data transmission to transfer data from the edge computing module to the cloud server for storage and management in the cloud. Specifically, the data transmission process includes three links: data packaging, transmission, and reception, and the data storage process includes the design of data storage format, index establishment, and data update and maintenance.

[0062] It should be noted that the data processed by the edge computing module includes multi-dimensional fusion data X fusion (t) and compressed data X comp (t). These data have high compactness and accuracy, which can significantly reduce the burden on the transmission network.

[0063] As an option, during the data transmission process, the MQTT protocol is used for wireless data transmission. The MQTT protocol is a lightweight communication protocol based on the publish / subscribe model and is suitable for wireless network environments with low bandwidth and high latency. Exemplarily, the transmission data packaging format can be designed as: D pack ={t,X fusion (t),X comp (t),ID,Location} Where: t represents the data timestamp; X fusion (t) is the high-confidence data after fusion; X comp (t) is the compressed data; ID represents the unique identifier of the concrete mixer truck; Location represents the location information of the truck obtained through GPS.

[0064] In a possible implementation, the data transmission rate can be dynamically adjusted according to network conditions to ensure the real-time and reliable nature of the data. For example, when the network bandwidth is high, the system can transmit the complete set of fusion data and compressed data; when the network bandwidth is low, the system can preferentially transmit the key data X comp (t).

[0065] It should be noted that to ensure the integrity and reliability of data transmission, a data verification mechanism is adopted in this embodiment, specifically including: In the data packaging stage, cyclic redundancy check (CRC) is performed on the transmission data to generate a check code; When the cloud server receives data, verification is performed on the received data packet. If the verification fails, a request for data transmission is made again.

[0066] Specifically, the cyclic redundancy check calculation formula is: CCRC = X pack mod G Where: X pack The data packet to be transmitted; G is the generating polynomial; C CRC Is the generated check code.

[0067] During the data reception process, if the check code of the received data is inconsistent with the check code generated by the sender, it is considered that an error has occurred in the data transmission, and the retransmission mechanism is triggered.

[0068] In some embodiments, in order to further improve the reliability and security of data transmission, the data transmission can adopt an encryption algorithm, such as the AES encryption algorithm, to encrypt and transmit the data packet. Specifically, before transmission, the data is encrypted, and after decryption at the receiving end, it is stored.

[0069] Exemplarily, after receiving the data, the cloud server stores the data in a time series database for subsequent data query and analysis. The time series database structure is designed as follows: D store = {t, ID, Location, X fusion (t), X comp (t), I(t)} Where: The timestamp t is used as the primary key for data storage, ID and Location are used as retrieval indexes; X fusion (t) and X comp (t) are the stored data content, I(t) is the image data collected by the high-definition camera device.

[0070] In a possible implementation manner, the cloud server manages data storage through a distributed storage architecture, supporting high-concurrency data read and write operations. When storing data, the system will regularly back up the data to prevent data loss.

[0071] It should be noted that to ensure the traceability of data, the system can add metadata to each stored data record, including the data generation time, transmission path, and processing status, etc. These metadata will be stored together with the data itself for subsequent data management and analysis.

[0072] In some embodiments, after receiving the data, the cloud server can also generate a data reception confirmation feedback and send it back to the edge computing module through a wireless network. Specifically, the confirmation feedback can include the data transmission status, reception time, and data verification result to ensure the closed-loop management of the data transmission process.

[0073] Step S4: Cloud data analysis Cloud data analysis is a key link in realizing the monitoring and prediction of concrete state in the present invention. By deeply analyzing the fused data, compressed data, and image data transmitted by the edge computing module, the law of concrete state change is identified, and a state evaluation report is generated. This step utilizes the powerful data processing ability of the cloud server and combines a deep learning model to perform real-time analysis and prediction on various parameters during the concrete transportation process, thereby achieving precise control of the concrete state and providing basic support for subsequent anomaly detection and action regulation.

[0074] In this embodiment, cloud data analysis mainly includes data reception, feature extraction, state prediction, result generation, etc., and the specific implementation is as follows: It should be noted that the data received by the cloud server includes the sensor fused data X fusion (t), the compressed data X comp (t), the location information, and the image data I(t). These data are high-quality processed data uploaded from the edge computing module, which can ensure the accuracy of data analysis.

[0075] Specifically, first, the cloud analysis module receives and parses the data packets transmitted by the edge computing module, classifies and indexes the data through the timestamp t and the vehicle unique identifier ID to ensure data integrity and timeliness. Exemplarily, the following data set can be formed after data parsing: D cloud ={t,X fusion (t),X comp (t),ID,Location,I(t)} In a possible implementation manner, in order to extract the key features of the concrete state, the cloud server processes the sensor data and image data in the data set respectively: Sensor data feature extraction: Feature extraction is performed on sensor data such as temperature, humidity, and vibration through a time series analysis algorithm. The extracted features include information such as mean, variance, and trend. As an option, the sliding window method is used to calculate the mean of the sensor data: where W is the window size and X k is the sensor data point.

[0076] Image data feature extraction: The image data I(t) collected by the high-definition camera device extracts the spatial features of the concrete image through a convolutional neural network (CNN). Specifically, the input image undergoes multiple convolutional and pooling operations to extract the key features F of the concrete stateCNN : F CNN = σ(W * I + b) where W is the convolutional kernel, * is the convolution operation, b is the bias term, and σ is the activation function.

[0077] Secondly, the cloud analysis module fuses the features extracted from the sensor data and the image data, and inputs them into the Long Short-Term Memory Network (LSTM) to perform time series prediction on the concrete state. The LSTM network can capture the dynamic changes of the concrete state over time, and the specific calculation formula is as follows: h t = tanh(W h h t-1 + W x x t + b h ) Where: h t is the hidden state of the LSTM network, x t is the time series input data; W h and W x are the network weight matrices, is the predicted concrete state value.

[0078] It should be noted that the LSTM network can identify the relationship between parameters such as concrete temperature, humidity, and vibration and the change of concrete state by training the historical concrete data set, so as to accurately predict the concrete state during the current transportation process.

[0079] Exemplarily, the cloud analysis module compares the prediction result output by the LSTM network with the preset state threshold to generate a concrete state evaluation report. The report content includes: The current concrete temperature, humidity, and vibration trends; The concrete state prediction results, including possible risks of stratification, segregation, or solidification; The time nodes and risk levels of state changes.

[0080] In a possible implementation, the cloud server can generate a visualization report according to the analysis result, and display the change law of the concrete state over time in combination with charts and prediction curves. The report content can be automatically pushed to the terminal management module for construction management personnel to view in real time.

[0081] In some embodiments, to further improve the accuracy of the analysis results, the cloud server can dynamically train and optimize the parameters of the deep learning model by combining historical transportation data. Specifically, the system regularly updates the weight matrix of the LSTM network with newly collected data, enabling the model to adapt to the changing laws of the concrete state under different transportation conditions.

[0082] It can be understood that the core of cloud data analysis lies in accurately predicting the concrete state through a deep learning model, identifying potential risks during concrete transportation, and providing decision-making support for subsequent anomaly detection and action regulation through the generation and push of evaluation reports.

[0083] Step S5: Anomaly Detection and Early Warning Response Anomaly detection and early warning response are important links in the intelligent monitoring of the concrete transportation state in this invention. By comparing the concrete state prediction results provided by the cloud data analysis module with the set state thresholds in real time, potential abnormal conditions during transportation are identified, and the early warning mechanism is triggered to notify relevant personnel to take corresponding measures in a timely manner. This step not only ensures the real-time nature of anomaly detection but also improves the pertinence of early warning information and the efficiency of system processing through a hierarchical response mechanism.

[0084] In this embodiment, anomaly detection is based on the prediction results of the cloud analysis module, combined with preset thresholds and multi-level judgment conditions, to identify and trigger early warnings for abnormal states. The specific implementation is as follows: Specifically, first, the concrete state prediction results output by the cloud analysis module serve as the input data for anomaly detection and are compared in real time with the set safety threshold Q threshold The threshold can be preset or dynamically adjusted according to the characteristics of the concrete, transportation conditions, and construction requirements to form an anomaly determination condition: Where: is the predicted concrete state value at the current moment, including parameters such as temperature, humidity, and vibration amplitude; Q threshold is the safety threshold; E = 1 indicates that the abnormal state is triggered.

[0085] It should be noted that anomaly detection is not only for a single parameter but can also be based on an anomaly determination rule that combines multiple parameters. For example, the combined anomaly condition of temperature and vibration amplitude can be expressed as: Where: represents the predicted temperature at the current moment; Tmax is the upper temperature limit; is the predicted vibration amplitude; V threshold is the vibration threshold.

[0086] In a possible implementation, the anomaly detection module can perform hierarchical processing according to the severity of the anomaly. For example, the anomaly levels can be divided into "low-level anomaly", "medium-level anomaly" and "high-level anomaly": Low-level anomaly: A single parameter slightly exceeds the threshold, and the system only records it.

[0087] Medium-level anomaly: Multiple parameters deviate from the threshold simultaneously, and the system triggers an early warning mechanism and sends a notice to the construction person in charge.

[0088] High-level anomaly: The parameter seriously deviates from the threshold or there is a continuous anomaly, and the system triggers an emergency alarm and links to the action execution module for automatic regulation.

[0089] Specifically, once an abnormal state is detected, the system triggers an early warning mechanism through the alarm module and automatically sends early warning information to relevant personnel. As an option, the early warning information can be transmitted in the following multiple ways: SMS notification: Send an early warning SMS to the mobile device of the construction management personnel, and the content includes the anomaly type, time, parameter value and current status.

[0090] Automatic voice call: The system automatically dials the phone number of the construction person in charge and informs the abnormal situation through voice broadcast.

[0091] APP push: Push detailed early warning information and suggested measures through the mobile application of the construction management system.

[0092] Exemplarily, the early warning information includes but is not limited to the following content: The time and location where the anomaly occurs; The specific value of the abnormal parameter and the degree of deviation; The anomaly level and possible impacts; Suggested emergency treatment measures.

[0093] In a possible implementation, the alarm module establishes a linkage mechanism with the construction management terminal. After receiving the confirmation response from the personnel, the system can record the process and result of anomaly handling. It should be noted that while triggering the early warning, the system can also automatically generate an anomaly log to record the detected anomaly data, system response time and early warning sending record, which is convenient for subsequent data analysis and evaluation of the anomaly handling effect.

[0094] In some embodiments, to improve the reliability and timeliness of warning information, the system can send warning information to multiple responsible persons simultaneously through a redundancy mechanism, and continue to send notifications until a feedback confirmation is received in case no response is received.

[0095] It can be understood that anomaly detection and warning response are important technical means in the present invention to ensure the quality and safety of concrete transportation. Through multi-parameter fusion anomaly detection, hierarchical warning, and multi-mode notification mechanisms, a rapid response and handling of abnormal states are effectively achieved.

[0096] Embodiment 2: Please refer to the appendix Figure 2 , a concrete transportation monitoring system, comprising: A data acquisition module, including a temperature sensor, a humidity sensor, a vibration sensor, a light sensor, and a high-definition camera device, for real-time acquisition of concrete state data and transportation environment data; An edge computing module, connected to the data acquisition module, for performing fusion, anomaly detection, and compression processing on the acquired data; a cloud analysis module, connected to the edge computing module, for receiving data and performing concrete state prediction and anomaly analysis based on a deep learning model; An action execution module, connected to the cloud analysis module, for performing actions such as temperature regulation, vibration compensation, and light compensation; an alarm module, connected to the cloud analysis module, for sending alarm notifications in various forms during anomaly detection; A terminal management module, connected to the cloud analysis module and the action execution module, for real-time monitoring, viewing alarm information, and sending remote control instructions.

[0097] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring concrete transportation, characterized in that: The following steps are involved: Step S1: data acquisition, real-time acquisition of concrete state data and environmental data through a data acquisition module, wherein the data acquisition module includes a temperature sensor, a humidity sensor, a vibration sensor, a light sensor and a high-definition camera device; Step S2: Data fusion and preprocessing: the collected data is transmitted to the edge computing module, the data is processed through the multi-sensor data fusion algorithm, and abnormal screening and compression are performed; Step S3: Data transmission and cloud storage, the pre-processed data is transmitted to the cloud server via a wireless network and stored in a time series database; Step S4: Cloud data analysis: Through the cloud analysis module, the state of concrete is predicted in real time based on the deep learning model to generate a state assessment report; Step S5: abnormality detection and early warning response, detecting data abnormalities according to the analysis results and the preset threshold, triggering the alarm module, and sending alarm information to the construction manager; Step S6: Action control, triggering the action execution module to perform temperature control, vibration compensation or light compensation according to the abnormality type; Step S7: Feedback and remote management, feeding back monitoring data, abnormal warning information and action execution results to the terminal management module to achieve data visualization monitoring and remote control.

2. A method for monitoring concrete transportation according to claim 1, characterized in that: The data fusion is implemented by an extended Kalman filter algorithm, which specifically includes: Set the system state equation and observation equation, use Kalman gain to optimize the data fusion, and output the fused state vector.

3. A method for monitoring concrete transportation according to claim 1, characterized in that: The data preprocessing includes: performing multi-sensor data fusion on the temperature, humidity and vibration data, and processing them using an extended Kalman filter algorithm.

4. A method for monitoring concrete transportation according to claim 1, characterized in that: The anomaly detection is achieved through the 3σ,criterion, specifically: Set the data mean μ and standard deviation σ, and judge the data X i Does it satisfy |X i -μ|>3σ.

5. A method for monitoring concrete transportation according to claim 1, characterized in that: The data compression adopts the sliding window average method, and the compressed data calculation formula is: Where W is the sliding window size.

6. A method for monitoring concrete transportation according to claim 1, characterized in that: The action execution module includes: A drip device is used to cool the concrete when the temperature is abnormal; A heating device, used to heat the concrete when the temperature is lower than a set value; A fill light device is used to provide light compensation when the light is insufficient; The vibration control device is used to perform shock absorption compensation when the tank body vibrates too much.

7. A method for monitoring concrete transportation according to claim 1, characterized in that: The alarm module automatically triggers multiple alarm modes according to the abnormality level, including: SMS notification, automatic voice call, APP push and remote contact meeting initiation.

8. A method for monitoring concrete transportation according to claim 1, characterized in that: The terminal management module includes: a real-time monitoring interface for displaying sensor data, image monitoring results and vehicle location information; Alarm information display module, used to view abnormal warning information and solutions; The control instruction module is used to send action control instructions to the action execution module.

9. A method for monitoring concrete transportation according to claim 1, characterized in that: The cloud analysis module dynamically updates model parameters through historical data, so that the deep learning model can achieve adaptive optimization.

10. A concrete transportation monitoring system, according to a concrete transportation monitoring method as claimed in any one of claims 1 to 9, characterized in that: include: Data acquisition module, including temperature sensor, humidity sensor, vibration sensor, light sensor and high-definition camera device, used to collect concrete status data and transportation environment data in real time; An edge computing module, connected to the data acquisition module, for fusing, detecting anomalies and compressing the collected data; A cloud analysis module, connected to the edge computing module, for receiving data and performing concrete state prediction and abnormality analysis based on a deep learning model; An action execution module, connected to the cloud analysis module, for executing actions such as temperature control, vibration compensation, and light compensation; an alarm module, connected to the cloud analysis module, for sending various forms of alarm notifications when an abnormality is detected; The terminal management module is connected to the cloud analysis module and the action execution module, and is used for real-time monitoring, checking alarm information and sending remote control instructions.

Images