Big data basic business management system for canal dredging construction

Abstract

The present invention discloses a big data basic business management system for canal channel dredging construction, which relates to the field of dredging construction data management. The big data basic business management system for canal channel dredging construction includes a data processing module, a data analysis module and a data management module. The present invention solves the problem that the existing technology can only manage the business data in the construction of the suction dredger during actual use, and cannot provide accurate decision-making support for the channel dredging work. The present invention collects and processes various types of data in the channel dredging process in real time, and uses big data analysis methods to conduct in-depth mining and intelligent analysis of the collected data, thereby providing accurate decision-making support for the channel dredging work. In addition, the system also has functions such as remote monitoring and fault warning, which can realize comprehensive and efficient management of the big data basic business of canal channel dredging construction, improve construction efficiency and quality, and reduce construction costs and risks.

Description

Technical Field

[0001] The present invention relates to the technical field of dredging construction data management, and in particular to a big data-based business management system for canal waterway dredging construction. Background Art

[0002] A waterway area refers to a specific area of ​​water or channel that ships need to pass through during navigation. These areas are usually carefully planned and marked to ensure that ships can pass through safely and efficiently. Dredging construction refers to the engineering activities of excavating and removing mud, silt, rocks, and other sediments from rivers, lakes, ports, waterways, and other water bodies through the use of specialized machinery and equipment. Its main purpose is to maintain or increase the depth of the water body, ensure the smooth flow of waterways and the safe navigation of ships, and also help prevent floods, prevent siltation, and improve water quality. Due to the complexity of dredging projects, the resulting data business is relatively complex, affecting the overall business management efficiency and business management experience.

[0003] Chinese patent publication number CN115018358A discloses a big data-based business management system for dredging operations with trailing suction hopper dredgers. The system includes a vessel location service module, a dredging loading analysis module, a dredging overflow analysis module, and a vessel energy consumption analysis module. The vessel location service module manages dredging operation location service data, the dredging loading analysis module manages dredging loading data, the dredging overflow analysis module manages dredging overflow data, and the vessel energy consumption analysis module manages dredging operation energy consumption data. Based on this, through the construction of various business modules, the system meets the business data management needs of dredging operations with trailing suction hopper dredgers, improving overall operation management efficiency and user experience.

[0004] In actual use, the above patent can only manage the business data during the construction of the trailing suction hopper dredger, and cannot provide accurate decision-making support for the waterway dredging work; therefore, it does not meet the existing needs. In response to this, we proposed a big data-based business management system for canal waterway dredging construction. Summary of the Invention

[0005] The purpose of this invention is to provide a big data-based business management system for canal dredging construction. By employing advanced technologies such as cloud computing, the Internet of Things, and machine learning, it collects and processes various types of data from the dredging process in real time. By applying big data analysis methods, it conducts in-depth mining and intelligent analysis of the collected data, providing accurate decision-making support for dredging operations. Furthermore, the system also features remote monitoring and fault warning capabilities, enabling comprehensive and efficient management of the big data-based business of canal dredging construction, improving construction efficiency and quality, and reducing construction costs and risks, thus resolving the issues raised in the aforementioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a big data-based business management system for canal dredging construction, comprising:

[0007] The data processing module is used to collect various data in the waterway dredging process in real time using sensors, and transmit the data collected by the Internet of Things to the cloud computing platform for pre-processing and storage after processing;

[0008] A data analysis module, which uses a cloud computing platform to extract water level, flow velocity, and sediment content data from the dredging construction database. It then uses machine learning algorithms to conduct in-depth analysis of the extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in the dredging construction data.

[0009] The data management module is used to establish a canal dredging construction early warning model, use the canal dredging construction early warning model to output the corresponding navigation warning level information and construction progress and cost forecast results, analyze the operating status of the canal dredging equipment, and perform visual display.

[0010] Preferably, the data processing module includes:

[0011] The data acquisition module is used to use the Internet of Things technology to set sensors at key locations of waterway dredging equipment, ships, and the surrounding environment, and use the sensors to collect various data during the waterway dredging process in real time;

[0012] The data preprocessing module is used to transmit the data collected by the Internet of Things to the cloud computing platform. The cloud computing platform stores, cleans, converts and aggregates the acquired data. After processing, it is stored to establish a dredging construction database.

[0013] Preferably, the data preprocessing module is further used to:

[0014] Real-time recording of the reception time of data information sent by sensors installed at key locations of waterway dredging equipment, ships and surrounding environment;

[0015] Obtaining the data information receiving time interval corresponding to each sensor according to the receiving time corresponding to the data information; wherein the data information receiving time interval refers to the time interval between the sensor sending the data information and the data preprocessing module receiving the data information;

[0016] Extracting the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the reception moment of each data information;

[0017] Obtaining a data transmission stability coefficient corresponding to each sensor according to the data information receiving time interval corresponding to each sensor and the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of each data information;

[0018] The data transmission stability coefficient corresponding to each sensor is obtained by the following formula:

[0019]

[0020] Where Q represents the data transmission stability coefficient corresponding to each sensor; n represents the number of data transmissions corresponding to each sensor; T i represents the time interval for receiving data information of the i-th data transmission corresponding to each sensor; B i T represents the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of the i-th transmission data information corresponding to each sensor; bi represents the standard deviation of the time interval for receiving data information corresponding to the i-th data transmission of each sensor; B bi represents the standard deviation of the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of the i-th transmission data information corresponding to each sensor; T c Indicates the preset time interval reference value; B c Indicates the preset data transmission rate reference value;

[0021] The data transmission stability coefficient corresponding to each sensor is used to determine the stability of the data transmission channel between the sensor and the data preprocessing module.

[0022] Preferably, the stability of the data transmission channel between the sensor and the data preprocessing module is abnormally determined by using the data transmission stability coefficient corresponding to each sensor, including:

[0023] Extract the data transmission stability coefficient corresponding to each sensor;

[0024] Comparing the data transmission stability coefficient corresponding to each sensor with a preset data transmission stability coefficient threshold;

[0025] When the data transmission stability coefficient corresponding to any sensor exceeds the preset data transmission stability coefficient threshold, the data transmission stability coefficient corresponding to each sensor is retrieved in real time after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold;

[0026] Obtaining a comprehensive stability coefficient using the data transmission stability coefficient corresponding to each sensor;

[0027] The comprehensive stability coefficient is obtained by the following formula:

[0028]

[0029] Where W represents the comprehensive stability coefficient; m represents the number of data transmissions corresponding to each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Q j It represents the data transmission stability coefficient corresponding to the j-th data transmission of each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Q c Indicates the data transmission stability coefficient corresponding to exceeding the preset data transmission stability coefficient threshold;

[0030] Comparing the comprehensive stability coefficient with a preset comprehensive coefficient threshold;

[0031] When the comprehensive stability coefficient exceeds a preset comprehensive coefficient threshold, it is determined that there is an abnormality in the stability of the data transmission channel between the sensor and the data preprocessing module, and an abnormality alarm is issued.

[0032] Preferably, the data preprocessing module includes:

[0033] Data cleaning: Use deletion, filling, and interpolation methods to handle missing values ​​in the acquired data; identify and process abnormal data through statistical analysis; identify duplicate data by comparing key fields and delete or merge them;

[0034] Data conversion and aggregation: The cleaned data is converted into a unified format, and then the converted data is fused through merging, cropping, denoising, and data thinning. During the data fusion process, data from multiple measurements are superimposed.

[0035] Data storage: Build a big data storage platform on the cloud computing platform and use the big data storage platform to store the processed data.

[0036] Preferably, the data analysis module includes:

[0037] Data extraction module, used to extract water level, flow rate and sediment content data from the dredging construction database;

[0038] The data recognition module, combined with machine learning algorithms, conducts in-depth analysis of extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in dredging construction data.

[0039] Preferably, the in-depth analysis of the extracted water level, flow velocity and sediment content data using a machine learning algorithm specifically includes:

[0040] Use statistical methods to analyze linear or nonlinear relationships between water level, flow velocity, and sediment content data;

[0041] Use time series analysis to obtain the temporal trends of water level, flow velocity and sediment content data and their dynamic relationships;

[0042] A multiple regression model was established, with water level and flow velocity as independent variables and sediment content as dependent variable, to analyze the influence of independent variables on dependent variables.

[0043] Preferably, the data management module includes:

[0044] The model building module is used to train an initial bidirectional LSTM network model using patterns, trends, outliers, and historical warning labels in historical dredging construction data, and perform parameter adjustment, algorithm optimization, and verification to obtain a canal dredging construction warning model;

[0045] The early warning module is used to optimize the dredging construction process based on the output of the canal dredging construction early warning model and issue corresponding early warning signals according to the early warning level;

[0046] Real-time monitoring module, used to monitor the operating parameters of the waterway dredging equipment collected by sensors in real time and analyze the operating status of the waterway dredging equipment;

[0047] The visualization module is used to visualize the analysis and warning results in the form of charts and reports.

[0048] Preferably, the model building module specifically includes:

[0049] Collect patterns, trends and outliers in historical dredging data and obtain historical warning levels for the waterway in the assessment results;

[0050] Based on the evaluation results of historical dredging projects, corresponding warning labels are established for historical dredging data;

[0051] Select a bidirectional LSTM network model, divide the historical dredging data and warning labels into a training set and a validation set, and use the training set to train the initial bidirectional LSTM network model;

[0052] Adjust the parameters of the initial bidirectional LSTM network model and optimize the algorithm based on the training results;

[0053] After the adjustment is completed, the initial bidirectional LSTM network model is verified using the validation set to obtain the canal dredging construction early warning model;

[0054] Input patterns, trends, and outliers from current dredging construction data into a canal channel dredging construction early warning model;

[0055] The canal dredging construction warning model outputs the corresponding navigation warning level information as well as the construction progress and cost forecast results.

[0056] Preferably, the real-time monitoring module includes:

[0057] Set parameter warning thresholds for normal operation of waterway dredging equipment;

[0058] Using sensors on the waterway dredging equipment to collect operating parameters of the waterway dredging equipment in real time, and analyzing the operating parameters collected in real time;

[0059] If the operating parameters of the waterway equipment exceed the set warning threshold, it is determined that there is a fault in the waterway dredging equipment and a maintenance signal is issued;

[0060] If the operating parameters of the channel dredging equipment are close to the warning threshold, it is judged that there is a possibility of failure of the channel dredging equipment, and a failure warning is issued;

[0061] If the operating parameters of the waterway dredging equipment are normal, it means that the operating status of the waterway dredging equipment is normal and no early warning is issued.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] This system leverages advanced technologies such as cloud computing, the Internet of Things, and machine learning to collect and process various data from the waterway dredging process in real time. By applying big data analytics, it conducts in-depth mining and intelligent analysis of this data, providing accurate decision-making support for waterway dredging operations. Furthermore, the system also includes remote monitoring and fault warning capabilities, enabling comprehensive and efficient management of the big data-based operations of canal dredging construction, improving construction efficiency and quality while reducing costs and risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a schematic diagram of the canal dredging construction big data basic business management system module of the present invention;

[0065] Figure 2 This is a workflow diagram of the canal waterway dredging construction big data basic business management system of the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] In order to solve the problem that the existing technology can only manage the business data of the trailing suction hopper dredger in actual use, but cannot provide accurate decision support for the channel dredging work, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0068] The big data basic business management system for canal dredging construction includes:

[0069] The data processing module is used to collect various data in the waterway dredging process in real time using sensors, and transmit the data collected by the Internet of Things to the cloud computing platform for pre-processing and storage after processing;

[0070] A data analysis module, which uses a cloud computing platform to extract water level, flow velocity, and sediment content data from the dredging construction database. It then uses machine learning algorithms to conduct in-depth analysis of the extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in the dredging construction data.

[0071] The data management module is used to establish a canal dredging construction early warning model, use the canal dredging construction early warning model to output the corresponding navigation warning level information and construction progress and cost forecast results, analyze the operating status of the canal dredging equipment, and perform visual display.

[0072] Data processing module, including:

[0073] The data acquisition module is used to use IoT technology to set up sensors at key locations of waterway dredging equipment, ships, and the surrounding environment. The sensors collect various data during the waterway dredging process in real time, such as equipment operating status, water level, flow rate, soil quality, and ship location.

[0074] The data preprocessing module is used to transmit the data collected by the Internet of Things to the cloud computing platform. The cloud computing platform stores, cleans, converts and aggregates the acquired data. After processing, it is stored and a dredging construction database is established. The elasticity and scalability of cloud computing ensure that resources can be dynamically adjusted according to changes in data volume to meet the needs of real-time processing.

[0075] Data preprocessing module, including:

[0076] Data cleaning: Use deletion, filling, and interpolation methods to handle missing values ​​in the acquired data; identify and process abnormal data through statistical analysis; identify duplicate data by comparing key fields and delete or merge them;

[0077] Data conversion and aggregation: The cleaned data is converted into a unified format, and then the converted data is fused through merging, cropping, denoising, and data thinning. During the data fusion process, data from multiple measurements are superimposed to analyze changes in the waterway at different time points.

[0078] Data storage: Build a big data storage platform on the cloud computing platform and use the big data storage platform to store the processed data.

[0079] The system leverages advanced technologies such as cloud computing, the Internet of Things, and machine learning to collect and process various data from the waterway dredging process in real time, including water levels, flow rates, and sediment content. By applying big data analytics, it conducts in-depth mining and intelligent analysis of this collected data, providing accurate decision-making support for waterway dredging operations. Furthermore, the system includes remote monitoring and fault warning capabilities to reduce dredging risks and improve construction efficiency.

[0080] On the cloud computing platform, machine learning algorithms are used to analyze pre-processed data. Machine learning can identify patterns, trends and anomalies in the data, and provide real-time decision support for the channel dredging process. Through continuous learning and optimization, the machine learning model can gradually improve the accuracy and efficiency of the analysis. Through real-time data collection through Internet of Things technology, data storage and processing on the cloud computing platform, machine learning technology analysis and optimization, as well as visual monitoring and command input, it is possible to achieve real-time collection and processing of various types of data in the channel dredging process, providing strong support for the intelligent and efficient channel dredging.

[0081] Specifically, the data preprocessing module is further used to:

[0082] Real-time recording of the reception time of data information sent by sensors installed at key locations of waterway dredging equipment, ships and surrounding environment;

[0083] Obtaining the data information receiving time interval corresponding to each sensor according to the receiving time corresponding to the data information; wherein the data information receiving time interval refers to the time interval between the sensor sending the data information and the data preprocessing module receiving the data information;

[0084] Extracting the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the reception moment of each data information;

[0085] Obtaining a data transmission stability coefficient corresponding to each sensor according to the data information receiving time interval corresponding to each sensor and the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of each data information;

[0086] The data transmission stability coefficient corresponding to each sensor is obtained by the following formula:

[0087]

[0088] Where Q represents the data transmission stability coefficient corresponding to each sensor; n represents the number of data transmissions corresponding to each sensor; T i represents the time interval for receiving data information of the i-th data transmission corresponding to each sensor; B i T represents the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of the i-th transmission data information corresponding to each sensor; bi represents the standard deviation of the time interval for receiving data information corresponding to the i-th data transmission of each sensor; B bi represents the standard deviation of the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of the i-th transmission data information corresponding to each sensor; T c Indicates the preset time interval reference value; B c Indicates the preset data transmission rate reference value;

[0089] The data transmission stability coefficient corresponding to each sensor is used to determine the stability of the data transmission channel between the sensor and the data preprocessing module.

[0090] The technical solution described above provides the following technical benefits: By recording the real-time reception times of data sent by sensors located at key locations on waterway dredging equipment, vessels, and the surrounding environment, it ensures real-time monitoring of key parameters during dredging operations. This real-time performance is crucial for waterway maintenance, vessel safety, and environmental monitoring, enabling timely identification and resolution of potential issues. By calculating the data reception interval corresponding to each sensor, the solution quantitatively assesses data transmission efficiency. Shorter intervals indicate faster data transmission, which is particularly important for monitoring systems that require real-time response. By extracting the data transmission rate of the data transmission channel between the sensor and the data preprocessing module at the time of each data reception, the channel's performance can be further analyzed. Data transmission rate is a key indicator of channel quality and directly impacts the stability and efficiency of data transmission. By introducing a data transmission stability coefficient, Q, the solution comprehensively considers the data reception interval, data transmission rate, and their standard deviation, as well as preset reference values ​​for the interval and data transmission rate, to quantitatively assess the stability of the data transmission channel between the sensor and the data preprocessing module. This coefficient accurately reflects data transmission stability and, by comparing it with a preset threshold, enables detection of abnormalities in data transmission channel stability. This is crucial for promptly identifying and resolving data transmission issues and ensuring data integrity and accuracy. By continuously monitoring and evaluating data transmission stability and efficiency, bottlenecks and issues can be identified, enabling appropriate optimization measures to be taken, ultimately improving the performance and reliability of the entire monitoring system.

[0091] In summary, this technical solution achieves comprehensive monitoring and evaluation of the stability and efficiency of data transmission channels in waterway dredging operations by real-time recording and analyzing the reception time of sensor data information, calculating the data information reception time interval, extracting the data transmission rate, and calculating the data transmission stability coefficient, providing strong support for optimizing system performance and ensuring data accuracy and timeliness.

[0092] Specifically, the stability of the data transmission channel between the sensor and the data preprocessing module is judged as abnormal by using the data transmission stability coefficient corresponding to each sensor, including:

[0093] Extract the data transmission stability coefficient corresponding to each sensor;

[0094] Comparing the data transmission stability coefficient corresponding to each sensor with a preset data transmission stability coefficient threshold;

[0095] When the data transmission stability coefficient corresponding to any sensor exceeds the preset data transmission stability coefficient threshold, the data transmission stability coefficient corresponding to each sensor is retrieved in real time after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold;

[0096] Obtaining a comprehensive stability coefficient using the data transmission stability coefficient corresponding to each sensor;

[0097] The comprehensive stability coefficient is obtained by the following formula:

[0098]

[0099] Where W represents the comprehensive stability coefficient; m represents the number of data transmissions corresponding to each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Q j It represents the data transmission stability coefficient corresponding to the j-th data transmission of each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Q c Indicates the data transmission stability coefficient corresponding to exceeding the preset data transmission stability coefficient threshold;

[0100] Comparing the comprehensive stability coefficient with a preset comprehensive coefficient threshold;

[0101] When the comprehensive stability coefficient exceeds a preset comprehensive coefficient threshold, it is determined that there is an abnormality in the stability of the data transmission channel between the sensor and the data preprocessing module, and an abnormality alarm is issued.

[0102] The technical effect of the above technical solution is that by extracting the data transmission stability coefficient corresponding to each sensor and comparing it with a preset data transmission stability coefficient threshold, this technical solution can promptly identify potential stability issues in the data transmission channel. Once the data transmission stability coefficient of any sensor exceeds the preset threshold, the system enters a real-time monitoring state, retrieving and analyzing the data transmission stability coefficient of each sensor in real time. This enables rapid response and early warning of data transmission channel anomalies. After the data transmission stability coefficient exceeds the preset threshold, by introducing a comprehensive stability coefficient W, this technical solution comprehensively considers the data transmission stability performance of all sensors, providing a global stability assessment indicator for the system. This comprehensive assessment method helps system administrators gain a more comprehensive understanding of the overall stability of the data transmission channel, providing a strong basis for decision support. By monitoring and assessing the stability of the data transmission channel in real time, this technical solution can promptly identify and resolve potential data transmission issues, thereby avoiding data loss, delays, or errors. This is crucial for improving the reliability and stability of the entire monitoring system and helping ensure the safe and smooth progress of waterway dredging operations. Through preset thresholds and an automatic determination mechanism, this technical solution achieves automated and intelligent data transmission channel stability determination. This significantly reduces the cost and workload of manual monitoring and determination, and improves the system's operational efficiency and accuracy. The comprehensive stability coefficient calculation formula and preset thresholds in the technical solution can be adjusted and optimized based on actual needs to adapt to the data transmission channel stability assessment requirements in different scenarios and conditions. This flexibility and scalability enable the technical solution to be widely applied in various monitoring systems to meet the actual needs of different fields.

[0103] In summary, this technical solution realizes real-time monitoring and abnormality judgment of the stability of the data transmission channel between the sensor and the data preprocessing module by introducing the data transmission stability coefficient and the comprehensive stability coefficient, thereby improving the reliability and stability of the system, reducing the cost of manual monitoring, and improving the level of automation and intelligence.

[0104] Data analysis modules, including:

[0105] The data extraction module is used to extract water level, flow rate and sediment content data from the dredging construction database using the cloud computing platform;

[0106] The data recognition module uses machine learning algorithms to conduct in-depth analysis of extracted water level, flow rate, and sediment content data, identifying patterns, trends, and outliers in dredging construction data, providing a scientific basis and decision support for dredging construction. For example, machine learning can be used to predict water level trends or analyze the relationship between sediment content and flow rate to optimize dredging construction plans.

[0107] By collecting data through Internet of Things technology, processing and storing data through cloud computing technology, and analyzing data through machine learning technology, a comprehensive and in-depth analysis of water levels, flow rates, and sediment content in dredging construction data can be achieved, providing strong support for the optimization and decision-making of dredging construction. Cluster analysis can be performed on the usage data of mechanical equipment to identify equipment usage patterns in different construction stages, or association rule mining can be performed on silt volume and construction progress data to discover the potential relationship between them.

[0108] In-depth analysis of the extracted water level, flow velocity, and sediment content data using machine learning algorithms includes:

[0109] Use statistical methods to analyze the linear or nonlinear relationships between water level, flow velocity, and sediment content data to determine which variables have significant correlations;

[0110] Use time series analysis to obtain the temporal trends of water level, flow velocity and sediment content data and their dynamic relationships;

[0111] A multiple regression model was established, with water level and flow velocity as independent variables and sediment content as dependent variable, to analyze the influence of independent variables on dependent variables.

[0112] Data management module, including:

[0113] The model building module is used to train an initial bidirectional LSTM network model using patterns, trends, outliers, and historical warning labels in historical dredging construction data, and perform parameter adjustment, algorithm optimization, and verification to obtain a canal dredging construction warning model. The canal dredging construction warning model outputs corresponding navigation warning level information as well as construction progress and cost forecast results, thereby optimizing construction planning, resource allocation, and progress control to improve construction efficiency and quality.

[0114] The early warning module is used to optimize the dredging construction process based on the output of the canal dredging construction early warning model and issue corresponding early warning signals according to the early warning level;

[0115] Real-time monitoring module, used to monitor the operating parameters of the waterway dredging equipment collected by sensors in real time and analyze the operating status of the waterway dredging equipment;

[0116] The visualization module is used to visualize the analysis and warning results in the form of charts and reports, which can clearly show the changing trends of key indicators and potential problems in the construction process.

[0117] Model building modules, including:

[0118] Collect patterns, trends and outliers in historical dredging data and obtain historical warning levels for the waterway in the assessment results;

[0119] Based on the evaluation results of historical dredging projects, corresponding warning labels should be established for historical dredging data. These labels should correspond one-to-one with the historical warning levels of the waterway.

[0120] A bidirectional LSTM network model was selected. The historical dredging data and warning labels were divided into a training set and a validation set. The training set was used to train the initial bidirectional LSTM network model. The initial bidirectional LSTM network model included a bidirectional long short-term memory neural network Bi-LSTM layer for extracting time series features, a dropout layer to prevent network overfitting, a fully connected layer (dense layer) for classification, and an activation layer for performing activation function operations.

[0121] Adjust the parameters of the initial bidirectional LSTM network model and optimize the algorithm based on the training results. By adjusting the model parameters and optimizing the algorithm, the prediction accuracy of the model is improved.

[0122] After the adjustment was completed, the initial bidirectional LSTM network model was verified using the validation set to obtain a canal dredging construction early warning model to ensure the model's stability and accuracy in different scenarios.

[0123] Input patterns, trends, and outliers from current dredging construction data into a canal channel dredging construction early warning model;

[0124] The canal dredging construction warning model outputs corresponding navigation warning level information as well as construction progress and cost forecast results, providing real-time warnings to waterway managers and ship drivers;

[0125] The canal dredging construction early warning model can be used to predict and warn of abnormal situations or potential risks that may occur during the construction process. For example, risks such as equipment failure and construction delays can be predicted, and countermeasures can be taken in advance. Combined with the real-time computing capabilities of cloud computing, early warning information and decision-making recommendations can be pushed to relevant personnel in a timely manner to support them in making quick and accurate decisions. This can achieve comprehensive and efficient management of the basic big data business of canal dredging construction, improve construction efficiency and quality, and reduce construction costs and risks.

[0126] Real-time monitoring module, including:

[0127] Set parameter warning thresholds for normal operation of waterway dredging equipment;

[0128] Using sensors on the waterway dredging equipment to collect operating parameters of the waterway dredging equipment in real time, and analyzing the operating parameters collected in real time;

[0129] If the operating parameters of the waterway equipment exceed the set warning threshold, it is determined that there is a fault in the waterway dredging equipment and a maintenance signal is issued;

[0130] If the operating parameters of the channel dredging equipment are close to the warning threshold, it is judged that there is a possibility of failure of the channel dredging equipment, and a failure warning is issued;

[0131] If the operating parameters of the waterway dredging equipment are normal, it means that the operating status of the waterway dredging equipment is normal and no warning is issued;

[0132] Cloud computing platforms can dynamically allocate computing and storage resources based on actual demand, ensuring efficient processing of large amounts of data during peak data periods and reducing resource usage and costs during low data periods. Data from canal dredging construction is crucial for construction decision-making and progress monitoring. Cloud computing platforms typically have multiple data centers and backup mechanisms to ensure data storage space and disaster recovery, reducing the risk of data loss and system interruptions, thereby improving business continuity. Canal dredging construction involves complex computing tasks such as construction simulation and optimization plan formulation. Cloud computing platforms provide powerful computing power and can efficiently handle these tasks. Through cloud computing platforms, large-scale data analysis and simulation can be quickly performed to optimize construction decisions and plans, improve construction efficiency, and reduce costs. Combining big data technology with the real-time data processing capabilities of cloud computing, by collecting and processing various types of data during canal dredging construction, such as sensor data and equipment operating status data, real-time monitoring and early warning of the construction process can be achieved, helping to promptly identify potential problems and take appropriate countermeasures to ensure construction safety and progress.

[0133] The workflow of the big data-based business management system for canal dredging construction includes the following steps:

[0134] Step 1: Use IoT technology to install sensors at key locations of waterway dredging equipment, ships, and the surrounding environment, and use the sensors to collect various data during the dredging process in real time;

[0135] Step 2: The data collected by the Internet of Things is transmitted to the cloud computing platform. The cloud computing platform stores, cleans, converts and aggregates the acquired data. After processing, it is stored and a dredging construction database is established.

[0136] Step 3: Extract water level, flow velocity, and sediment content data from the dredging construction database and use machine learning algorithms to conduct in-depth analysis of the extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in the dredging construction data.

[0137] Step 4: Collect patterns, trends, and outliers from historical dredging construction data, and obtain the historical warning levels of the waterway from the evaluation results. Based on the evaluation results of historical dredging projects, establish corresponding warning labels for the historical dredging data;

[0138] Step 5: Select a bidirectional LSTM network model, divide the historical dredging data and warning labels into a training set and a validation set, use the training set to train the initial bidirectional LSTM network model, adjust the parameters of the initial bidirectional LSTM network model and optimize the algorithm based on the training results, and after the adjustment is completed, use the validation set to verify the initial bidirectional LSTM network model to obtain the canal dredging construction warning model;

[0139] Step 6: Input the patterns, trends, and outliers in the current dredging construction data into the canal dredging construction early warning model, which outputs the corresponding navigation warning level information as well as construction progress and cost forecast results;

[0140] Step 7: Use sensors to collect the operating parameters of the waterway dredging equipment in real time, analyze the operating parameters of the waterway dredging equipment collected in real time, judge the operating status of the waterway dredging equipment based on the analysis results, and issue corresponding warnings based on the operating status.

[0141] In summary, the canal channel dredging construction big data basic business management system of the present invention utilizes the elastic computing of cloud computing to process the canal channel dredging construction big data, which can realize dynamic management, efficient processing and real-time monitoring of data, and provide strong support for construction decision-making and scheme optimization. It can realize comprehensive and efficient management of the canal channel dredging construction big data basic business, improve construction efficiency and quality, reduce construction costs and risks, and adopt cloud computing, Internet of Things, machine learning and other advanced technologies to collect and process various types of data in the channel dredging process in real time. By using big data analysis methods, the collected data is deeply mined and intelligently analyzed to provide accurate decision-making support for channel dredging work. In addition, the system also has functions such as remote monitoring and fault warning to reduce the risks of dredging work and improve construction efficiency. On the cloud computing platform, machine learning algorithms are used to analyze pre-processed data. Machine learning can identify patterns, trends and anomalies in the data and provide real-time decision support for the waterway dredging process. Through continuous learning and optimization, the machine learning model can gradually improve the accuracy and efficiency of analysis. Through real-time data collection through Internet of Things technology, data storage and processing on the cloud computing platform, machine learning technology analysis and optimization, as well as visual monitoring and command input, it can realize real-time collection and processing of various types of data in the waterway dredging process, providing strong support for the intelligent and efficient waterway dredging.

[0142] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0143] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The big data basic business management system for canal dredging construction is characterized by: include: The data processing module is used to collect various data in the waterway dredging process in real time using sensors, and transmit the data collected by the Internet of Things to the cloud computing platform for pre-processing and storage after processing; The data processing module includes: The data acquisition module is used to use the Internet of Things technology to set sensors at key locations of waterway dredging equipment, ships, and the surrounding environment, and use the sensors to collect various data during the waterway dredging process in real time; The data pre-processing module is used to transmit the data collected by the Internet of Things to the cloud computing platform. The cloud computing platform stores, cleans, converts and aggregates the acquired data. After processing, it is stored and a dredging construction database is established. The data preprocessing module is further used to: Real-time recording of the reception time of data information sent by sensors installed at key locations of waterway dredging equipment, ships and surrounding environment; Obtaining the data information receiving time interval corresponding to each sensor according to the receiving time corresponding to the data information; wherein the data information receiving time interval refers to the time interval between the sensor sending the data information and the data preprocessing module receiving the data information; Extracting the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the reception moment of each data information; Obtaining a data transmission stability coefficient corresponding to each sensor according to the data information receiving time interval corresponding to each sensor and the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the receiving moment of each data information; The data transmission stability coefficient corresponding to each sensor is obtained by the following formula: ； Wherein, Q represents the data transmission stability coefficient corresponding to each sensor; n represents the number of data transmissions corresponding to each sensor; Ti represents the time interval for receiving data information for the i-th data transmission corresponding to each sensor; Bi represents the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the reception moment of the i-th data transmission corresponding to each sensor; Tbi represents the standard deviation of the time interval for receiving data information corresponding to the i-th data transmission corresponding to each sensor; Bbi represents the standard deviation of the data transmission rate of the data transmission channel between the sensor and the data preprocessing module corresponding to the reception moment of the i-th data transmission corresponding to each sensor; Tc represents the preset time interval reference value; Bc represents the preset data transmission rate reference value; The data transmission stability coefficient corresponding to each sensor is used to determine the stability of the data transmission channel between the sensor and the data preprocessing module. Specifically, the following are performed: Extract the data transmission stability coefficient corresponding to each sensor; Comparing the data transmission stability coefficient corresponding to each sensor with a preset data transmission stability coefficient threshold; When the data transmission stability coefficient corresponding to any sensor exceeds the preset data transmission stability coefficient threshold, the data transmission stability coefficient corresponding to each sensor is retrieved in real time after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Obtaining a comprehensive stability coefficient using the data transmission stability coefficient corresponding to each sensor; The comprehensive stability coefficient is obtained by the following formula: ； Wherein, W represents the comprehensive stability coefficient; m represents the number of data transmissions corresponding to each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Qj represents the data transmission stability coefficient corresponding to the j-th data transmission of each sensor after the data transmission stability coefficient exceeds the preset data transmission stability coefficient threshold; Qc represents the data transmission stability coefficient corresponding to exceeding the preset data transmission stability coefficient threshold; Comparing the comprehensive stability coefficient with a preset comprehensive coefficient threshold; When the comprehensive stability coefficient exceeds a preset comprehensive coefficient threshold, it is determined that there is an abnormality in the stability of the data transmission channel between the sensor and the data preprocessing module, and an abnormality alarm is issued; A data analysis module, which uses a cloud computing platform to extract water level, flow velocity, and sediment content data from the dredging construction database. It then uses machine learning algorithms to conduct in-depth analysis of the extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in the dredging construction data. The data management module is used to establish a canal dredging construction early warning model, use the canal dredging construction early warning model to output the corresponding navigation warning level information and construction progress and cost forecast results, analyze the operating status of the canal dredging equipment, and perform visual display.

2. The big data-based business management system for canal dredging construction according to claim 1 is characterized by: The data preprocessing module includes: Data cleaning: Use deletion, filling, and interpolation methods to handle missing values ​​in the acquired data; identify and process abnormal data through statistical analysis; identify duplicate data by comparing key fields and delete or merge them; Data conversion and aggregation: The cleaned data is converted into a unified format, and then the converted data is fused through merging, cropping, denoising, and data thinning. During the data fusion process, data from multiple measurements are superimposed. Data storage: Build a big data storage platform on the cloud computing platform and use the big data storage platform to store the processed data.

3. The big data-based business management system for canal dredging construction according to claim 1 is characterized by: The data analysis module includes: Data extraction module, used to extract water level, flow rate and sediment content data from the dredging construction database; The data recognition module, combined with machine learning algorithms, conducts in-depth analysis of extracted water level, flow velocity, and sediment content data to identify patterns, trends, and outliers in dredging construction data.

4. The big data-based business management system for canal dredging construction according to claim 3 is characterized by: The machine learning algorithm is used to conduct in-depth analysis of the extracted water level, flow rate, and sediment content data, including: Use statistical methods to analyze linear or nonlinear relationships between water level, flow velocity, and sediment content data; Use time series analysis to obtain the temporal trends of water level, flow velocity and sediment content data and their dynamic relationships; A multiple regression model was established, with water level and flow velocity as independent variables and sediment content as dependent variable, to analyze the influence of independent variables on dependent variables.

5. The big data-based business management system for canal dredging construction according to claim 1 is characterized by: The data management module includes: The model building module is used to train an initial bidirectional LSTM network model using patterns, trends, outliers, and historical warning labels in historical dredging construction data, and perform parameter adjustment, algorithm optimization, and verification to obtain a canal dredging construction warning model; The early warning module is used to optimize the dredging construction process based on the output of the canal dredging construction early warning model and issue corresponding early warning signals according to the early warning level; Real-time monitoring module, used to monitor the operating parameters of the waterway dredging equipment collected by sensors in real time and analyze the operating status of the waterway dredging equipment; The visualization module is used to visualize the analysis and warning results in the form of charts and reports.

6. The big data-based business management system for canal dredging construction according to claim 5 is characterized by: The model building module specifically includes: Collect patterns, trends and outliers in historical dredging data and obtain historical warning levels for the waterway in the assessment results; Based on the evaluation results of historical dredging projects, corresponding warning labels are established for historical dredging data; Select a bidirectional LSTM network model, divide the historical dredging data and warning labels into a training set and a validation set, and use the training set to train the initial bidirectional LSTM network model; Adjust the parameters of the initial bidirectional LSTM network model and optimize the algorithm based on the training results; After the adjustment is completed, the initial bidirectional LSTM network model is verified using the validation set to obtain the canal dredging construction early warning model; Input patterns, trends, and outliers from current dredging construction data into a canal channel dredging construction early warning model; The canal dredging construction warning model outputs the corresponding navigation warning level information as well as the construction progress and cost forecast results.

7. The big data-based business management system for canal dredging construction according to claim 5 is characterized by: The real-time monitoring module includes: Setting parameter warning thresholds for normal operation of waterway dredging equipment; Using sensors on the waterway dredging equipment to collect operating parameters of the waterway dredging equipment in real time, and analyzing the operating parameters collected in real time; If the operating parameters of the waterway equipment exceed the set warning threshold, it is determined that there is a fault in the waterway dredging equipment and a maintenance signal is issued; If the operating parameters of the channel dredging equipment are close to the warning threshold, it is judged that there is a possibility of failure of the channel dredging equipment, and a failure warning is issued; If the operating parameters of the waterway dredging equipment are normal, it means that the operating status of the waterway dredging equipment is normal and no early warning is issued.

Images