Article laying ship operation intelligent control method and system based on Internet of ships

Abstract

The invention discloses a geotextile laying ship operation intelligent control method and system based on the Internet of ships, and belongs to the technical field of ship engineering, and the method comprises the following steps: S1, collecting geotextile laying ship operation real-time data based on the Internet of ships through employing the Internet of Things technology; s2, processing and analyzing the geotextile laying ship operation real-time data based on the Internet of ships, timely discovering potential safety hazards and problems, and determining a geotextile laying ship operation risk prediction result; and S3, according to the operation risk prediction result of the geotextile laying ship, intelligent real-time adjustment and control are performed on the ship, so that the ship is always kept in a safe range in the geotextile laying process. The problem that intelligent control over ship laying operation cannot be effectively achieved in the prior art is solved. The system can achieve the functions of real-time monitoring, remote control, automatic control and the like, can improve the safety and efficiency of a ship in the arrangement process, can reduce the risk of manual operation errors, improves the accuracy and safety of arrangement work, and reduces the operation cost.

Description

Technical Field

[0001] The present invention relates to the technical field of ship engineering, and in particular to an intelligent control method and system for laying ship operations based on ship networking. Background Art

[0002] The raft laying ship, also known as the raft sinking ship, is designed to meet the engineering needs for soft foundation riverbed structures in the Yangtze River and coastal waterway regulation, combined with the laying construction of soft rafts for slope protection and bottom protection in the Yangtze River waters. When the ship is operating at sea, it is necessary to observe and monitor the water environment around the hull to ensure navigation safety.

[0003] The Chinese patent with publication number CN108279598A discloses a monitoring and protection system for laying anchor cables and a protection method thereof, including a photoelectric switch for detecting cable laying devices and cables, etc. The anchor cable equipment monitoring and early warning protection system can assist in ship positioning, avoid major accidents of anchor cable equipment, save a lot of manpower and material costs, and avoid the impact of equipment failure on construction progress and efficiency; however, the patent has the following defects: When existing ships are performing laying operations, they usually need to control the position and speed of the ship through manual operation. This operation method has many problems and risks. For example, improper operation may cause accidents such as loss of control and collision of the ship. It will also waste a lot of manpower, material resources and time resources, and cannot effectively realize the intelligent control of ship laying operations. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent control method and system for laying ship operations based on ship networking, which can realize functions such as real-time monitoring, remote control and automatic control, improve the safety and efficiency of the ship during the laying process, reduce the risk of human operating errors, improve the accuracy and safety of laying work, reduce operating costs, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The intelligent control method for laying ship operation based on ship networking includes the following steps: S1: Use IoT technology to collect ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform based on the wireless communication technology; S2: Process and analyze the real-time data of the laying ship operation based on the ship networking through the cloud computing platform, and make risk predictions on the real-time data of the laying ship operation based on deep learning technology, so as to timely discover potential safety hazards and problems and determine the risk prediction results of the laying ship operation; S3: Based on the risk prediction results of the laying ship operation, the ship's operating position R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Intelligent real-time adjustment and control are carried out to ensure that the ship is always kept within a safe range during the deployment process and to respond to emergencies in a timely manner.

[0006] Preferably, in S1, real-time data of laying ship operations based on ship networking is collected, and the following operations are performed: Based on the Internet of Things technology, sensors are used to monitor the operating position of the laying ship during operation. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct real-time monitoring and collection to obtain ship operation status data ship sta-data ; Based on the Internet of Things technology, sensors are used to monitor the wind speed during the laying ship operation. W sp , high waves W hei , water flow speed W vel , water temperature W tem and weather conditions M phe Conduct real-time monitoring and collection to obtain ship operating environment data ship env-data ; Based on the Internet of Things technology, sensors are used to monitor the operating status of the laying equipment on the shore R sta , Fault information F inf And load conditions L sit Conduct real-time monitoring and collection to obtain laying equipment status data Laysta-data ; Among them, based on the ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of laying ship operations based on ship networking.

[0007] Preferably, in said S1, the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform, and the following operations are performed: The bandwidth of the communication channel corresponding to the cloud computing platform during initial operation is set to be lower than the rated bandwidth of the communication channel; Real-time monitoring of the data volume corresponding to each laying ship operation real-time data transmission; Extract the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions; Compare the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions with a preset data volume increase rate threshold; When the data volume increase rate exceeds the preset data volume increase rate threshold, the data volume corresponding to each real-time data transmission of the laying ship operation is retrieved; Using the data volume corresponding to the real-time data transmission of each laying ship operation, a predicted value of the data volume corresponding to the data transmission is obtained; The data volume prediction value is obtained by the following formula:

[0008] Among them, S represents the predicted value of data volume; C max Indicates the maximum amount of data corresponding to real-time data transmission; C f represents the data transmission volume variance corresponding to the real-time data transmission of the laying ship operation; C p Represents the average data volume corresponding to real-time data transmission; G p G represents the average time interval corresponding to the real-time data transmission of the laying ship operation; max represents the maximum time interval corresponding to the real-time data transmission of the laying ship operation; g represents the variance of the time interval corresponding to the real-time data transmission of the laying ship operation; C t represents the data transmission volume of other data during the real-time data transmission of the laying ship operation; r represents the variance corresponding to the comprehensive data transmission time interval of other data except the real-time data of the laying ship operation; f p Indicates the comprehensive data transmission frequency of other data except the real-time data of laying ship operation; f c Indicates the data transmission frequency of real-time data of laying vessel operation; The reserved bandwidth is set for the cloud computing platform according to the data volume prediction value.

[0009] Preferably, the reserved bandwidth setting of the cloud computing platform is performed according to the data volume prediction value, and the following operations are performed: Extracting the data volume prediction value; Obtaining an estimated load of a communication channel corresponding to the cloud computing platform using the data volume prediction value; The estimated load is obtained by the following formula:

[0010] Where L represents the expected load; L0 represents the actual load of the current communication channel; C b represents the standard deviation of the data volume corresponding to real-time data transmission; C tb It represents the standard deviation of the data transmission volume of other data during the real-time data transmission of the laying ship operation; C tp represents the average data volume of other data during the real-time data transmission of the laying ship operation; S represents the predicted value of the data volume; C e Indicates the rated bandwidth of the communication channel; comparing the predicted load with a preset load reference value; When the predicted load exceeds a preset load reference value, the predicted load is used to set a reserved bandwidth; The reserved bandwidth is obtained by the following formula:

[0011] Where B represents the reserved bandwidth; B c represents the preset reserved bandwidth base value; P represents the actual bandwidth utilization of the current communication channel; L represents the expected load; L y represents a preset load reference value; λ represents a preset sensitivity coefficient of bandwidth adjustment, and the sensitivity coefficient is obtained by experiment according to actual application requirements; The bandwidth of the communication channel corresponding to the cloud computing platform is released according to the reserved bandwidth, and the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform according to the released bandwidth; When the ratio between the released bandwidth value and the rated bandwidth of the communication channel reaches or exceeds the rated bandwidth occupancy ratio of the communication channel, a communication overload warning is issued.

[0012] Preferably, in S2, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are performed: Based on Power Query tool, clean the real-time data of laying ship operation based on ship networking; Search the real-time data of the laying ship operation based on the ship networking one by one, check whether there are duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, and process the duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking; Among them, duplicate values ​​in the real-time data of laying ship operations based on ship networking are removed, and duplicate data records are deleted; Among them, the interpolation method is used to fill the missing values ​​in the real-time data of the laying ship operation based on the ship networking, so that the missing values ​​in the real-time data of the laying ship operation based on the ship networking are complete; Among them, the interpolation method is used to correct the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, so that the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking are normal.

[0013] Preferably, in said S2, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are further performed: Based on the Z-score standardization, the real-time data of laying ship operations based on the ship networking are normalized; Unify the real-time data of laying ship operations based on ship networking to the same dimension and range, remove the dimension differences between the real-time data of laying ship operations based on ship networking, and determine the standardized real-time data of laying ship operations; Integrate the standardized real-time data of laying ship operations into a unified data view, and verify the integrated real-time data of laying ship operations to determine whether the integrated real-time data of laying ship operations is missing; After the data verification is qualified, the integrated and standardized real-time data of the laying ship operation is safely stored, and the real-time data of the laying ship operation is stored in the database.

[0014] Preferably, in S2, the real-time data of the laying ship operation based on the ship networking is analyzed, and the following operations are performed: According to the intelligent control requirements of the laying ship operation based on the ship networking, the historical data of the laying ship operation is collected, and the collected historical data of the laying ship operation is divided to determine the training set and the test set; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the risk prediction process of laying ship operation, and determine the risk prediction model of laying ship operation based on deep learning; Based on the test set, the performance of the deep learning-based risk prediction model for laying ship operations is tested to determine whether the deep learning-based risk prediction model for laying ship operations can achieve the expected results. The parameters and structure of the deep learning-based risk prediction model for laying ship operations are adjusted according to the test results. After continuous iterative optimization, the optimal risk prediction model for laying ship operations is determined. The optimal risk prediction model for laying ship operation is deployed in the actual risk prediction environment for laying ship operation, and the real-time data of laying ship operation is input into the optimal risk prediction model for laying ship operation; Based on the optimal risk prediction model for laying ship operations, the real-time data of laying ship operations are analyzed to determine whether there are risky behaviors in the laying ship operations, so as to timely discover potential safety hazards and problems and determine the risk prediction results for laying ship operations.

[0015] Preferably, in S3, the following operations are performed to ensure that the ship is always kept within a safe range during the laying process: According to the risk prediction results of the laying ship operation, the real-time data of the laying ship operation is analyzed to find the risk causes of the laying ship operation. Based on the risk causes of the laying ship operation, the operation position of the ship is determined. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct intelligent real-time adjustment and control; When potential safety hazards and problems are detected, the ship operation risk warning alarm is issued in time and the ship's speed is automatically changed. R spe or heading R cou , ensuring that the ship is always within a safe range during the laying process.

[0016] Preferably, in S3, in response to emergencies in a timely manner, the following operations are performed: Acquire real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, organize and analyze the real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, form an intelligent control report of laying ship operation, and display the intelligent control report of laying ship operation in a visual form on the human-computer interaction interface, so that users can intuitively view the operation status of laying ship remotely, and optimize and monitor the ship's route and speed parameters in real time, so as to respond to emergencies in time.

[0017] According to another aspect of the present invention, an intelligent control system for laying ship operations based on ship networking is provided, which is used to implement the intelligent control method for laying ship operations based on ship networking as described above, including: The ship networking platform is used to connect and integrate the ship with the onshore laying equipment and control system using the Internet of Things technology, collect the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform; The cloud computing platform is used to process and analyze the real-time data of the laying ship operation based on the ship networking, use artificial intelligence algorithms for real-time monitoring and prediction, timely discover potential safety hazards and problems, and determine the risk prediction results of the laying ship operation; The intelligent control platform is used to automatically or remotely control the ship's speed, heading and the working status of the laying equipment according to the risk prediction results of the laying ship's operations, so as to respond to emergencies in a timely manner.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention connects and integrates the ship with the onshore laying equipment and control system through the Internet of Things technology, and collects the ship's operating status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of laying ship operations based on ship networking, process and analyze the real-time data of laying ship operations based on ship networking, and use deep learning technology to predict the risks of laying ship operations in real time, timely discover potential safety hazards and problems, determine the risk prediction results of laying ship operations, and according to the risk prediction results of laying ship operations, predict the operating position of the ship. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Intelligent real-time adjustment and control can be carried out to keep the ship within a safe range during the laying process and respond to emergencies in a timely manner. It can realize functions such as real-time monitoring, remote control and automatic control, which can effectively improve the safety and efficiency of the ship during the laying process, reduce the risk of human operational errors, improve the accuracy and safety of the laying work, and reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1It is a flow chart of the intelligent control method of laying ship operation based on ship networking of the present invention; Figure 2 It is a structural diagram of the intelligent control system for laying ship operations based on ship networking of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In order to solve the problem that the existing ships cannot effectively realize the intelligent control of ship laying operations during laying operations, please refer to Figure 1 - Figure 2 , this embodiment provides the following technical solutions: The intelligent control method for laying ship operation based on ship networking includes the following steps: S1: Use IoT technology to collect ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform based on the wireless communication technology; In this embodiment, real-time data of laying ship operations based on ship networking is collected, and the following operations are performed: Based on the Internet of Things technology, sensors are used to monitor the operating position of the laying ship during operation. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct real-time monitoring and collection to obtain ship operation status data ship sta-data ; Among them, GPS is used to monitor the operating position of the laying ship during operation. R pos Conduct real-time monitoring and collection to obtain the operation location information of the laying vessel; Among them, a speedometer is used to measure the running speed of the laying ship during operation. R speConduct real-time monitoring and collection to obtain information on the operation speed of the laying vessel; Among them, the compass is used to check the running direction of the laying ship during operation. R cou Conduct real-time monitoring and collection to obtain the operation direction information of the laying ship; Among them, the attitude meter is used to monitor the operating attitude of the laying ship during operation. R att Conduct real-time monitoring and collection to obtain the operation posture information of the laying vessel; Among them, the depth of the draught of the laying ship during operation is measured by a depth sounder. R dra Conduct real-time monitoring and collection to obtain the draft information of laying vessels; Based on the Internet of Things technology, sensors are used to monitor the wind speed during the laying ship operation. W sp , high waves W hei , water flow speed W vel , water temperature W tem and weather conditions M phe Conduct real-time monitoring and collection to obtain ship operating environment data ship env-data ; Among them, anemometer is used to measure the wind speed during the laying ship operation. W sp Conduct real-time monitoring and collection to obtain wind speed information for laying ship operations; Among them, a wave height meter is used to measure the wave height when the laying ship is operating. W hei Conduct real-time monitoring and collection to obtain wave height information for laying vessel operations; Among them, a water flow velocity meter is used to measure the water flow velocity during the laying ship operation. W vel Conduct real-time monitoring and collection to obtain water flow velocity information of laying ship operations; Among them, a temperature sensor is used to measure the water temperature during the operation of the laying ship. W tem Carry out real-time monitoring and collection to obtain water temperature information of laying ship operation; Among them, meteorological sensors are used to monitor the meteorological conditions when the laying ship is operating. M phe Conduct real-time monitoring and collection to obtain meteorological information of laying ship operations; Based on the Internet of Things technology, sensors are used to monitor the operating status of the laying equipment on the shore R sta , Fault information F infAnd load conditions L sit Conduct real-time monitoring and collection to obtain laying equipment status data Lay sta-data ; Among them, based on the ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of laying ship operations based on ship networking.

[0022] Specifically, in S1, the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform, and the following operations are performed: The bandwidth of the communication channel corresponding to the cloud computing platform during initial operation is set to be lower than the rated bandwidth of the communication channel; Real-time monitoring of the data volume corresponding to each laying ship operation real-time data transmission; Extract the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions; Compare the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions with a preset data volume increase rate threshold; When the data volume increase rate exceeds the preset data volume increase rate threshold, the data volume corresponding to each real-time data transmission of the laying ship operation is retrieved; Using the data volume corresponding to the real-time data transmission of each laying ship operation, a predicted value of the data volume corresponding to the data transmission is obtained; The data volume prediction value is obtained by the following formula:

[0023] Among them, S represents the predicted value of data volume; C max Indicates the maximum amount of data corresponding to real-time data transmission; C f represents the data transmission volume variance corresponding to the real-time data transmission of the laying ship operation; C p Represents the average data volume corresponding to real-time data transmission; G p G represents the average time interval corresponding to the real-time data transmission of the laying ship operation; max represents the maximum time interval corresponding to the real-time data transmission of the laying ship operation; g represents the variance of the time interval corresponding to the real-time data transmission of the laying ship operation; C t represents the data transmission volume of other data during the real-time data transmission of the laying ship operation; r represents the variance corresponding to the comprehensive data transmission time interval of other data except the real-time data of the laying ship operation; f pIndicates the comprehensive data transmission frequency of other data except the real-time data of laying ship operation; f c Indicates the data transmission frequency of real-time data of laying vessel operation; The reserved bandwidth is set for the cloud computing platform according to the data volume prediction value.

[0024] The technical effect of the above technical solution is: by setting the bandwidth of the communication channel corresponding to the cloud computing platform to be lower than the rated bandwidth of the communication channel during initial operation, and dynamically adjusting it according to the data transmission demand in the future, the technical solution realizes the effective utilization of bandwidth resources. This avoids the over-allocation and waste of bandwidth resources, especially when the data transmission volume is low or stable. By real-time monitoring the data volume corresponding to the real-time data transmission of each laying ship operation, the technical solution can timely discover the change of data transmission volume. When the data volume increase rate exceeds the preset data volume increase rate threshold, the system can respond quickly, further analyze and predict future data transmission needs. Using the above technical solution and mathematical model, the technical solution can accurately predict the future data transmission volume. Based on these predicted values, the cloud computing platform can reserve sufficient bandwidth resources in advance to ensure the smoothness and stability of data transmission. This predictive bandwidth reservation strategy helps to reduce the transmission delay or data loss caused by insufficient bandwidth. By dynamically adjusting bandwidth and predictive reservation, the technical solution not only improves the utilization rate of cloud computing platform resources, but also helps to reduce operating costs. Because bandwidth resources are allocated according to actual needs, unnecessary waste is avoided. The technical solution can be dynamically adjusted according to the real-time changes in data transmission volume, thereby enhancing the flexibility and adaptability of the entire system. This helps to cope with fluctuations in data transmission volume in different operating scenarios and ensures that the system always operates in the best condition.

[0025] In summary, this technical solution achieves effective utilization and optimal configuration of bandwidth resources on the cloud computing platform through strategies such as real-time monitoring, dynamic adjustment and predictive bandwidth reservation, improves the stability and flexibility of the system, and reduces operating costs.

[0026] Specifically, the reserved bandwidth is set for the cloud computing platform according to the data volume prediction value, and the following operations are performed: Extracting the data volume prediction value; Obtaining an estimated load of a communication channel corresponding to the cloud computing platform using the data volume prediction value; The estimated load is obtained by the following formula:

[0027] Where L represents the expected load; L0 represents the actual load of the current communication channel; C b represents the standard deviation of the data volume corresponding to real-time data transmission; Ctb It represents the standard deviation of the data transmission volume of other data during the real-time data transmission of the laying ship operation; C tp represents the average data volume of other data during the real-time data transmission of the laying ship operation; S represents the predicted value of the data volume; C e Indicates the rated bandwidth of the communication channel; comparing the predicted load with a preset load reference value; When the predicted load exceeds a preset load reference value, the predicted load is used to set a reserved bandwidth; The reserved bandwidth is obtained by the following formula:

[0028] Where B represents the reserved bandwidth; B c represents the preset reserved bandwidth base value; P represents the actual bandwidth utilization of the current communication channel; L represents the expected load; L y represents a preset load reference value; λ represents a preset sensitivity coefficient of bandwidth adjustment, and the sensitivity coefficient is obtained by experiment according to actual application requirements; The bandwidth of the communication channel corresponding to the cloud computing platform is released according to the reserved bandwidth, and the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform according to the released bandwidth; When the ratio between the released bandwidth value and the rated bandwidth of the communication channel reaches or exceeds the rated bandwidth occupancy ratio of the communication channel, a communication overload warning is issued.

[0029] The technical effect of the above technical solution is: by extracting the predicted value of the data volume and using a complex predicted load formula to calculate the predicted load of the communication channel corresponding to the cloud computing platform, the technical solution can more accurately predict future communication needs. Based on this predicted load, the system can dynamically set the reserved bandwidth to ensure the smoothness and stability of data transmission. The reserved bandwidth formula in the technical solution takes into account multiple factors, including the preset reserved bandwidth base value, the actual bandwidth utilization rate of the current communication channel, the predicted load, the preset load reference value, and the preset bandwidth adjustment sensitivity coefficient. This comprehensive consideration makes bandwidth management more flexible and can be dynamically adjusted according to actual application needs. Through precise bandwidth reservation and flexible bandwidth management, the technical solution avoids excessive allocation and waste of bandwidth resources. It ensures that bandwidth resources are available when needed, and does not occupy too many resources when not needed, thereby improving resource utilization. When the ratio between the released bandwidth value and the rated bandwidth of the communication channel reaches or exceeds the rated bandwidth occupancy ratio of the communication channel, the system can issue a communication overload warning. This warning mechanism helps to timely discover and respond to potential communication bottlenecks, thereby avoiding problems such as data transmission interruption or delay. Through dynamic bandwidth reservation and release, as well as communication overload warning mechanism, this technical solution can improve the stability of the entire system. It ensures the continuity and reliability of data transmission, thereby improving the efficiency and quality of laying ship operations based on ship networking. The bandwidth management strategy in this technical solution is scalable. As the amount of data transmission increases or the communication demand changes, the system can adapt to new demands by adjusting parameters such as the reserved bandwidth base value, load reference value, and sensitivity coefficient. This scalability enables the system to continue to meet possible future data transmission and communication needs.

[0030] In summary, this technical solution achieves effective utilization and optimal configuration of bandwidth resources on the cloud computing platform through accurate bandwidth reservation, flexible bandwidth management, efficient resource utilization, communication overload warning, and improved system stability and scalability.

[0031] S2: Process and analyze the real-time data of the laying ship operation based on the ship networking through the cloud computing platform, and make risk predictions on the real-time data of the laying ship operation based on deep learning technology, so as to timely discover potential safety hazards and problems and determine the risk prediction results of the laying ship operation; In this embodiment, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are performed: Based on Power Query tool, clean the real-time data of laying ship operation based on ship networking; Search the real-time data of the laying ship operation based on the ship networking one by one, check whether there are duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, and process the duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking; Among them, duplicate values ​​in the real-time data of laying ship operations based on ship networking are removed, and duplicate data records are deleted; Among them, the interpolation method is used to fill the missing values ​​in the real-time data of the laying ship operation based on the ship networking, so that the missing values ​​in the real-time data of the laying ship operation based on the ship networking are complete; Among them, the interpolation method is used to correct the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, so that the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking are normal.

[0032] In this embodiment, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are also performed: Based on the Z-score standardization, the real-time data of laying ship operations based on the ship networking are normalized; Unify the real-time data of laying ship operations based on ship networking to the same dimension and range, remove the dimension differences between the real-time data of laying ship operations based on ship networking, and determine the standardized real-time data of laying ship operations; Integrate the standardized real-time data of laying ship operations into a unified data view, and verify the integrated real-time data of laying ship operations to determine whether the integrated real-time data of laying ship operations is missing; After the data verification is qualified, the integrated and standardized real-time data of the laying ship operation is safely stored, and the real-time data of the laying ship operation is stored in the database.

[0033] In this embodiment, the real-time data of the laying ship operation based on the ship networking is analyzed, and the following operations are performed: According to the intelligent control requirements of the laying ship operation based on the ship networking, the historical data of the laying ship operation is collected, and the collected historical data of the laying ship operation is divided to determine the training set and the test set; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the risk prediction process of laying ship operation, and determine the risk prediction model of laying ship operation based on deep learning; Based on the test set, the performance of the deep learning-based risk prediction model for laying ship operations is tested to determine whether the deep learning-based risk prediction model for laying ship operations can achieve the expected results. The parameters and structure of the deep learning-based risk prediction model for laying ship operations are adjusted according to the test results. After continuous iterative optimization, the optimal risk prediction model for laying ship operations is determined. The optimal risk prediction model for laying ship operation is deployed in the actual risk prediction environment for laying ship operation, and the real-time data of laying ship operation is input into the optimal risk prediction model for laying ship operation; Based on the optimal risk prediction model for laying ship operations, the real-time data of laying ship operations are analyzed to determine whether there are risky behaviors in the laying ship operations, so as to timely discover potential safety hazards and problems and determine the risk prediction results for laying ship operations.

[0034] S3: Based on the risk prediction results of the laying ship operation, the ship's operating position R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Intelligent real-time adjustment and control are carried out to ensure that the ship is always kept within a safe range during the deployment process and to respond to emergencies in a timely manner.

[0035] In this embodiment, the following operations are performed to ensure that the ship is always within a safe range during the laying process: According to the risk prediction results of the laying ship operation, the real-time data of the laying ship operation is analyzed to find the risk causes of the laying ship operation. Based on the risk causes of the laying ship operation, the operation position of the ship is determined. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct intelligent real-time adjustment and control; When potential safety hazards and problems are detected, the ship operation risk warning alarm is issued in time and the ship's speed is automatically changed. R spe or heading R cou , ensuring that the ship is always within a safe range during the laying process.

[0036] In this embodiment, to deal with emergencies in a timely manner, perform the following operations: Acquire real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, organize and analyze the real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, form an intelligent control report of laying ship operation, and display the intelligent control report of laying ship operation in a visual form on the human-computer interaction interface, so that users can intuitively view the operation status of laying ship remotely, and optimize and monitor the ship's route and speed parameters in real time, so as to respond to emergencies in time.

[0037] In order to better demonstrate the intelligent control principle of the laying ship operation based on the ship networking, this embodiment now provides an intelligent control system for laying ship operation based on the ship networking, which is used to implement the intelligent control method for laying ship operation based on the ship networking as described above, including: The ship networking platform is used to connect and integrate the ship with the onshore laying equipment and control system using the Internet of Things technology, collect the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform; The cloud computing platform is used to process and analyze the real-time data of the laying ship operation based on the ship networking, use artificial intelligence algorithms for real-time monitoring and prediction, timely discover potential safety hazards and problems, and determine the risk prediction results of the laying ship operation; The intelligent control platform is used to automatically or remotely control the ship's speed, heading and the working status of the laying equipment according to the risk prediction results of the laying ship's operations, so as to respond to emergencies in a timely manner.

[0038] In summary, by using the Internet of Things technology to connect and integrate ships with onshore laying equipment and control systems, and realize functions such as real-time monitoring, remote control and automatic control, the safety and efficiency of ships in the laying process can be effectively improved, the risk of human operating errors can be reduced, and the accuracy and safety of laying work can be improved; secondly, by optimizing parameters such as the ship's route and speed, energy consumption and fuel consumption can be reduced, thereby reducing operating costs; it can also provide real-time monitoring and management data to help companies better understand the operating conditions of ships and equipment, and warn of possible failures and problems in advance, so as to carry out targeted maintenance and management to avoid accidents due to accidents. The company can prevent losses caused by obstacles and accidents, respond to emergencies in a timely manner, and realize real-time monitoring and remote control of ship laying operations through ship networking technology. Relevant personnel can view the real-time position, speed, attitude and other information of the ship through computers, mobile phones and other terminal devices. At the same time, they can also remotely control the ship's sailing direction, speed and other parameters to ensure that the ship completes the laying task safely and efficiently. Through ship networking technology, various data of the ship in the laying process, such as operation trajectory, speed, etc., are collected and sorted out, which can help enterprises better understand the operating conditions of ships and equipment, discover problems and take corresponding measures, and also help to formulate ship maintenance plans and reduce operating costs.

[0039] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0040] Although 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 the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control method for laying ship operation based on ship networking, characterized in that: The steps include: S1: Use IoT technology to collect ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform based on the wireless communication technology; S2: Process and analyze the real-time data of the laying ship operation based on the ship networking through the cloud computing platform, and make risk predictions on the real-time data of the laying ship operation based on deep learning technology, so as to timely discover potential safety hazards and problems and determine the risk prediction results of the laying ship operation; S3: Based on the risk prediction results of the laying ship operation, the ship's operating position R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Carry out intelligent real-time adjustment and control to keep the ship within a safe range during the laying process; In S1, the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform, and the following operations are performed: The bandwidth of the communication channel corresponding to the cloud computing platform during initial operation is set to be lower than the rated bandwidth of the communication channel; Real-time monitoring of the data volume corresponding to each laying ship operation real-time data transmission; Extract the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions; Compare the data volume increase rate between the corresponding data volumes of two adjacent real-time data transmissions with a preset data volume increase rate threshold; When the data volume increase rate exceeds the preset data volume increase rate threshold, the data volume corresponding to each real-time data transmission of the laying ship operation is retrieved; Using the data volume corresponding to the real-time data transmission of each laying ship operation, a predicted value of the data volume corresponding to the data transmission is obtained; The reserved bandwidth is set for the cloud computing platform according to the data volume prediction value.

2. The intelligent control method for laying ship operation based on ship networking according to claim 1 is characterized in that: In S1, real-time data of the laying ship operation based on the ship networking is collected, and the following operations are performed: Based on the Internet of Things technology, sensors are used to monitor the operating position of the laying ship during operation. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct real-time monitoring and collection to obtain ship operation status data ship sta-data ; Based on the Internet of Things technology, sensors are used to monitor the wind speed during the laying ship operation. W sp , high waves W hei , water flow speed W hei , water temperature W tem and weather conditions M phe Conduct real-time monitoring and collection to obtain ship operating environment data ship env-data ; Based on the Internet of Things technology, sensors are used to monitor the operating status of the laying equipment on the shore R sta , Fault information F inf And load conditions L sit Conduct real-time monitoring and collection to obtain laying equipment status data Lay sta-data ; Among them, based on the ship operation status data ship sta-data , Ship operating environment data ship env-data And layout equipment status data Lay sta-data , determine the real-time data of laying ship operations based on ship networking.

3. The intelligent control method for laying ship operation based on ship networking according to claim 1 is characterized in that: The data volume prediction value is obtained by the following formula: ； Among them, S represents the predicted value of data volume; C max Indicates the maximum amount of data corresponding to real-time data transmission; C f represents the data transmission volume variance corresponding to the real-time data transmission of the laying ship operation; C p Represents the average data volume corresponding to real-time data transmission; G p G represents the average time interval corresponding to the real-time data transmission of the laying ship operation; max represents the maximum time interval corresponding to the real-time data transmission of the laying ship operation; g represents the variance of the time interval corresponding to the real-time data transmission of the laying ship operation; C t represents the data transmission volume of other data during the real-time data transmission of the laying ship operation; r represents the variance corresponding to the comprehensive data transmission time interval of other data except the real-time data of the laying ship operation; f p Indicates the comprehensive data transmission frequency of other data except the real-time data of laying ship operation; f c Indicates the data transmission frequency of real-time data of laying vessel operation.

4. The intelligent control method for laying ship operation based on ship networking according to claim 3 is characterized in that: The reserved bandwidth of the cloud computing platform is set according to the data volume prediction value, and the following operations are performed: Extracting the data volume prediction value; Obtaining an estimated load of a communication channel corresponding to the cloud computing platform using the data volume prediction value; The estimated load is obtained by the following formula: ； Where L represents the expected load; L0 represents the actual load of the current communication channel; C b represents the standard deviation of the data volume corresponding to real-time data transmission; C tb It represents the standard deviation of the data transmission volume of other data during the real-time data transmission of the laying ship operation; C tp represents the average data volume of other data during the real-time data transmission of the laying ship operation; S represents the predicted value of the data volume; C e Indicates the rated bandwidth of the communication channel; comparing the predicted load with a preset load reference value; When the predicted load exceeds a preset load reference value, the predicted load is used to set a reserved bandwidth; The reserved bandwidth is obtained by the following formula: ； Where B represents the reserved bandwidth; B c represents the preset reserved bandwidth base value; P represents the actual bandwidth utilization of the current communication channel; L represents the expected load; L y represents a preset load reference value; λ represents a preset sensitivity coefficient of bandwidth adjustment; The bandwidth of the communication channel corresponding to the cloud computing platform is released according to the reserved bandwidth, and the collected real-time data of the laying ship operation based on the ship networking is transmitted to the cloud computing platform according to the released bandwidth; When the ratio between the released bandwidth value and the rated bandwidth of the communication channel reaches or exceeds the rated bandwidth occupancy ratio of the communication channel, a communication overload warning is issued.

5. The intelligent control method for laying ship operation based on ship networking according to claim 2 is characterized in that: In S2, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are performed: Based on Power Query tool, clean the real-time data of laying ship operation based on ship networking; Search the real-time data of the laying ship operation based on the ship networking one by one, check whether there are duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, and process the duplicate values, missing values ​​and abnormal values ​​in the real-time data of the laying ship operation based on the ship networking; Among them, duplicate values ​​in the real-time data of laying ship operations based on ship networking are removed, and duplicate data records are deleted; Among them, the interpolation method is used to fill the missing values ​​in the real-time data of the laying ship operation based on the ship networking, so that the missing values ​​in the real-time data of the laying ship operation based on the ship networking are complete; Among them, the interpolation method is used to correct the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking, so that the abnormal values ​​in the real-time data of the laying ship operation based on the ship networking are normal.

6. The intelligent control method for laying ship operation based on ship networking according to claim 5 is characterized in that: In S2, the real-time data of the laying ship operation based on the ship networking is processed, and the following operations are performed: Based on the Z-score standardization, the real-time data of laying ship operations based on the ship networking are normalized; Unify the real-time data of laying ship operations based on ship networking to the same dimension and range, remove the dimension differences between the real-time data of laying ship operations based on ship networking, and determine the standardized real-time data of laying ship operations; Integrate the standardized real-time data of laying ship operations into a unified data view, and verify the integrated real-time data of laying ship operations to determine whether the integrated real-time data of laying ship operations is missing; After the data verification is qualified, the integrated and standardized real-time data of the laying ship operation is safely stored, and the real-time data of the laying ship operation is stored in the database.

7. The intelligent control method for laying ship operation based on ship networking according to claim 6 is characterized in that: In S2, the real-time data of the laying ship operation based on the ship networking is analyzed, and the following operations are performed: According to the intelligent control requirements of the laying ship operation based on the ship networking, the historical data of the laying ship operation is collected, and the collected historical data of the laying ship operation is divided to determine the training set and the test set; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the risk prediction process of laying ship operation, and determine the risk prediction model of laying ship operation based on deep learning; Based on the test set, the performance of the deep learning-based risk prediction model for laying ship operations is tested to determine whether the deep learning-based risk prediction model for laying ship operations can achieve the expected results. The parameters and structure of the deep learning-based risk prediction model for laying ship operations are adjusted according to the test results. After continuous iterative optimization, the optimal risk prediction model for laying ship operations is determined. The optimal risk prediction model for laying ship operation is deployed in the actual risk prediction environment for laying ship operation, and the real-time data of laying ship operation is input into the optimal risk prediction model for laying ship operation; Based on the optimal risk prediction model for laying ship operations, the real-time data of laying ship operations are analyzed to determine whether there are risky behaviors in the laying ship operations, so as to timely discover potential safety hazards and problems and determine the risk prediction results for laying ship operations.

8. The intelligent control method for laying ship operation based on ship networking according to claim 7 is characterized in that: In S3, the following operations are performed to ensure that the ship is always within a safe range during the laying process: According to the risk prediction results of the laying ship operation, the real-time data of the laying ship operation is analyzed to find the risk causes of the laying ship operation. Based on the risk causes of the laying ship operation, the operation position of the ship is determined. R pos ,speed R spe ,course R cou ,attitude R att and draft R dra Conduct intelligent real-time adjustment and control; When potential safety hazards and problems are detected, the ship operation risk warning alarm is issued in time and the ship's speed is automatically changed. R spe or heading R cou , ensuring that the ship is always within a safe range during the laying process.

9. The intelligent control method for laying ship operation based on ship networking according to claim 8 is characterized in that: In S3, in order to deal with emergencies in a timely manner, the following operations are performed: Acquire real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, organize and analyze the real-time data of laying ship operation, risk prediction results of laying ship operation and intelligent real-time adjustment control plan, form an intelligent control report of laying ship operation, and display the intelligent control report of laying ship operation in a visual form on the human-computer interaction interface, so that users can intuitively view the operation status of laying ship remotely, and optimize and monitor the ship's route and speed parameters in real time, so as to respond to emergencies in time.

10. An intelligent control system for laying ship operations based on ship networking, used to implement the intelligent control method for laying ship operations based on ship networking as claimed in claim 9, characterized in that: include: The ship networking platform is used to connect and integrate the ship with the onshore laying equipment and control system using the Internet of Things technology, collect the real-time data of the laying ship operation based on the ship networking, and transmit the collected real-time data of the laying ship operation based on the ship networking to the cloud computing platform; The cloud computing platform is used to process and analyze the real-time data of the laying ship operation based on the ship networking, use artificial intelligence algorithms for real-time monitoring and prediction, timely discover potential safety hazards and problems, and determine the risk prediction results of the laying ship operation; The intelligent control platform is used to automatically or remotely control the ship's speed, heading and the working status of the laying equipment according to the risk prediction results of the laying ship's operations, so as to respond to emergencies in a timely manner.

Images