Ship magnetic conversion power state remote monitoring system

Abstract

The invention provides a ship magnetic conversion power state remote monitoring system comprising a magnetic conversion power parameter acquisition module which captures magnetic conversion power state parameters of magnetic field change, power output and the like of a ship under different working conditions through a multi-data acquisition device; the remote communication and data transmission module transmits the acquired magnetic conversion power state parameters to a remote control center through a self-adaptive communication protocol; the adaptive communication protocol automatically adjusts the transmission rate and the data compression mode according to the network condition; the optimization algorithm and safety control module operates in a remote control center, and receives and analyzes the transmitted magnetic conversion power state parameters; through a built-in magnetic transformation power optimization algorithm model, the operation state of the ship is evaluated in real time, and potential risks are predicted; when an anomaly is detected, a fluid-actuated safety device is enabled, and related personnel are notified via a remote fault alert system. According to the invention, comprehensive monitoring, efficient transmission and intelligent management of the magnetic conversion power state of the ship are realized.

Description

Technical Field

[0001] The invention relates to the technical field of safety equipment for fluid actuation systems, and in particular to a remote monitoring system for the magnetic conversion power state of a ship. Background Art

[0002] With the rapid development of the shipping industry, the safety and efficiency of ships have become the focus of attention. Traditional ship monitoring systems mainly rely on sensors and local control systems on board ships, which have limitations in data collection and processing capabilities. With the development of Internet of Things (IoT) and artificial intelligence (AI) technologies, remote monitoring systems have gradually become an important tool for ship management. The ship magnetic conversion power state remote monitoring system is developed based on this background technology; using advanced sensor technology, high-speed communication network and intelligent algorithm, real-time monitoring and remote control of the ship's power state are realized. It can not only improve the safety of ships, but also optimize the operation efficiency of ships and reduce operating costs. Although the existing ship monitoring system has improved the safety and management efficiency of ships to a certain extent, it still has the following major defects: the traditional system relies on sensors on board ships, and the accuracy and comprehensiveness of data collection are limited, especially in complex sea conditions, the data is easily interfered. Although the existing communication technology (such as satellite communication) can realize remote data transmission, the real-time and stability of data transmission are difficult to guarantee when the network coverage is insufficient or the signal is unstable. Most of the existing monitoring systems rely on simple rules and thresholds for judgment, lack intelligent analysis and prediction capabilities, and are difficult to cope with the complex and changeable ship operation environment.

[0003] Prior art 1, application number: CN202411071114.5 discloses a common-mode suppression method based on a series hybrid ship DC integrated power system, wherein a common-mode inductor and a high-frequency converter module connected at the midpoint of the AC / DC side structure are used between the converter module and the motor to suppress the common-mode voltage; a common-mode inductor and a high-frequency converter module connected at the midpoint of the AC / DC side structure are used on the DC side of the converter module to suppress the common-mode voltage, which can suppress the common-mode voltage of the high-frequency converter module on the motor side; a magnetic ring is added to the battery side loop of the DC / DC module to suppress the common-mode voltage, which can suppress the common-mode voltage of the high-frequency DC / DC module; an isolation transformer is used on the battery converter side to suppress the common-mode voltage. Although the main goal is to achieve safe and reliable operation of the DC integrated power system, the proposed common-mode suppression scheme reduces the reliability problems of the system caused by the common-mode interference of the system, thereby ensuring the normal power supply of the power system and improving the reliability of the safe operation of the DC integrated power system. However, in relatively complex sea conditions, it is easy to be interfered, resulting in the inability of the DC common-mode suppression to be efficient and complete, which affects the power output of the ship to a certain extent.

[0004] Prior art 2, application number: CN202410230644.3 discloses an engine mainly driven by magnetic power, including a support plate, a first support seat is installed on the front surface of the support plate, a coil is installed on the upper surface of the first support seat, a magnetic column is passed through the internal movement of the coil, a hinge seat is installed at the lower end of the magnetic column, and a lubrication mechanism is arranged on the front side of the support plate below the crankshaft. Although the rotation of the crankshaft is realized by using magnetic power through structures such as coils, magnetic columns, hinge seats, connecting rods and micro switches, no harmful emissions are generated during operation, and the impact on the environment is small; by pushing the sliding rod in the lubrication mechanism to drive the oil push plate to rise, the lubricating oil in the oil tank is squeezed out, and the connection is refueled and lubricated, a convenient refueling lubrication is realized, and the connecting rod does not need to be disassembled for refueling, and refueling can be performed according to demand, which will not cause waste of lubricating oil; but its structure is relatively simple and the degree of intelligence is low, resulting in a low engine power conversion loss rate.

[0005] Prior art three, application number: CN202411155529.0 discloses a movable magnetic torsion and energy circulation power system, including: a power unit, a working unit, an energy storage unit, an energy compensation unit and a control unit. The power unit includes an energy supply battery that stores electrical energy and can output electrical energy, and the charge amount of the energy supply battery must be greater than the power consumption or slightly exceed the balance amount; the working unit includes an active motor and a generator, and the active motor or generator is arranged at the hub or other places; the energy storage unit includes an energy storage battery capable of trickle charging; the energy compensation unit is used to charge the power supply battery or the energy storage battery, and the charging time is less than the power consumption time; the control unit includes an intelligent processor and an electric energy sensor. Although the physical principle of the magnetic effect is used to circulate the controllable program, continuously regenerate, and continue the magnetic effect; the inertial energy of the object is used to continuously act on the kinetic demand and power of the object itself; but each period is easily affected by the complex environment at sea, resulting in unstable operation of each device and ineffective power output.

[0006] At present, the existing technologies 1, 2 and 3 have limited data acquisition accuracy and comprehensiveness, and the data is easily disturbed by complex sea conditions; the real-time and stability of data transmission are difficult to guarantee; and they lack intelligent analysis and prediction capabilities, making it difficult to cope with the complex and changeable ship operating environment. Therefore, the present invention provides a remote monitoring system for the magnetic conversion power state of a ship. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a remote monitoring system for the magnetic conversion power state of a ship, comprising:

[0008] The magnetic conversion power parameter acquisition module is responsible for capturing the magnetic field changes of the ship under different working conditions and the magnetic conversion power state parameters of the power output through multiple data acquisition devices;

[0009] The remote communication and data transmission module is responsible for transmitting the collected magnetic conversion power state parameters to the remote control center through the adaptive communication protocol; the adaptive communication protocol automatically adjusts the transmission rate and data compression method according to the network conditions;

[0010] The optimization algorithm and safety control module is responsible for running in the remote control center, receiving and analyzing the transmitted magnetic conversion power state parameters; through the built-in magnetic conversion power optimization algorithm model, it evaluates the operating status of the ship in real time and predicts potential risks; when an abnormality is detected, it activates the fluid-actuated safety equipment and notifies relevant personnel through the remote fault warning system.

[0011] Optional, magnetic conversion dynamic parameter acquisition module, including:

[0012] The network architecture submodule is responsible for building a distributed network consisting of multiple nodes. Various sensors are installed at various key parts of the ship to capture the magnetic conversion power state parameters and transmit them to multiple nodes of the distributed processing network through the network. The nodes include sensor nodes, intermediate nodes and central nodes, and the nodes are interconnected through the network.

[0013] The weighted fusion submodule is responsible for evaluating the quality of the data source of each magnetic conversion dynamic state parameter and generating an initial quality score for each data source; calculating the real-time quality score of the data source and dynamically updating the weight of each data source; performing weighted processing on the magnetic conversion dynamic state parameters according to the weight of each data source and calculating the weighted average value;

[0014] The parameter storage submodule is responsible for using distributed storage to disperse and store the fused magnetic conversion dynamic state parameters on multiple nodes of the distributed network.

[0015] Optional remote communication and data transmission module, including:

[0016] The data encapsulation and compression submodule is responsible for intelligently encapsulating the collected magnetic conversion dynamic state parameters and dynamically selecting the data compression algorithm based on the real-time network bandwidth and delay conditions and the adaptive communication protocol;

[0017] The transmission path selection submodule is responsible for selecting the optimal transmission path by using multi-path routing technology when the data packet is sent through the remote communication and data transmission modules;

[0018] The receiving and decompression submodule is responsible for dynamically adjusting the decompression parameters according to the compression strategy of the sender after the remote control center receives the data packet. The decompressed magnetic conversion power state parameters are analyzed in real time, and the storage strategy is selected to determine the storage device.

[0019] Optional, remote communication and data transmission module, also includes:

[0020] The master node setting submodule is responsible for taking network bandwidth and delay conditions, multi-path routing technology and compression strategy as master nodes respectively. Network bandwidth and delay conditions are used to set master nodes through network probes, multi-path routing technology is used to set master nodes through network scanning, and compression strategies formulate different compression strategies.

[0021] The slave node setting submodule is responsible for dynamically selecting the compression algorithm based on the real-time bandwidth and delay data provided by the network bandwidth and delay conditions; the slave node optimal transmission path selects the transmission path with the best performance based on the path evaluation results provided by the master node multi-path routing technology; the slave node dynamically adjusts the decompression parameters based on the compression strategy transmitted by the master node compression strategy;

[0022] The node collaborative work submodule is responsible for implementing the data encapsulation and compression submodule to obtain bandwidth and delay data from the network bandwidth and delay of the main node, and the transmission path selection submodule to obtain the path evaluation result from the multi-path routing technology of the main node; according to the shared data, the data encapsulation and compression submodule and the transmission path selection submodule dynamically adjust their respective strategies; the transmission path selection submodule passes the selected optimal path information to the receiving and decompression submodule to predict the arrival time of the data packet and the possible compression strategy; the data encapsulation and compression submodule passes the selected compression strategy to the receiving and decompression submodule to correctly decompress the data.

[0023] Optional, optimization algorithm and safety control module, including:

[0024] The initial state assessment submodule is responsible for the preliminary state assessment of the magnetic conversion power optimization algorithm model. Through statistical analysis and rule engine, it is determined whether the current operating state of the ship is within the normal range. If it is within the normal range, the preliminary state assessment will continue; if it is not within the normal range, the in-depth state assessment will be started.

[0025] The deep state assessment submodule is responsible for obtaining the magnetic field change trend and real-time data of power output stability from the magnetic conversion power state parameters. Combining historical data and real-time data, the magnetic conversion power optimization algorithm model conducts a deep assessment of the ship's operating state and obtains the state assessment results.

[0026] The risk probability prediction submodule is responsible for identifying potential risk factors and screening out risk factors that may affect the safe operation of ships; combining real-time data and historical data to predict the probability of occurrence of each potential risk factor and obtain the final risk prediction result.

[0027] Optional, initial state assessment submodule, including:

[0028] The statistical identification unit is responsible for calculating the mean, variance, extreme value and other statistical quantities of the magnetic conversion dynamic state parameters, obtaining the distribution characteristics of the magnetic conversion dynamic state parameters; using statistical methods to detect abnormal points in the magnetic conversion dynamic state parameters and identifying possible abnormal states;

[0029] The rule matching unit is responsible for building a series of rules based on historical data and expert knowledge to define the boundary conditions for the normal operation of the ship; matching the current magnetic conversion power state parameters with the rules in the rule base to determine whether the ship's operating state meets the standards for normal operation;

[0030] The status judgment unit is responsible for judging whether the ship's operating status is within the normal range based on the results of statistical analysis and rule matching; if it meets the normal standards, it will continue with the preliminary status assessment; if it does not meet the standards, it will start the in-depth status assessment.

[0031] Optional, deep state assessment submodule, including:

[0032] The input layer processing unit is responsible for inputting the characteristic data of the extracted magnetic conversion dynamic state parameters into the input layer of the magnetic conversion dynamic optimization algorithm model, and the input layer performs preliminary processing on the magnetic conversion dynamic state parameters;

[0033] The hidden layer analysis unit is responsible for extracting feature data three times, fusing the weighted feature data, and generating new feature representations for deep state assessment;

[0034] The output layer generation unit is responsible for generating multiple state evaluation indicators through the fully connected layer and activation function.

[0035] Optional, hidden layer analysis unit, including:

[0036] The signal generation subunit is responsible for generating a supervisory signal using the first half of the time series data and the second half of the time series data predicted by the magnetic conversion dynamic optimization algorithm model;

[0037] The relational learning subunit is responsible for generating multiple views by randomly cropping and flipping the time series data. Through comparative learning tasks, the magnetic conversion dynamics optimization algorithm model learns the invariance characteristics between different views. It generates supervision signals by predicting the characteristic value of a certain time point based on the characteristics of the time series data, so that the magnetic conversion dynamics optimization algorithm model learns the intrinsic relationship between the features.

[0038] The weighted fusion subunit is responsible for further optimizing the feature extraction capability of the model through the supervision signal generated by self-supervised learning; feature fusion fuses the weighted features to generate a new feature representation for the final state evaluation.

[0039] Optional, risk probability prediction submodule, including:

[0040] The hierarchical division unit is responsible for calculating the characteristic values ​​of risk factors and calculating the corresponding probability of occurrence of the characteristic values ​​through the probability density function; the risk factors are divided into multiple levels according to the probability density function, including extremely high, high, medium, low and extremely low, and each level corresponds to a different risk level and response strategy;

[0041] The threshold adjustment unit is responsible for adjusting the risk level threshold based on historical data and real-time data;

[0042] The measure triggering unit is responsible for automatically triggering corresponding control measures according to the risk level, such as adjusting operating parameters, starting the backup system or issuing an emergency alarm.

[0043] Optionally, a threshold adjustment unit comprises:

[0044] The cumulative probability determination subunit is responsible for determining the cumulative probability corresponding to each risk level according to the risk level classification;

[0045] The threshold calculation subunit is responsible for calculating the threshold corresponding to each risk level using the threshold model expression;

[0046] The dynamic adjustment subunit is responsible for combining real-time data and dynamically adjusting parameters to adapt to environmental changes and fluctuations in risk factors.

[0047] The magnetic conversion power parameter acquisition module of the present invention can simultaneously capture the magnetic conversion power state parameters of the ship in multiple dimensions, such as magnetic field changes and power output under different working conditions; ensure the accuracy and real-time nature of the data, and provide a reliable basis for analysis. The remote communication and data transmission module automatically adjusts the transmission rate and data compression method according to the network conditions to ensure the stability and efficiency of data transmission; it can transmit the collected magnetic conversion power state parameters to the remote control center in real time to ensure the timeliness of the information. The optimization algorithm and safety control module runs in the remote control center, receives and analyzes the transmitted magnetic conversion power state parameters, and evaluates the operating status of the ship in real time; through the built-in magnetic conversion power optimization algorithm model, it can predict potential risks and take timely measures; when an abnormality is detected, the fluid-actuated safety device is enabled, and the relevant personnel are notified through the remote fault warning system to ensure the safe operation of the ship.

[0048] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0049] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0051] Figure 1 This is a block diagram of a remote monitoring system for magnetic conversion power state of a ship in Embodiment 1 of the present invention;

[0052] Figure 2 This is a block diagram of a magnetic conversion power parameter acquisition module in Example 2 of the present invention;

[0053] Figure 3 The remote communication and data transmission module frame in Embodiment 3 of the present invention Figure 1 ;

[0054] Figure 4 The remote communication and data transmission module frame in Embodiment 4 of the present invention Figure 2 ;

[0055] Figure 5 This is a block diagram of the optimization algorithm and safety control module in Example 5 of the present invention;

[0056] Figure 6 This is a block diagram of the initial state evaluation submodule in Example 6 of the present invention;

[0057] Figure 7 This is a block diagram of a depth state assessment submodule in Embodiment 7 of the present invention;

[0058] Figure 8 This is a block diagram of a hidden layer analysis unit in Embodiment 8 of the present invention;

[0059] Fig. 9 This is a block diagram of the risk probability prediction submodule in Example 9 of the present invention;

[0060] Fig.10 This is a block diagram of a threshold adjustment unit in Embodiment 10 of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0063] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0064] Example 1: Figure 1 As shown, an embodiment of the present invention provides a remote monitoring system for the magnetic conversion power state of a ship, comprising:

[0065] The magnetic conversion power parameter acquisition module is responsible for capturing the magnetic conversion power state parameters such as the magnetic field changes and power output of the ship under different working conditions through multiple data acquisition devices;

[0066] The remote communication and data transmission module is responsible for transmitting the collected magnetic conversion power state parameters to the remote control center through the adaptive communication protocol; the adaptive communication protocol automatically adjusts the transmission rate and data compression method according to the network conditions;

[0067] The optimization algorithm and safety control module is responsible for running in the remote control center, receiving and analyzing the transmitted magnetic conversion power state parameters; through the built-in magnetic conversion power optimization algorithm model, it evaluates the operating status of the ship in real time and predicts potential risks; when an abnormality is detected, it activates the fluid-actuated safety equipment and notifies relevant personnel through the remote fault warning system.

[0068] The working principle and beneficial effects of the above technical solution are as follows: the magnetic conversion power parameter acquisition module of this embodiment captures the magnetic conversion power state parameters such as magnetic field changes and power output of the ship under different working conditions through multiple data acquisition devices; the remote communication and data transmission module transmits the collected magnetic conversion power state parameters to the remote control center through an adaptive communication protocol; the adaptive communication protocol automatically adjusts the transmission rate and data compression method according to the network status; the optimization algorithm and safety control module runs in the remote control center to receive and analyze the transmitted magnetic conversion power state parameters; through the built-in magnetic conversion power optimization algorithm model, the operating status of the ship is evaluated in real time and potential risks are predicted; when an abnormality is detected, the fluid-actuated safety device is enabled, and the relevant personnel are notified through the remote fault warning system. The magnetic conversion power parameter acquisition module of the above scheme can simultaneously capture the magnetic conversion power state parameters of the ship in multiple dimensions such as magnetic field changes and power output under different working conditions; ensure the accuracy and real-time nature of the data, and provide a reliable basis for analysis. The significance achieved: through multiple data acquisition devices, the magnetic conversion power state of the ship can be fully monitored and abnormal conditions can be discovered in time; it provides a high-quality data basis for remote communication and data analysis, and ensures the effectiveness of the monitoring system. The remote communication and data transmission module automatically adjusts the transmission rate and data compression method according to the network status to ensure the stability and efficiency of data transmission; it can transmit the collected magnetic conversion power state parameters to the remote control center in real time to ensure the timeliness of information. Significance achieved: Through the remote communication and data transmission module, remote monitoring of the ship's magnetic conversion power state is realized, reducing the need for on-site maintenance; the adaptive communication protocol ensures the efficiency and stability of data transmission and improves the reliability of the monitoring system. The optimization algorithm and safety control module runs in the remote control center, receives and analyzes the transmitted magnetic conversion power state parameters, and evaluates the ship's operating status in real time; through the built-in magnetic conversion power optimization algorithm model, it can predict potential risks and take timely measures; when an abnormality is detected, the fluid-actuated safety device is enabled, and the relevant personnel are notified through the remote fault warning system to ensure the safe operation of the ship. Significance achieved: Through the optimization algorithm and safety control module, the ship's magnetic conversion power state can be intelligently managed to improve operating efficiency; real-time analysis and risk prediction functions ensure that the ship can promptly discover and deal with potential safety hazards during operation, ensuring the safe operation of the ship; through the remote fault warning system, relevant personnel can respond and deal with abnormal situations in a timely manner, improving emergency response capabilities.

[0069] In summary, this embodiment realizes comprehensive monitoring, efficient transmission and intelligent management of the ship's magnetic conversion power state through the collaborative work of multiple modules. It not only improves the accuracy and real-time performance of monitoring, but also enhances the safety and reliability of ship operation, and has important practical application value.

[0070] Example 2: Figure 2 As shown, based on Example 1, the magnetic conversion power parameter acquisition module provided by the embodiment of the present invention includes:

[0071] The network architecture submodule is responsible for building a distributed network consisting of multiple nodes. Various sensors are installed at various key parts of the ship (such as the hull, engine, cockpit, etc.) to capture the magnetic conversion power state parameters and transmit them to multiple nodes of the distributed processing network through the network; the nodes include sensor nodes, intermediate nodes and central nodes, and the nodes are interconnected through the network;

[0072] The weighted fusion submodule is responsible for evaluating the quality of the data source of each magnetic conversion dynamic state parameter and generating an initial quality score for each data source; calculating the real-time quality score of the data source and dynamically updating the weight of each data source; performing weighted processing on the magnetic conversion dynamic state parameters according to the weight of each data source and calculating the weighted average value;

[0073] The parameter storage submodule is responsible for using distributed storage to disperse and store the fused magnetic conversion dynamic state parameters on multiple nodes of the distributed network.

[0074] Among them, the network architecture submodule describes the data transmission and synchronization process between nodes:

[0075]

[0076] In the formula, Represents the magnetic conversion dynamic state parameter matrix The partial derivative at time t, A represents the transmission matrix from the sensor node to the intermediate node, Represents the raw data matrix captured by the sensor node The partial derivative with respect to time t, B represents the transmission matrix from the intermediate node to the central node, Represents the data matrix after processing by the intermediate nodes The partial derivative with respect to time t, c represents the data matrix processed by the central node, Represents the data matrix processed by the central node The partial derivative with respect to time t;

[0077] The weighted fusion submodule uses gradient descent and integration to describe the dynamic update process of weights:

[0078]

[0079] Where W(t) represents the weight matrix at time t, W(t-1) represents the weight matrix at time \(t-1\), η represents the learning rate, Represents the loss function from time t-1 to t The gradient integral of the weight matrix W is: represents the loss function, which depends on the weight matrix W(τ) and the quality score matrix Q(τ) at time τ, where Q(τ) represents the quality score matrix at time τ;

[0080] The parameter storage submodule describes the data sharding and storage process:

[0081]

[0082] Where D(t) represents the data matrix after segmentation at time t, It represents the integral of the sharding function Sharding from time 0 to t, M(τ) represents the magnetic conversion dynamic state parameter matrix at time \(\tau\), P represents the sharding strategy matrix, which describes how to shard the data to different nodes, Sharding represents the sharding function, which shards the data matrix M(τ) to different nodes according to the sharding strategy matrix P; it covers the key processes in the magnetic conversion dynamic parameter acquisition module.

[0083] The working principle and beneficial effects of the above technical solution are as follows: the network architecture submodule of this embodiment constructs a distributed network composed of multiple nodes, installs multiple sensors at various key parts of the ship (such as the hull, engine, cockpit, etc.), captures magnetic conversion power state parameters, and transmits them to multiple nodes of distributed processing networks through the network; wherein the nodes include sensor nodes, intermediate nodes and central nodes, and the nodes are interconnected through the network; the weighted fusion submodule evaluates the quality of the data source of each magnetic conversion power state parameter and generates an initial quality score for each data source; calculates the real-time quality score of the data source and dynamically updates the weight of each data source; according to the weight of each data source, the magnetic conversion power state parameters are weighted and the weighted average is calculated; the parameter storage submodule adopts distributed storage to store the fused magnetic conversion power state parameters in multiple nodes of the distributed network. The network architecture submodule of the above scheme installs sensors at various key parts of the ship to construct a distributed network composed of multiple nodes to ensure comprehensive data collection and real-time transmission; the nodes are interconnected through the network to achieve rapid data transmission and efficient processing. Significance achieved: By installing sensors at various key parts of the ship, the ship's status can be fully monitored to ensure the integrity and accuracy of the data; the distributed network can transmit data in real time, ensuring that the system can quickly respond to changes in the ship's status and improve the safety and reliability of the ship. The weighted fusion submodule evaluates the quality of the data source of each magnetic conversion power state parameter, generates an initial quality score, and ensures the reliability of the data source; according to the real-time quality score, the weight of each data source is dynamically updated to ensure the accuracy and robustness of the fusion result; according to the weight of each data source, the magnetic conversion power state parameters are weighted and the weighted average is calculated to improve the accuracy of the fusion result. Significance achieved: Through quality assessment and dynamic weight adjustment, the reliability of the fusion result is ensured to avoid errors caused by fluctuations in the quality of the data source; weighted processing can effectively improve the accuracy of the fusion result and provide more accurate data support for the ship's operating status. The parameter storage submodule adopts distributed storage technology to store the fused magnetic conversion power state parameters in multiple nodes of the distributed network to ensure the security and reliability of the data; distributed storage can achieve redundant backup of data, avoid single point failures, and improve the fault tolerance of the system. Significance achieved: Distributed storage can ensure data security and avoid data loss due to single point failure; through data redundancy and fault tolerance mechanisms, it can improve system reliability and ensure the continuous availability of ship operation status data.

[0084] To sum up, the magnetic conversion power parameter acquisition module of this embodiment can realize comprehensive monitoring of the ship status, real-time response, improved data reliability, improved accuracy, data security protection and enhanced system reliability; it provides strong support for the safe operation and efficient management of ships.

[0085] Example 3: Figure 3 As shown, based on Example 1, the remote communication and data transmission module provided by the embodiment of the present invention includes:

[0086] The data encapsulation and compression submodule is responsible for intelligently encapsulating the collected magnetic conversion dynamic state parameters and dynamically selecting the data compression algorithm based on the real-time network bandwidth and delay conditions and the adaptive communication protocol;

[0087] The transmission path selection submodule is responsible for selecting the optimal transmission path by using multi-path routing technology when the data packet is sent through the remote communication and data transmission modules;

[0088] The receiving and decompression submodule is responsible for dynamically adjusting the decompression parameters according to the compression strategy of the sender after the remote control center receives the data packet. The decompressed magnetic conversion power state parameters are analyzed in real time, and the storage strategy is selected to determine the storage device.

[0089] The working principle and beneficial effects of the above technical scheme are as follows: the data encapsulation and compression submodule of this embodiment intelligently encapsulates the collected magnetic conversion power state parameters, and the adaptive communication protocol dynamically selects the data compression algorithm according to the real-time network bandwidth and delay; when the transmission path selection submodule data packet is sent through the remote communication and data transmission module, the adaptive communication protocol uses multi-path routing technology to select the optimal transmission path; after the remote control center of the receiving and decompression submodule receives the data packet, the adaptive communication protocol dynamically adjusts the decompression parameters according to the compression strategy of the sender; the decompressed magnetic conversion power state parameters are parsed in real time, and the storage strategy is selected to determine the storage device. The data encapsulation and compression submodule of the above scheme can intelligently encapsulate the collected magnetic conversion power state parameters, and dynamically select the optimal data compression algorithm according to the real-time network bandwidth and delay, which not only improves the efficiency of data transmission, but also reduces the occupation of network bandwidth, ensuring the integrity and real-time of data during transmission. Significance: Through the selection of adaptive communication protocol and intelligent compression algorithm, the module ensures that efficient data transmission can be achieved in different network environments, which is particularly important for systems that require real-time monitoring and remote control, not only improving the response speed of the system, but also reducing the communication cost. The transmission path selection submodule uses multipath routing technology to dynamically select the optimal transmission path when sending data packets; even in complex or unstable network environments, data packets can quickly and reliably reach their destinations through the optimal path. Significance: Through adaptive communication protocols and multipath routing technology, this module significantly improves the reliability and stability of data transmission; for remote control systems that require high reliability, it ensures the continuity and accuracy of data transmission and avoids communication interruptions or data loss caused by network fluctuations. After receiving the data packet at the remote control center, the receiving and decompression submodule dynamically adjusts the decompression parameters according to the compression strategy of the sender; the decompressed magnetic conversion power state parameters are analyzed in real time, and the storage device is determined according to the storage strategy; the integrity and accuracy of the data are ensured, and the utilization of storage resources is optimized. Significance: Through adaptive decompression and intelligent storage strategies, this module ensures that the receiving end can process and store data efficiently and accurately; for systems that require long-term monitoring and data analysis, it not only improves the efficiency of data processing, but also provides a reliable basis for subsequent data analysis and decision-making.

[0090] In summary, this embodiment realizes efficient and secure data transmission, ensures the overall performance and reliability of the remote communication and data transmission module, and has important technical significance and practical application value for modern remote control systems, Internet of Things devices, and various application scenarios requiring real-time data transmission.

[0091] Example 4: Figure 4As shown, based on Example 3, the remote communication and data transmission module provided in this embodiment of the present invention further includes:

[0092] The master node setting submodule is responsible for taking network bandwidth and delay conditions, multi-path routing technology and compression strategy as master nodes respectively. Network bandwidth and delay conditions are used to set master nodes through network probes, multi-path routing technology is used to set master nodes through network scanning, and compression strategies formulate different compression strategies.

[0093] The slave node setting submodule is responsible for dynamically selecting the compression algorithm based on the real-time bandwidth and delay data provided by the network bandwidth and delay conditions; the slave node optimal transmission path selects the transmission path with the best performance based on the path evaluation results provided by the master node multi-path routing technology; the slave node dynamically adjusts the decompression parameters based on the compression strategy transmitted by the master node compression strategy;

[0094] The node collaborative work submodule is responsible for implementing the data encapsulation and compression submodule to obtain bandwidth and delay data from the network bandwidth and delay of the main node, and the transmission path selection submodule to obtain the path evaluation result from the multi-path routing technology of the main node; according to the shared data, the data encapsulation and compression submodule and the transmission path selection submodule dynamically adjust their respective strategies; the transmission path selection submodule passes the selected optimal path information to the receiving and decompression submodule to predict the arrival time of the data packet and the possible compression strategy; the data encapsulation and compression submodule passes the selected compression strategy to the receiving and decompression submodule to correctly decompress the data.

[0095] The working principle and beneficial effects of the above technical solution are as follows: the master node setting submodule of this embodiment uses network bandwidth and delay conditions, multi-path routing technology and compression strategy as master nodes respectively, the network bandwidth and delay conditions are used to realize master node setting through network probes, the multi-path routing technology realizes master node setting through network scanning, and the compression strategy formulates different compression strategies; the slave node setting submodule dynamically selects the compression algorithm according to the real-time bandwidth and delay data provided by the network bandwidth and delay conditions; the slave node optimal transmission path selects the transmission path with the best performance according to the path evaluation result provided by the master node multi-path routing technology; the slave node dynamically adjusts the decompression parameters according to the master node The compression strategy transmitted by the compression strategy dynamically adjusts the decompression parameters; the node collaborative work submodule realizes that the data encapsulation and compression submodule obtains bandwidth and delay data from the network bandwidth and delay of the main node, and the transmission path selection submodule obtains the path evaluation result from the multi-path routing technology of the main node; according to the shared data, the data encapsulation and compression submodule and the transmission path selection submodule dynamically adjust their respective strategies; the transmission path selection submodule passes the selected optimal path information to the receiving and decompression submodule to predict the arrival time and possible compression strategy of the data packet; the data encapsulation and compression submodule passes the selected compression strategy to the receiving and decompression submodule to correctly decompress the data. The main node setting submodule of the above scheme monitors the network bandwidth and delay in real time through the network probe to ensure the real-time and reliability of data transmission; detects multiple transmission paths through network scanning to provide flexibility and reliability of path selection; formulates different compression strategies according to the data type and network environment to optimize the data transmission efficiency. The significance achieved: ensure the real-time performance of data transmission and reduce delay; improve the reliability of data transmission through multi-path selection and dynamic compression strategy; adapt to different network environments and data types, and enhance the adaptive ability of the system. The node setting submodule dynamically selects the optimal compression algorithm based on the real-time bandwidth and delay data to improve the data transmission efficiency; selects the transmission path with the best performance based on the path evaluation results to reduce the delay and packet loss rate of data transmission; dynamically adjusts the decompression parameters based on the compression strategy to ensure the accuracy and efficiency of data decompression. The significance achieved: Improve the efficiency of data transmission and decompression through dynamic selection and adjustment; ensure the accuracy of data during transmission and decompression and reduce data errors; automatically adjust the strategy according to different network environments and data types to enhance the system's adaptive ability. The node collaborative work submodule realizes information transmission and collaborative work between submodules through the data sharing mechanism; based on the shared data, each submodule dynamically adjusts its own strategy to achieve the best data transmission effect; the transmission path selection submodule passes the optimal path information to the receiving and decompression submodule to predict the arrival time of the data packet and the possible compression strategy; the data encapsulation and compression submodule passes the selected compression strategy to the receiving and decompression submodule to ensure the correctness of data decompression.The significance achieved: Through the collaborative work between nodes, efficient and reliable data transmission is achieved; according to real-time data and policy adjustments, the data transmission path and compression strategy are optimized to improve transmission efficiency; through path information transmission and policy synchronization, the arrival and decompression of data packets are predicted and prepared in advance to reduce delays and errors.

[0096] In summary, the remote communication and data transmission module of this embodiment realizes efficient, reliable and adaptive data transmission. Each submodule ensures the quality and efficiency of data during transmission through real-time monitoring, dynamic adjustment and information transmission. It not only improves the efficiency and reliability of data transmission, but also enhances the adaptive ability of the system, enabling it to maintain stable performance in a complex network environment.

[0097] Example 5: Figure 5 As shown, based on Example 1, the optimization algorithm and safety control module provided by the embodiment of the present invention include:

[0098] The initial state assessment submodule is responsible for the preliminary state assessment of the magnetic conversion power optimization algorithm model. Through statistical analysis and rule engine, it is determined whether the current operating state of the ship is within the normal range. If it is within the normal range, the preliminary state assessment will continue; if it is not within the normal range, the in-depth state assessment will be started.

[0099] The deep state assessment submodule is responsible for obtaining real-time data such as magnetic field change trend and power output stability from the magnetic conversion power state parameters. Combining historical data and real-time data, the magnetic conversion power optimization algorithm model conducts a deep assessment of the ship's operating state and obtains the state assessment results.

[0100] The risk probability prediction submodule is responsible for identifying potential risk factors and screening out risk factors that may affect the safe operation of ships; combining real-time data and historical data to predict the probability of occurrence of each potential risk factor and obtain the final risk prediction result.

[0101] Among them, the construction process of the magnetic conversion power optimization algorithm model: collect various data during ship operation, including magnetic field changes, power output and environmental parameters; process noise, missing values, etc. in the data; annotate the data to distinguish normal and abnormal states; extract features related to magnetic conversion power from the original data, such as magnetic field strength, power output stability, etc.; divide the data set into training set, validation set and test set; use the training set to train the magnetic conversion power optimization algorithm model, and adjust the parameters of the magnetic conversion power optimization algorithm model to optimize performance; adjust the hyperparameters of the magnetic conversion power optimization algorithm model through the validation set, such as learning rate, regularization coefficient, etc.; use the test set to evaluate the performance of the model, including indicators such as accuracy, recall rate and F1 score.

[0102] The working principle and beneficial effects of the above technical scheme are as follows: the initial state assessment submodule of this embodiment performs a preliminary state assessment, and through statistical analysis and rule engine, determines whether the current operating state of the ship is within the normal range; within the normal range, continue to perform preliminary state assessment; if not within the normal range, start deep state assessment; the deep state assessment submodule obtains real-time data such as magnetic field change trend and power output stability from the magnetic conversion power state parameters, and combines historical data and real-time data. The magnetic conversion power optimization algorithm model performs a deep assessment of the ship's operating state and obtains the state assessment result; the risk probability prediction submodule identifies potential risk factors and screens out risk factors that may affect the safe operation of the ship; combined with real-time data and historical data, predicts the probability of occurrence of each potential risk factor, and obtains the final risk prediction result. The initial state assessment submodule of the above scheme monitors the operating state of the ship in real time through statistical analysis and rule engine to ensure that it is within the normal range; conducts a preliminary assessment of the ship's magnetic conversion power to determine whether it needs further deep assessment. Significance achieved: By quickly judging the status of the ship, unnecessary in-depth evaluation can be avoided, computing resources and time can be saved; potential problems can be discovered in time to prevent small problems from turning into major failures, and the reliability and safety of the ship can be improved. The in-depth status evaluation submodule combines real-time data and historical data to conduct an in-depth analysis of the ship's magnetic field change trend and power output stability; through the magnetic conversion power optimization algorithm model, a more accurate operation status evaluation result is obtained. Significance achieved: Provide detailed status evaluation to help ship managers make more scientific decisions; through in-depth analysis, optimize the ship's operating parameters, improve operating efficiency and energy utilization. The risk probability prediction submodule identifies and screens potential risk factors that may affect the safe operation of the ship; combines real-time data and historical data to predict the probability of occurrence of each potential risk factor. Significance achieved: Early warning of potential risks, providing decision support for ship managers, and reducing the possibility of accidents; through scientific risk prediction, improve the safety and stability of ship operation, and ensure the safety of personnel and property.

[0103] In summary, the submodules of this embodiment together constitute a complete safety control system, which ensures that ships can operate safely and efficiently in various complex environments through real-time monitoring, in-depth analysis and risk prediction. It not only improves the operating efficiency of ships, but also greatly enhances their safety and reliability, providing strong technical support for ship managers and operators.

[0104] Example 6: Figure 6 As shown, based on Example 5, the initial state evaluation submodule provided in this embodiment of the present invention includes:

[0105] The statistical identification unit is responsible for calculating the mean, variance, extreme value and other statistical quantities of the magnetic conversion dynamic state parameters, obtaining the distribution characteristics of the magnetic conversion dynamic state parameters; using statistical methods to detect abnormal points in the magnetic conversion dynamic state parameters and identifying possible abnormal states;

[0106] The rule matching unit is responsible for building a series of rules based on historical data and expert knowledge to define the boundary conditions for the normal operation of the ship; matching the current magnetic conversion power state parameters with the rules in the rule base to determine whether the ship's operating state meets the standards for normal operation;

[0107] The status judgment unit is responsible for judging whether the ship's operating status is within the normal range based on the results of statistical analysis and rule matching; if it meets the normal standards, it will continue with the preliminary status assessment; if it does not meet the standards, it will start the in-depth status assessment.

[0108] The working principle and beneficial effects of the above technical solution are as follows: the statistical identification unit of this embodiment calculates the mean, variance and extreme value of the magnetic conversion power state parameters to obtain the distribution characteristics of the magnetic conversion power state parameters; the abnormal points in the magnetic conversion power state parameters are detected by statistical methods to identify possible abnormal states; the rule matching unit builds a series of rules based on historical data and expert knowledge to define the boundary conditions for normal operation of the ship; the current magnetic conversion power state parameters are matched with the rules in the rule base to determine whether the operating state of the ship meets the standard for normal operation; the state judgment unit determines whether the operating state of the ship is within the normal range according to the results of statistical analysis and rule matching; if it meets the normal standard, the preliminary state assessment is continued; if it does not meet the standard, the deep state assessment is started. The statistical identification unit of the above scheme can fully understand the distribution characteristics of these parameters by calculating the mean, variance and extreme value of the magnetic conversion power state parameters; the abnormal points are detected by statistical methods, and potential abnormal states can be discovered in time to provide data support for state assessment. Significance: The statistical analysis method can help quickly identify abnormal conditions in the operation of the ship, thereby providing early warning, avoiding possible failures or accidents, and ensuring the safe operation of the ship. Rule matching unit: The rule base built based on historical data and expert knowledge can define the boundary conditions for the normal operation of the ship; by matching the current magnetic conversion power state parameters with the rules in the rule base, it can accurately determine whether the ship's operating status meets the normal standards. Significance: The rule matching unit provides an evaluation method based on experience and knowledge to ensure that the ship can maintain the best state under various operating conditions and improve the stability and reliability of operation. State judgment unit: Based on the results of statistical analysis and rule matching, the state judgment unit can comprehensively evaluate the operating status of the ship; if it meets the normal standards, it will continue to conduct preliminary state evaluation; if it does not meet the standards, it will start a deep state evaluation to further analyze the root cause of the problem. Significance: The state judgment unit ensures the comprehensiveness and depth of the evaluation process, and can take timely measures to prevent the problem from expanding and ensure the continuous and safe operation of the ship when the ship's operating status is abnormal.

[0109] In summary, the initial state assessment submodule of this embodiment realizes a comprehensive and accurate assessment of the ship's operating status through three steps: statistical identification, rule matching, and state judgment. This not only improves the safety and reliability of ship operation, but also provides a scientific basis for ship maintenance and management.

[0110] Example 7: Figure 7 As shown, based on Example 5, the depth state assessment submodule provided in this embodiment of the present invention includes:

[0111] The input layer processing unit is responsible for inputting the characteristic data of the extracted magnetic conversion dynamic state parameters into the input layer of the magnetic conversion dynamic optimization algorithm model, and the input layer performs preliminary processing on the magnetic conversion dynamic state parameters;

[0112] The hidden layer analysis unit is responsible for extracting feature data three times, fusing the weighted feature data, and generating new feature representations for deep state assessment;

[0113] Among them, the first hidden layer performs preliminary nonlinear transformation on the input feature data through the fully connected layer and activation function to extract primary features;

[0114] In the fully connected layer, the input feature data is linearly transformed through the weight matrix and bias term, and then nonlinearity is introduced through the ReLU activation function to extract primary features;

[0115] Randomly discard some neurons through Dropout technology;

[0116] The second hidden layer performs in-depth analysis of primary features through convolutional layers to capture the trend of magnetic field changes and power output stability;

[0117] The convolution layer uses multiple convolution kernels to perform convolution operations on primary features, extract local features, and capture local patterns of magnetic field changes;

[0118] The pooling layer reduces the dimension of the output of the convolutional layer through the maximum pooling operation while retaining important features;

[0119] The long short-term memory network layer processes the time series data in the feature data, captures the time dependence of the magnetic field change, and extracts the long-term trend of the power output;

[0120] The third hidden layer weights the key features through the attention mechanism;

[0121] The attention mechanism calculates the attention weight of each feature, and weights the features according to the weight to highlight the impact of important features;

[0122] Feature fusion fuses the weighted features to generate new feature representations for final state evaluation;

[0123] The output layer generation unit is responsible for generating multiple state evaluation indicators through the fully connected layer and activation function (such as Sigmoid or Softmax);

[0124] The fully connected layer inputs the fused features into the fully connected layer and generates state evaluation indicators through linear transformation and activation function;

[0125] The activation function uses Sigmoid or Softmax function to normalize the output to ensure that the evaluation index is within a reasonable range.

[0126] The working principle and beneficial effects of the above technical solution are as follows: the input layer processing unit of this embodiment inputs the feature data of the extracted magnetic conversion power state parameters into the input layer of the magnetic conversion power optimization algorithm model, and the input layer performs preliminary processing on the magnetic conversion power state parameters; the hidden layer analysis unit extracts the feature data three times, fuses the weighted feature data, and generates a new feature representation for deep state evaluation; wherein, the first hidden layer performs a preliminary nonlinear transformation on the input feature data through the fully connected layer and the activation function to extract the primary features; in the fully connected layer, the input feature data is linearly transformed through the weight matrix and the bias term, and then the nonlinearity is introduced through the ReLU activation function to extract the primary features; some neurons are randomly discarded through the Dropout technology; the second hidden layer performs a deep analysis of the primary features through the convolution layer to capture the magnetic field change trend and the power output stability; the convolution layer uses multiple convolution kernels to perform convolution operations on the primary features to extract local features , capturing the local pattern of magnetic field changes; the pooling layer reduces the dimension of the output of the convolution layer through the maximum pooling operation while retaining important features; the long short-term memory network layer processes the time series data, captures the time dependence of magnetic field changes, and extracts the long-term trend of power output; the third hidden layer weights the key features through the attention mechanism; the attention mechanism calculates the attention weight of each feature, and weights the features according to the weight to highlight the influence of important features; feature fusion fuses the weighted features to generate a new feature representation for the final state evaluation; the output layer generation unit generates multiple state evaluation indicators through the fully connected layer and the activation function (such as Sigmoid or Softmax); the fully connected layer inputs the fused features into the fully connected layer, and generates the state evaluation indicators through linear transformation and activation function; the activation function uses Sigmoid or Softmax function to normalize the output to ensure that the evaluation indicators are within a reasonable range. The input layer processing unit of the above scheme performs preliminary processing on the input magnetic conversion power state parameters to ensure that the data format and quality meet the requirements of subsequent analysis. Significance: Provide high-quality input data for in-depth analysis to ensure the accuracy and stability of the entire model. The hidden layer analysis unit generates new feature representations through three extractions and weighted fusion to enhance the expressiveness of features. Significance: Improve the feature extraction capability of the model, so that the model can more accurately capture the key information of the magnetic conversion dynamic state. The first hidden layer enhances the nonlinear modeling capability of the model, and at the same time improves the generalization capability of the model through the Dropout technology to avoid overfitting on the training data. The second hidden layer enhances the model's ability to capture the trend of magnetic field changes and the stability of power output, and at the same time reduces the computational complexity through dimensionality reduction to improve the efficiency of the model. The long short-term memory network layer enhances the model's ability to process time series data, so that the model can better understand the historical trend of magnetic field changes and improve the accuracy of state assessment.The third hidden layer enhances the model's ability to identify and utilize key features, allowing the model to more accurately evaluate the state of magnetic conversion dynamics. Feature fusion improves the comprehensive expression of features, allowing the model to more comprehensively evaluate the state of magnetic conversion dynamics. The output layer generation unit generates accurate and easy-to-interpret state evaluation indicators, providing a reliable basis for decision-making.

[0127] In summary, the deep state assessment submodule of this embodiment extracts valuable features from complex magnetic conversion dynamic state parameters through multi-level processing and analysis, and finally generates accurate state assessment indicators. It not only improves the accuracy and stability of the model, but also enhances the generalization ability of the model and the ability to identify key features, providing strong support for the assessment of magnetic conversion dynamic state.

[0128] Example 8: Figure 8 As shown, based on Example 7, the hidden layer analysis unit provided in this embodiment of the present invention includes:

[0129] The signal generation subunit is responsible for generating a supervisory signal using the first half of the time series data and the second half of the time series data predicted by the magnetic conversion dynamic optimization algorithm model;

[0130] The relational learning subunit is responsible for generating multiple views by randomly cropping and flipping the time series data. Through comparative learning tasks, the magnetic conversion dynamics optimization algorithm model learns the invariance characteristics between different views. It generates supervision signals by predicting the characteristic value of a certain time point based on the characteristics of the time series data, so that the magnetic conversion dynamics optimization algorithm model learns the intrinsic relationship between the features.

[0131] The weighted fusion subunit is responsible for further optimizing the feature extraction capability of the model through the supervision signal generated by self-supervised learning; feature fusion fuses the weighted features to generate a new feature representation for the final state evaluation.

[0132] The working principle and beneficial effects of the above technical solution are as follows: the signal generation subunit of this embodiment uses the first half of the time series data to generate a supervisory signal through the second half of the time series data predicted by the magnetic conversion power optimization algorithm model; the relationship learning subunit generates multiple views by randomly cropping and flipping the time series data, and enables the magnetic conversion power optimization algorithm model to learn the invariance characteristics between different views through the comparative learning task; the supervisory signal is generated by predicting the feature value of a certain time point based on the features of the time series data, so that the magnetic conversion power optimization algorithm model learns the intrinsic relationship between the features; the weighted fusion subunit further optimizes the feature extraction ability of the model through the supervisory signal generated by self-supervised learning; the feature fusion fuses the weighted features to generate a new feature representation for the final state evaluation. The prediction ability of the signal generation subunit of the above scheme is based on the magnetic conversion power optimization algorithm model, which can capture the dynamic changes and trends in the time series. Significance: The subunit provides a forward-looking supervisory signal for the model, so that the model can better understand and predict future data changes; it is particularly important for application scenarios that require real-time decision-making. The relationship learning subunit helps the model learn the invariance characteristics between different views through the comparative learning task. In addition, the feature value at a certain point in time can be predicted based on the features of the time series data to generate a supervisory signal. Significance: The subunit enhances the model's understanding of the intrinsic relationship of the time series data, enabling the model to better identify and utilize patterns and regularities in the data; it is of great significance to improve the generalization and robustness of the model, especially in scenarios with high data diversity and complexity. The weighted fusion subunit further optimizes the model's feature extraction capabilities, fuses the weighted features, and generates a new feature representation for the final state assessment. Significance: The subunit improves the model's comprehensive analysis capabilities through feature fusion, enabling the model to more accurately evaluate and predict the state of complex systems; this is particularly important for application scenarios that require the integration of multiple features for decision-making.

[0133] In summary, the various subunits of the hidden layer analysis unit of this embodiment jointly improve the model's processing capability and prediction accuracy for time series data through their own technical means, providing strong support for intelligent decision-making of various complex systems.

[0134] Identify potential risk factors and screen out risk factors that may affect the safe operation of ships; combine real-time data and historical data to predict the probability of occurrence of each potential risk factor and obtain the final risk prediction results.

[0135] Example 9: Fig. 9 As shown, based on Example 5, the risk probability prediction submodule provided by the embodiment of the present invention includes:

[0136] The hierarchical division unit is responsible for calculating the characteristic values ​​of risk factors and calculating the corresponding probability of occurrence of the characteristic values ​​through the probability density function; the risk factors are divided into multiple levels according to the probability density function, including extremely high, high, medium, low and extremely low, and each level corresponds to a different risk level and response strategy;

[0137] Among them, the expression of probability density function is:

[0138]

[0139] Wherein, f(x; α, β, γ) represents a new probability density function, which represents the probability density of the random variable x at a specific value x, x represents the value of the random variable, that is, the characteristic value of the risk factor, α represents the location parameter, which represents the central position or benchmark value of the random variable x; in risk management, the location parameter can represent the benchmark level of the risk factor, β represents the scale parameter, which represents the scale or range of the random variable x; in risk management, the scale parameter can represent the fluctuation range of the risk factor, and γ represents the shape parameter, which represents the shape characteristics of the random variable x; in risk management, the shape parameter can represent the distribution form of the risk factor. This is part of the normalization constant that ensures that the integral of the probability density function is equal to 1 over the entire real number range;

[0140] The threshold adjustment unit is responsible for adjusting the risk level threshold based on historical data and real-time data;

[0141] The measure triggering unit is responsible for automatically triggering corresponding control measures according to the risk level, such as adjusting operating parameters, starting backup systems or issuing emergency alarms.

[0142] The working principle and beneficial effects of the above technical solution are as follows: the hierarchical division unit of this embodiment calculates the characteristic value of the risk factor, and calculates the occurrence probability corresponding to the characteristic value through the probability density function; the risk factors are divided into multiple levels according to the probability density function, including extremely high, high, medium, low and extremely low, and each level corresponds to a different risk level and response strategy; the threshold adjustment unit adjusts the threshold of the risk level according to historical data and real-time data; the measure triggering unit automatically triggers the corresponding control measures according to the risk level, such as adjusting operating parameters, starting the backup system or issuing an emergency alarm. The hierarchical division unit of the above scheme extracts characteristic values ​​from various data sources, and the module can quantify risk factors and provide basic data for probability calculation; the probability density function is used to calculate the occurrence probability corresponding to the characteristic value, which can accurately predict the possibility of risk events; the risk factors are divided into five levels: extremely high, high, medium, low and extremely low, and each level corresponds to a different risk level and response strategy, making risk management more refined. Significance achieved: Through hierarchical division, risks of different levels can be more accurately identified and managed; different levels correspond to different response strategies, so that the most appropriate measures can be taken quickly when risks occur, improving decision-making efficiency and response speed; through refined management, it can effectively reduce the failure or loss of the system caused by risk events, and enhance the stability and reliability of the system. The threshold adjustment unit analyzes historical data, and the module can identify the long-term trend and pattern of risk events, providing a basis for threshold adjustment; real-time monitoring of current data can timely discover changes in risk factors and dynamically adjust the threshold of risk level; according to changes in historical and real-time data, the threshold of risk level is automatically adjusted, making risk assessment more accurate and timely. Significance achieved: Through dynamic adjustment of thresholds, the current risk situation can be more accurately reflected, avoiding misjudgment caused by fixed thresholds; real-time data monitoring and dynamic threshold adjustment enable the system to adapt to various complex and changing environments, improving the adaptability and flexibility of the system; through precise threshold adjustment, the risk of false alarms and missed alarms can be effectively reduced, and the efficiency and effectiveness of risk management can be improved. The measure trigger unit automatically triggers corresponding control measures according to the risk level, such as adjusting operating parameters, starting backup systems or issuing emergency alarms, to achieve automated response; according to specific circumstances, the intensity and scope of control measures can be flexibly adjusted to ensure the effectiveness and pertinence of the measures; when risk events occur, actions can be taken quickly to reduce the impact and losses of risk events. Significance achieved: Automatically triggering control measures can respond quickly when risk events occur, reduce response time, and reduce the impact of risk events; automated response mechanism reduces the need for human intervention, reduces the possibility of human error, and improves system reliability; through timely and effective control measures, the impact of risk events on the system can be effectively reduced, and the security and stability of the system can be enhanced.

[0143] In summary, the risk probability prediction submodule of this embodiment can realize refined, dynamic and automated risk management, and improve the stability, security and adaptability of the system.

[0144] Example 10: Fig.10 As shown, based on Example 9, the threshold adjustment unit provided in this embodiment of the present invention includes:

[0145] The cumulative probability determination subunit is responsible for determining the cumulative probability corresponding to each risk level according to the risk level classification;

[0146] The threshold calculation subunit is responsible for calculating the threshold corresponding to each risk level using the threshold model expression;

[0147] T i =α+β·(-ln(1-p i )) 1 / γ

[0148] Where, T i represents the threshold of the ith risk level, p i represents the cumulative probability of the i-th risk level, that is, P(X≤T i ), α, β, γ are the same as the parameters in the probability density function, representing the location parameter, scale parameter, and shape parameter respectively;

[0149] The dynamic adjustment subunit is responsible for combining real-time data and dynamically adjusting parameters to adapt to environmental changes and fluctuations in risk factors.

[0150] The working principle and beneficial effects of the above technical solution are as follows: the cumulative probability determination subunit of this embodiment determines the cumulative probability corresponding to each risk level according to the risk level division; the threshold calculation subunit uses the threshold model expression to calculate the threshold corresponding to each risk level; the dynamic adjustment subunit combines real-time data to dynamically adjust parameters to adapt to environmental changes and fluctuations in risk factors. The cumulative probability determination subunit of the above scheme determines the cumulative probability corresponding to each risk level according to the risk level division, ensuring that the risk level division is both reasonable and accurate; based on historical data and statistical analysis, the cumulative probability of each risk level is calculated to ensure the scientificity and objectivity of risk assessment. The significance achieved: Through accurate cumulative probability, the risk is quantified, making risk management more intuitive and operational; providing accurate risk level information to the management to support its judgment and choice in risk management decisions. The threshold calculation subunit accurately calculates the threshold corresponding to each risk level; the parameters of the probability density function are applied to the threshold calculation to ensure that the threshold calculation is consistent with the theoretical model and meets actual needs. Significance achieved: Through the calculated thresholds, the boundaries of each risk level are clarified, making risk management clearer and more targeted; providing accurate thresholds for the risk warning system to ensure that warnings can be issued in a timely manner when the risk reaches or exceeds the threshold. Dynamic adjustment of subunits ensures that the model can adapt to environmental changes and fluctuations in risk factors; by continuously adjusting parameters, the model is adaptive and can maintain high accuracy in different environments and conditions. Significance achieved: Ensure that the risk management model can adapt to the changing environment and risk factors, and improve the practicality and reliability of the model; through dynamic adjustment, continuously optimize the risk management model to ensure that it remains efficient and accurate in long-term applications.

[0151] In summary, this embodiment enables the threshold adjustment unit to play an important role in risk management. Through precise cumulative probability determination, accurate threshold calculation and dynamic parameter adjustment, the risk management model is ensured to be both scientific and practical.

[0152] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of equivalent technologies of the present invention, the present invention is also intended to include these modifications and variations.

Claims

1. A remote monitoring system for ship magnetic conversion power status, characterized in that: Include: The magnetic conversion power parameter acquisition module is responsible for capturing the magnetic field changes of the ship under different working conditions and the magnetic conversion power state parameters of the power output through multiple data acquisition devices; The remote communication and data transmission module is responsible for transmitting the collected magnetic conversion power state parameters to the remote control center through the adaptive communication protocol; the adaptive communication protocol automatically adjusts the transmission rate and data compression method according to the network conditions; The optimization algorithm and safety control module is responsible for running in the remote control center, receiving and analyzing the transmitted magnetic conversion power state parameters; through the built-in magnetic conversion power optimization algorithm model, it evaluates the operating status of the ship in real time and predicts potential risks; when an abnormality is detected, it activates the fluid-actuated safety equipment and notifies relevant personnel through the remote fault warning system.

2. The ship magnetic conversion power state remote monitoring system according to claim 1, characterized in that: Magnetic conversion dynamic parameter acquisition module, including: The network architecture submodule is responsible for building a distributed network consisting of multiple nodes. Various sensors are installed at various key parts of the ship to capture the magnetic conversion power state parameters and transmit them to multiple nodes of the distributed processing network through the network. The nodes include sensor nodes, intermediate nodes and central nodes, and the nodes are interconnected through the network. The weighted fusion submodule is responsible for evaluating the quality of each data source of the magnetic conversion dynamic state parameter and generating an initial quality score for each data source; Calculate the real-time quality score of the data source and dynamically update the weight of each data source; perform weighted processing on the magnetic conversion dynamic state parameters according to the weight of each data source and calculate the weighted average value; The parameter storage submodule is responsible for using distributed storage to disperse and store the fused magnetic conversion dynamic state parameters on multiple nodes of the distributed network.

3. The ship magnetic conversion power state remote monitoring system according to claim 1, characterized in that: Remote communication and data transmission module, including: The data encapsulation and compression submodule is responsible for intelligently encapsulating the collected magnetic conversion dynamic state parameters and dynamically selecting the data compression algorithm based on the real-time network bandwidth and delay conditions and the adaptive communication protocol; The transmission path selection submodule is responsible for selecting the optimal transmission path by using multi-path routing technology when the data packet is sent through the remote communication and data transmission modules; The receiving and decompression submodule is responsible for dynamically adjusting the decompression parameters according to the compression strategy of the sender after the remote control center receives the data packet. The decompressed magnetic conversion power state parameters are analyzed in real time, and the storage strategy is selected to determine the storage device.

4. The ship magnetic conversion power state remote monitoring system according to claim 3, characterized in that: The remote communication and data transmission module also includes: The master node setting submodule is responsible for taking network bandwidth and delay conditions, multi-path routing technology and compression strategy as master nodes respectively. Network bandwidth and delay conditions are used to set master nodes through network probes, multi-path routing technology is used to set master nodes through network scanning, and compression strategies formulate different compression strategies. The slave node setting submodule is responsible for dynamically selecting the compression algorithm based on the real-time bandwidth and delay data provided by the network bandwidth and delay conditions; the slave node optimal transmission path selects the transmission path with the best performance based on the path evaluation results provided by the master node multi-path routing technology; the slave node dynamically adjusts the decompression parameters based on the compression strategy transmitted by the master node compression strategy; The node collaboration submodule is responsible for implementing the data encapsulation and compression submodule to obtain bandwidth and delay data from the network bandwidth and delay of the master node, and the transmission path selection submodule to obtain the path evaluation results from the multi-path routing technology of the master node; according to the shared data, the data encapsulation and compression submodule and the transmission path selection submodule dynamically adjust their respective strategies; The transmission path selection submodule passes the selected optimal path information to the receiving and decompression submodule to predict the arrival time of the data packet and the possible compression strategy; the data encapsulation and compression submodule passes the selected compression strategy to the receiving and decompression submodule to correctly decompress the data.

5. The ship magnetic conversion power state remote monitoring system according to claim 1, characterized in that: Optimization algorithm and safety control module, including: The initial state assessment submodule is responsible for the preliminary state assessment of the magnetic conversion power optimization algorithm model. Through statistical analysis and rule engine, it is determined whether the current operating state of the ship is within the normal range. If it is within the normal range, the preliminary state assessment will continue. If it is not within the normal range, initiate a deep status assessment; The deep state assessment submodule is responsible for obtaining the magnetic field change trend and real-time data of power output stability from the magnetic conversion power state parameters. Combining historical data and real-time data, the magnetic conversion power optimization algorithm model conducts a deep assessment of the ship's operating state and obtains the state assessment results. The risk probability prediction submodule is responsible for identifying potential risk factors and screening out risk factors that may affect the safe operation of the ship; Combine real-time data with historical data to predict the probability of occurrence of each potential risk factor and obtain the final risk prediction result.

6. The ship magnetic conversion power state remote monitoring system according to claim 5, characterized in that: The initial state assessment submodule includes: The statistical identification unit is responsible for calculating the mean, variance and extreme value statistics of the magnetic conversion dynamic state parameters, obtaining the distribution characteristics of the magnetic conversion dynamic state parameters; using statistical methods to detect abnormal points in the magnetic conversion dynamic state parameters and identify possible abnormal states; The rule matching unit is responsible for building a series of rules based on historical data and expert knowledge to define the boundary conditions for the normal operation of the ship; matching the current magnetic conversion power state parameters with the rules in the rule base to determine whether the ship's operating state meets the standards for normal operation; The status judgment unit is responsible for judging whether the ship's operating status is within the normal range based on the results of statistical analysis and rule matching; if it meets the normal standards, it will continue with the preliminary status assessment; if it does not meet the standards, it will start the in-depth status assessment.

7. The ship magnetic conversion power state remote monitoring system according to claim 5, characterized in that: The deep state assessment submodule includes: The input layer processing unit is responsible for inputting the characteristic data of the extracted magnetic conversion dynamic state parameters into the input layer of the magnetic conversion dynamic optimization algorithm model, and the input layer performs preliminary processing on the magnetic conversion dynamic state parameters; The hidden layer analysis unit is responsible for extracting feature data three times, fusing the weighted feature data, and generating new feature representations for deep state assessment; The output layer generation unit is responsible for generating multiple state evaluation indicators through the fully connected layer and activation function.

8. The ship magnetic conversion power state remote monitoring system according to claim 7, characterized in that: Hidden layer analysis unit, including: The signal generation subunit is responsible for generating a supervisory signal using the first half of the time series data and the second half of the time series data predicted by the magnetic conversion dynamic optimization algorithm model; The relational learning subunit is responsible for generating multiple views by randomly cropping and flipping the time series data. Through comparative learning tasks, the magnetic conversion dynamic optimization algorithm model learns the invariance characteristics between different views; by predicting the characteristic value of a certain time point based on the characteristics of the time series data, a supervision signal is generated, so that the magnetic conversion dynamic optimization algorithm model learns the intrinsic relationship between the features; The weighted fusion subunit is responsible for further optimizing the feature extraction capability of the model through the supervision signal generated by self-supervised learning; feature fusion fuses the weighted features to generate a new feature representation for the final state evaluation.

9. The ship magnetic conversion power state remote monitoring system according to claim 5, characterized in that: The risk probability prediction submodule includes: The hierarchical division unit is responsible for calculating the characteristic values ​​of risk factors and calculating the corresponding probability of occurrence of the characteristic values ​​through the probability density function; the risk factors are divided into multiple levels according to the probability density function, including extremely high, high, medium, low and extremely low, and each level corresponds to a different risk level and response strategy; The threshold adjustment unit is responsible for adjusting the risk level threshold based on historical data and real-time data; The measure triggering unit is responsible for automatically triggering corresponding control measures according to the risk level, such as adjusting operating parameters, starting the backup system or issuing an emergency alarm.

10. The ship magnetic conversion power state remote monitoring system according to claim 9, characterized in that: Threshold adjustment unit, comprising: The cumulative probability determination subunit is responsible for determining the cumulative probability corresponding to each risk level according to the risk level classification; The threshold calculation subunit is responsible for calculating the threshold corresponding to each risk level using the threshold model expression; The dynamic adjustment subunit is responsible for combining real-time data and dynamically adjusting parameters to adapt to environmental changes and fluctuations in risk factors.

Images