A security and monitoring system for a methanol fuel powered marine vessel

Abstract

The application provides a kind of security and monitoring system of methanol fuel power ship, security and monitoring system includes: parameter acquisition module, data analysis module and alarm output module.The application improves the safety and operating efficiency of methanol fuel power ship, specifically includes: timely monitoring the key parameters in the operation process of methanol fuel, discovering potential safety risks, avoiding accidents;Data analysis module provides early warning signal through analysis of parameter data, helps ship operator to take measures in time, avoids the development of failure or safety hazard;Alarm output module not only triggers alarm, but also provides the location information of alarm device and failure prediction result, provides accurate guidance and decision basis for rescue and maintenance;Can improve the safety, reliability and operating efficiency of methanol fuel power ship, protect the safety of ship personnel and environment, promote sustainable development.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring equipment technology, and in particular to a security and monitoring system for methanol-fueled ships. Background Technology

[0002] Methanol, as an alternative fuel, will inevitably become an important component of energy diversification, especially in regions with abundant coal resources and relatively scarce oil resources. Methanol fuel offers a significant development opportunity for my country's energy industry, reducing dependence on oil resources to a certain extent while also greatly benefiting environmental protection. Simultaneously, methanol diesel engines and other related equipment will have broader development prospects in this era of diversification. The security system for methanol-powered ships aims to ensure the safety and reliability of vessels using methanol as fuel. While methanol, as a clean marine fuel, boasts good economics, safety, and availability, it also possesses unique physical and chemical properties, such as a low flash point and a certain degree of toxicity. This necessitates specific safety measures and systems to ensure its safe use. However, the current lack of a dedicated security system for methanol-fueled ships results in low accuracy in methanol fuel monitoring, leading to poor navigational safety.

[0003] Prior art 1, application number: CN 202410122842.8, discloses a ship-shore collaborative integrated safety status monitoring system, including a memory and a processor. The processor executes a computer program stored in the memory to achieve the following steps: acquiring monitoring data of different ships at each collection time; obtaining the corresponding correlation degree based on the differences between the monitoring data of each ship at each collection time and the monitoring data of other ships, and the differences between the monitoring data and the data measured by the ship and the shore; clustering the monitoring data of all ships to obtain each cluster based on the similarity of the correlation degree of each ship with other ships at each collection time; and filtering target monitoring data based on the correlation degree of all collection times within the cluster where each ship is located at each collection time, thereby monitoring the integrated safety status of the ship. This invention improves the accuracy of the integrated safety status monitoring results of ships. However, it lacks specialized monitoring devices and only judges the safety status based on the monitoring data of the ships, without realizing the monitoring of the ships themselves. In particular, the means of ensuring and monitoring methanol are limited, and it cannot monitor the operation process, resulting in poor safety of ship navigation.

[0004] Prior art two, application number: CN 202311830293.1, discloses a method, apparatus, device, and readable storage medium for generating a ship monitoring interface. The method includes: obtaining the display requirements of the monitoring interface; generating an SVG file based on the display requirements, the SVG file including the object display attributes of the target monitored object; obtaining the monitoring protocol of the ship monitoring system; generating monitoring point information based on the monitoring protocol, the monitoring point information including the monitoring point ID and the model display attributes of the monitoring point; associating the monitoring point information with the SVG file according to the monitoring point ID to obtain an executable file; loading the executable file into the execution program to execute the display of the monitoring interface. Although this simplifies the development process and improves efficiency and accuracy, its functionality is limited and it does not address the control of methanol fuel, making it unsuitable for methanol-fueled ships.

[0005] Prior art three, application number CN 202310612423.8, discloses a method and management system for extracting effective segments from ship monitoring videos. The extraction algorithm includes video preprocessing; baseline video establishment; initial video extraction; effective segment extraction; and effective segment storage management. The system adopts a ship-to-shore structure, including a video acquisition module, a video grayscale module, an effective segment detection module, a data management module, a visualization module, and a communication module. Although the video preprocessing and baseline video establishment effectively improve the efficiency and accuracy of ship monitoring video processing, and the initial video extraction and effective segment extraction can accurately identify effective segments in the ship monitoring video, increasing the video's utilization value, its structure is relatively simple, its security is poor, and it cannot effectively improve the safety factor during ship navigation.

[0006] Current technologies 1, 2, and 3 suffer from relatively simple ship structures and functions, resulting in inadequate fuel safety measures and limited fuel monitoring methods, failing to effectively improve safety. Therefore, this invention provides a security and monitoring system for methanol-fueled ships. This system can detect potential safety risks immediately and trigger alarms and emergency responses. The system employs a highly integrated monitoring platform capable of real-time monitoring of key parameters of the methanol fuel supply system. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a security and monitoring system for methanol-fueled ships, comprising:

[0008] The parameter acquisition module is responsible for setting up combustible gas detectors, liquid leak detectors, and oxygen concentration sensors at key locations on methanol-fueled ships to acquire data during the methanol fuel operation process.

[0009] The data analysis module is responsible for analyzing the acquired data to obtain the analysis results of methanol data during the operation of methanol-fueled ships.

[0010] The alarm output module is responsible for triggering an alarm when the analysis results reach the alarm threshold, acquiring the location coordinates of the monitoring device that triggered the alarm, analyzing the alarm content, and obtaining fault prediction results.

[0011] Optional, parameter acquisition module, including:

[0012] The component screening submodule is responsible for obtaining the path model of methanol fuel from storage to combustion and discharge. Based on the operating conditions of the preset key components in the path model during normal operation, and combined with historical safety accident data, the preset key components are screened to obtain the screened key components, which are then designated as the first category of key locations.

[0013] The region determination submodule is responsible for collecting 3D point cloud data of the structure of methanol-fueled vessels and obtaining the inspection point set of methanol-fueled vessels. It performs point cloud segmentation on the 3D point cloud data of the structure to obtain new 3D point cloud data of the structure, and constructs a fenced area based on the new 3D point cloud data of the structure. Based on the new 3D point cloud data of the structure and the fenced area, it determines the installation area of ​​the monitoring equipment. Based on the positional weight of the structure of the methanol-fueled vessel and the distance to key components and pipelines in the path model, it selects the second type of key location from the installation area.

[0014] The location integration submodule is responsible for integrating the first and second types of key locations according to the identification of the path model and the 3D point cloud data of the structure, to obtain the key locations of the monitoring equipment installed on methanol fuel-powered ships, and marking them according to the location and attributes of the monitoring equipment.

[0015] Optional, location integration submodule, includes:

[0016] The equipment labeling unit is responsible for acquiring attribute information, including equipment type, sensor type, and monitoring parameters, for each monitoring device; and labeling the monitoring devices with icons based on the acquired location and attribute information.

[0017] The relationship establishment unit is responsible for obtaining location, attribute information and icons from the electronic data spreadsheet. In the electronic data spreadsheet, it finds the column used to store the location and attribute information of the monitoring equipment, and associates the column with the corresponding column in the electronic data spreadsheet to establish a data relationship.

[0018] The autofill cell is responsible for automatically filling the content of the spreadsheet using formulas based on data relationships. Specifically, for location information, the INDEX formula is used to find and obtain the corresponding location coordinates; for attribute information, the VLOOKUP formula is used to find and obtain the corresponding attribute value; and for icons, the conditional formatting function is used to automatically set the corresponding icon based on the attribute value.

[0019] Optional, data analysis module, including:

[0020] The model acquisition submodule is responsible for using historical data as training and testing sets to build a data mining and analysis model, and at the same time, it realizes wireless communication with the monitoring equipment through an interface.

[0021] The data processing submodule is responsible for acquiring data collected by monitoring equipment, obtaining preprocessed data based on the data, removing mismatched data according to the correspondence between the location and attribute information of the monitoring equipment, and obtaining corrected preprocessed data.

[0022] The output module is responsible for sending the corrected preprocessed data to the data mining analysis model using a Zigbee device. The data mining analysis model analyzes the corrected preprocessed data to obtain the analysis results of various indicators, trends and anomalies of methanol data during the operation of methanol-fueled ships.

[0023] Optional, the model acquisition submodule includes:

[0024] The interval division unit is responsible for obtaining the total pressure output range of methanol fuel, dividing the total pressure output range into multiple equal division points, with the distance between adjacent division points being a preset value; at the same time, it obtains various data from monitoring equipment at key locations during the safe operation of methanol fuel.

[0025] The data aggregation unit is responsible for monitoring the pressure gauge values ​​and monitoring equipment values ​​at the grid division nodes, mapping the pressure gauge values ​​and monitoring equipment values ​​to the division points one by one, and aggregating the data to obtain the data mining analysis model of the grid division nodes.

[0026] The model judgment unit is responsible for training the data mining analysis model using historical data as the training set, and then testing the data mining analysis model using the test set. If the test achieves the target result, it will communicate wirelessly with the monitoring equipment through the interface; if the test does not achieve the target result, it will continue to train the data mining analysis model.

[0027] Optional, the model decision unit includes:

[0028] The data identification subunit is responsible for obtaining real-time status data of the monitoring equipment from the data mining and analysis model, and inputting the real-time status data into the target BO-LSTM communication equipment status monitoring network model for identification to obtain the real-time status data of the communication equipment.

[0029] The status judgment subunit is responsible for judging the real-time status data of the monitoring equipment. If it is judged to be a serious fault of the monitoring equipment or a general fault of the communication equipment, it generates equipment fault maintenance measures based on the real-time status data of the monitoring equipment and sends the equipment fault maintenance measures to the server of the data mining analysis model, and at the same time issues an early warning to the server; if it is judged to be a minor fault of the monitoring equipment, it obtains the minor fault factors of the monitoring equipment based on the real-time status data of the monitoring equipment.

[0030] The instruction operation subunit is responsible for monitoring whether the device is judged to have a minor fault or no fault. The data mining analysis model issues an instruction to establish wireless communication. The monitoring device receives the instruction and feeds it back to the data mining analysis model. At this point, the wireless communication between the data mining analysis model and the monitoring device is established.

[0031] Optional, the data processing submodule includes:

[0032] The preprocessing unit is responsible for performing preprocessing operations such as noise removal and missing value processing based on the acquired data;

[0033] The matching and judgment unit is responsible for correcting data based on the location and attribute information of the monitoring equipment: matching the collected data with the corresponding location and attribute information according to the correspondence between the location and attribute information of the monitoring equipment; if the location of a certain monitoring equipment does not match the data, the data is discarded;

[0034] The data input unit is responsible for obtaining and correcting the data after the operation, and then inputting it into the data mining analysis model for analysis.

[0035] Optional, the results output submodule includes:

[0036] The feature extraction unit is responsible for receiving the corrected preprocessed data as input to the data mining and analysis model, extracting features from the input data, and extracting features that are useful for the analysis results from the corrected preprocessed data.

[0037] The feature analysis unit is responsible for analyzing the extracted features by the data mining and analysis model to obtain various indicators, trends and anomalies of methanol data during the operation of methanol-fueled ships. The analysis results are association rules.

[0038] The icon output unit is responsible for presenting the analysis results to the user through visual charts based on the analysis results.

[0039] Optional, alarm output module, including:

[0040] The threshold comparison submodule is responsible for receiving analysis results from the data analysis module, including abnormal methanol concentration and leakage risk. Based on the received analysis results, it determines whether a preset alarm threshold has been reached. When the analysis results exceed or reach a certain alarm threshold, it is considered that there is a potential safety risk or abnormal situation.

[0041] The action execution submodule is responsible for triggering the corresponding alarm action when the analysis results reach the alarm threshold.

[0042] The positioning and analysis submodule is responsible for obtaining the location coordinates of the alarm-issuing device when an alarm is triggered. The location coordinates are obtained by associating them with the location information of the monitoring device. The alarm content is analyzed to obtain fault prediction results.

[0043] Optional, the threshold comparison submodule includes:

[0044] The data verification unit is responsible for collecting historical methanol concentration and leakage risk data, observing the distribution characteristics of the data by drawing histograms, and performing normality tests on the data to determine whether it conforms to the normal distribution assumption.

[0045] The threshold determination unit is responsible for identifying data points that deviate significantly from normal data using density-based methods; determining the threshold for outliers or abnormal trends based on the outlier detection results; and selecting the threshold based on the distribution characteristics of the outliers.

[0046] The threshold adjustment unit is responsible for using a portion of historical observations as a validation set to verify whether the set threshold can accurately identify anomalies; and adjusting the threshold based on the validation results.

[0047] The parameter acquisition module of this invention installs monitoring equipment such as combustible gas detectors, liquid leak detectors, and oxygen concentration sensors at key locations on methanol-fueled vessels to acquire data during methanol fuel operation. The data analysis module analyzes the acquired data to obtain analysis results on methanol data during the operation of the methanol-fueled vessel. The alarm output module triggers an alarm when the analysis results reach an alarm threshold, simultaneously acquiring the location coordinates of the alarming monitoring equipment and analyzing the alarm content to obtain fault prediction results. The parameter acquisition module, through the installation of monitoring equipment such as combustible gas detectors, liquid leak detectors, and oxygen concentration sensors, acquires real-time data at key locations on methanol-fueled vessels, including methanol concentration, combustible gas concentration, liquid leakage, and oxygen concentration. By acquiring this parameter data, the operation of methanol fuel can be monitored in a timely manner, and potential safety risks can be identified. The data analysis module analyzes the acquired parameter data to obtain analysis results on methanol data during the operation of the methanol-fueled vessel. Through data analysis, abnormal situations can be identified, such as methanol concentration exceeding the safe range, increased combustible gas concentration, or liquid leakage. The analysis results can serve as early warning signals to detect potential faults or safety hazards in advance. When the data analysis module determines that there is a safety hazard in a methanol-fueled vessel, the alarm output module is responsible for triggering an alarm and obtaining the location coordinates of the monitoring equipment that triggered the alarm. At the same time, it analyzes the alarm content to obtain fault prediction results, which can promptly notify the vessel operators or relevant departments to take necessary countermeasures to avoid accidents or reduce their impact.

[0048] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0049] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0050] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0051] Figure 1 This is a block diagram of the security and monitoring system for methanol-fueled ships in Embodiment 1 of the present invention;

[0052] Figure 2 This is a block diagram of the parameter acquisition module in Embodiment 2 of the present invention;

[0053] Figure 3This is a block diagram of the position integration submodule in Embodiment 3 of the present invention;

[0054] Figure 4 This is a block diagram of the data analysis module in Embodiment 4 of the present invention;

[0055] Figure 5 This is a block diagram of the model acquisition submodule in Embodiment 5 of the present invention;

[0056] Figure 6 This is a block diagram of the model judgment unit in Embodiment 6 of the present invention;

[0057] Figure 7 This is a block diagram of the data processing submodule in Embodiment 7 of the present invention;

[0058] Figure 8 This is a block diagram of the result output submodule in Embodiment 8 of the present invention;

[0059] Figure 9 This is a block diagram of the alarm output module in Embodiment 8 of the present invention;

[0060] Figure 10 This is a block diagram of the threshold comparison submodule in Embodiment 10 of the present invention. Detailed Implementation

[0061] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0062] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0063] In the following description, when referring 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 this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0064] Example 1: As Figure 1 As shown, this embodiment of the invention provides a security and monitoring system for methanol-fueled ships, comprising:

[0065] The parameter acquisition module is responsible for setting up monitoring equipment such as combustible gas detectors, liquid leak detectors, and oxygen concentration sensors at key locations of methanol-fueled ships to acquire data during the methanol fuel operation process.

[0066] The data analysis module is responsible for analyzing the acquired data to obtain the analysis results of methanol data during the operation of methanol-fueled ships.

[0067] The alarm output module is responsible for triggering an alarm when the analysis results reach the alarm threshold, acquiring the location coordinates of the monitoring device that triggered the alarm, analyzing the alarm content, and obtaining fault prediction results.

[0068] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the parameter acquisition module installs monitoring equipment such as combustible gas detectors, liquid leak detectors, and oxygen concentration sensors at key locations of the methanol-fueled vessel to acquire data during the methanol fuel operation process; the data analysis module analyzes the acquired data to obtain the analysis results of methanol data during the operation of the methanol-fueled vessel; the alarm output module alarms when the analysis results reach the alarm threshold, simultaneously acquiring the location coordinates of the alarmed monitoring equipment and analyzing the alarm content to obtain fault prediction results. The parameter acquisition module of the above solution acquires data from key locations of the methanol-fueled vessel in real time by installing monitoring equipment such as combustible gas detectors, liquid leak detectors, and oxygen concentration sensors, including methanol concentration, combustible gas concentration, liquid leakage, and oxygen concentration; by acquiring these parameter data, the operation process of methanol fuel can be monitored in a timely manner, and potential safety risks can be detected. The data analysis module analyzes the acquired parameter data to obtain the analysis results of methanol data during the operation of the methanol-fueled vessel; through data analysis, abnormal situations can be identified, such as methanol concentration exceeding the safe range, increased combustible gas concentration, or liquid leakage, and the analysis results can serve as early warning signals to detect potential faults or safety hazards in advance. When the data analysis module determines that there is a safety hazard in a methanol-fueled vessel, the alarm output module is responsible for triggering an alarm and obtaining the location coordinates of the monitoring equipment that triggered the alarm. At the same time, it analyzes the alarm content to obtain fault prediction results, which can promptly notify the vessel operators or relevant departments to take necessary countermeasures to avoid accidents or reduce their impact.

[0069] In summary, this embodiment improves the safety and operational efficiency of methanol-fueled vessels by: timely monitoring of key parameters during methanol fuel operation to identify potential safety risks and prevent accidents; a data analysis module that provides early warning signals through parameter data analysis to help ship operators take timely measures to prevent the development of malfunctions or safety hazards; and an alarm output module that not only triggers alarms but also provides location information and fault prediction results for alarm devices, offering accurate guidance and decision-making basis for rescue and maintenance. This can enhance the safety, reliability, and operational efficiency of methanol-fueled vessels, protect the safety of personnel and the environment, and promote sustainable development.

[0070] Example 2: As Figure 2 As shown, based on Embodiment 1, the parameter acquisition module provided in this embodiment of the invention includes:

[0071] The component screening submodule is responsible for obtaining the path model of methanol fuel from storage to combustion and discharge. Based on the operating conditions of the preset key components in the path model during normal operation, and combined with historical safety accident data, the preset key components are screened to obtain the screened key components, which are then designated as the first category of key locations.

[0072] The region determination submodule is responsible for collecting 3D point cloud data of the structure of methanol-fueled vessels and obtaining the inspection point set of methanol-fueled vessels. It performs point cloud segmentation on the 3D point cloud data of the structure to obtain new 3D point cloud data of the structure, and constructs a fenced area based on the new 3D point cloud data of the structure. Based on the new 3D point cloud data of the structure and the fenced area, it determines the installation area of ​​the monitoring equipment. Based on the positional weight of the structure of the methanol-fueled vessel and the distance to key components and pipelines in the path model, it selects the second type of key location from the installation area.

[0073] The location integration submodule is responsible for integrating the first and second types of key locations according to the identification of the path model and the 3D point cloud data of the structure, to obtain the key locations of the monitoring equipment installed on methanol fuel-powered ships, and marking them according to the location and attributes of the monitoring equipment.

[0074] The working principle and beneficial effects of the above technical solution are as follows: The component screening submodule of this embodiment obtains the path model of methanol fuel from storage to combustion and discharge. Based on the operating conditions of the preset key components in the path model during normal operation, and combined with historical safety accident data, the preset key components are screened to obtain the screened key components, which are then used as the first type of key locations. The region determination submodule collects the structural three-dimensional point cloud data of the methanol fuel-powered ship and obtains the first inspection point set of the methanol fuel-powered ship. The structural three-dimensional point cloud data is segmented to obtain new structural three-dimensional point cloud data. Based on the new structural three-dimensional point cloud data, a fenced area is constructed. Based on the new structural three-dimensional point cloud data and the fenced area, the installation area of ​​the monitoring equipment is determined. Based on the position weight of the structure of the methanol fuel-powered ship and the distance to the key components and pipelines in the path model, the second key location is selected from the installation area. The location integration submodule integrates the first key location and the second key location according to the identifiers of the path model and the structural three-dimensional point cloud data to obtain the key location for installing the monitoring equipment on the methanol fuel-powered ship, and marks it according to the location and attributes of the monitoring equipment. The component screening submodule of the above scheme identifies critical components that play a vital role in methanol fuel operation and are prone to failure, improving the monitoring and management of these critical components and reducing potential safety risks. The region determination submodule, based on the ship's structure and path model, determines the optimal installation location for monitoring equipment, improving the accuracy and comprehensiveness of data acquisition. The location integration submodule* integrates key location information from different sources into a unified data structure, facilitating subsequent data management and monitoring.

[0075] In summary, this embodiment determines the optimal locations of key components and monitoring equipment in methanol-fueled vessels, improving the monitoring and management of these components and locations and reducing safety risks. Based on structural and path models, the installation areas of monitoring equipment are precisely located, improving the accuracy and completeness of monitoring data. The integration and labeling of key location information facilitates subsequent data management and monitoring, providing reliable technical support for the safe operation of the vessel.

[0076] Example 3: As Figure 3 As shown, based on Embodiment 2, the location integration submodule provided in this embodiment of the invention includes:

[0077] The equipment labeling unit is responsible for acquiring attribute information for each monitoring device, including device type, sensor type, and monitoring parameters; and labeling the monitoring device with icons based on the acquired location and attribute information.

[0078] The relationship establishment unit is responsible for obtaining location, attribute information and icons from the electronic data spreadsheet. In the electronic data spreadsheet, it finds the column used to store the location and attribute information of the monitoring equipment, and associates the column with the corresponding column in the electronic data spreadsheet to establish a data relationship.

[0079] The autofill cell is responsible for automatically filling the content of the spreadsheet using formulas based on data relationships. Specifically, for location information, the INDEX formula is used to find and obtain the corresponding location coordinates; for attribute information, the VLOOKUP formula is used to find and obtain the corresponding attribute values; and for icons, conditional formatting and other functions are used to automatically set the corresponding icons based on the attribute values.

[0080] The working principle and beneficial effects of the above technical solution are as follows: The device labeling unit in this embodiment acquires attribute information for each monitoring device, including device type, sensor type, and monitoring parameters. Based on the acquired location and attribute information, it labels the monitoring device with icons. The relationship establishment unit obtains the location, attribute information, and icons from the electronic data table. In the electronic data table, it finds the column used to store the location and attribute information of the monitoring device and associates this column with the corresponding column in the electronic data table to establish a data association relationship. The automatic filling unit automatically fills the content of the electronic data table using formulas based on the data association relationship. Specifically, for location information, the INDEX formula is used to find and obtain the corresponding location coordinates; for attribute information, the VLOOKUP formula is used to find and obtain the corresponding attribute value; for icons, conditional formatting and other functions are used to automatically set the corresponding icons based on the attribute values. The device labeling unit in the above solution extracts key attribute information from the actual monitoring device and intuitively represents it in the system through icon labeling, providing an accurate and visual foundation for subsequent data management. The relationship establishment unit, by establishing data association relationships, ensures the consistency between the data in the electronic data table and the location, attribute information, and corresponding icons of the actual monitoring device, providing an accurate data source for subsequent automatic filling. The autofill unit enables the automatic updating and filling of electronic data spreadsheet content. When the location, attributes, or icons of the monitoring device change, the spreadsheet content will be automatically updated to maintain consistency with the actual situation, thereby improving the efficiency and accuracy of data management.

[0081] In summary, the combined effect of these units in this embodiment enables the automated integration of the entire process from monitoring equipment to electronic spreadsheets, greatly reducing the workload of manual operations, improving the efficiency and accuracy of data management, and providing a reliable foundation for subsequent data analysis and applications.

[0082] Example 4: Figure 4 As shown, based on Embodiment 1, the data analysis module provided in this embodiment of the invention includes:

[0083] The model acquisition submodule is responsible for using historical data as training and testing sets to build a data mining and analysis model, and at the same time, it realizes wireless communication with the monitoring equipment through an interface.

[0084] The data processing submodule is responsible for acquiring data collected by monitoring equipment, obtaining preprocessed data based on the data, removing mismatched data according to the correspondence between the location and attribute information of the monitoring equipment, and obtaining corrected preprocessed data.

[0085] The output module is responsible for sending the corrected preprocessed data to the data mining analysis model using a Zigbee device. The data mining analysis model analyzes the corrected preprocessed data to obtain analysis results on various indicators, trends, and anomalies of methanol data during the operation of methanol-fueled ships.

[0086] In this embodiment, the data mining analysis model uses the decision tree algorithm. Decision trees perform classification or regression analysis by constructing a tree structure. The computational principle of decision trees can be divided into two main steps: feature selection and tree construction. The specific computational principle and formula are as follows:

[0087] Feature selection is a key step in decision tree algorithms, which involves making decisions by selecting the features that contribute the most to classification or regression. Feature selection criteria include information gain, information gain ratio, and Gini index.

[0088] Information gain: Information gain is a metric that measures the ability of a feature to classify a dataset. The calculation formula is:

[0089] Information gain = H(D) - H(D|A);

[0090] Where H(D) represents the entropy of dataset D, and the calculation formula is: H(D)=-Σ(p(x)*log2(p(x)));

[0091] H(D|A) represents the conditional entropy of dataset D given feature A, and is calculated using the following formula:

[0092] H(D|A)=Σ((|D i | / |D|)*H(D i ));

[0093] Among them, |D i | represents the number of samples in dataset D given that feature A takes the value i, H(D i ) represents the entropy of dataset D given that feature A takes the value i.

[0094] Information gain ratio: The information gain ratio is an improved indicator of feature selection based on information gain, which can avoid selecting features with too many possible values. The calculation formula is:

[0095] Information gain ratio = Information gain / Entropy of feature

[0096] The formula for calculating the entropy of a feature is:

[0097] Entropy of a feature = -Σ(p(x)*log2(p(x)))

[0098] H(D) represents the entropy of dataset D, and H(D|A) represents the conditional entropy of dataset D given feature A.

[0099] Gini index: The Gini index is an indicator used in classification problems to measure the impurity of a sample. The calculation formula is:

[0100] Gini index = 1 - Σ(p(i)) 2 )

[0101] Where p(i) represents the probability that a sample belongs to class i; the smaller the Gini index, the higher the purity of the sample.

[0102] Based on the above feature selection criteria, the information gain, information gain ratio, or Gini index of each feature can be calculated, and the feature with the maximum value can be selected as the splitting feature of the current node.

[0103] Tree construction generates a complete decision tree by recursively partitioning the dataset and building subtrees. The specific construction process is as follows:

[0104] If the samples of the current node belong to the same category, then mark the current node as a leaf node and assign the category label to the leaf node;

[0105] If the feature set of the current node is empty or the sample has the same value in the feature set, then mark the current node as a leaf node and assign the most common class label in the sample to the leaf node.

[0106] Otherwise, based on the selected features, the samples are divided into different subsets, each subset corresponding to a child node. The above steps are recursively performed on each child node until a termination condition is met. Through the above feature selection and tree construction process, a complete decision tree model can be generated. When applying the model for prediction, classification or regression prediction is performed based on the feature values ​​of the samples by traversing the nodes of the decision tree.

[0107] The data mining analysis model construction process in this embodiment includes the following steps:

[0108] Data preparation: Collect historical data as training and test sets, sort the data to find duplicate values, and delete duplicate values;

[0109] Feature engineering: Extracting features from the raw data using time series feature extraction, transforming the data into a feature representation;

[0110] Model selection: The decision tree algorithm was selected as the data mining algorithm and model for analysis and classification;

[0111] Model training and tuning: Train the selected model using the training set to learn the model's parameters; find the optimal combination of hyperparameters through grid search;

[0112] Model evaluation and validation: The trained model is evaluated and validated using a test set. Metrics such as accuracy, precision, recall, and F1 score are calculated to assess the model's performance.

[0113] Model application and deployment: The trained model is applied to real-world scenarios, and wireless communication with monitoring equipment is achieved through an interface to acquire real-time data and perform prediction and analysis; the results output submodule is responsible for outputting the analysis results to users or other systems, and can perform visualization and report generation, etc.

[0114] In this embodiment, the criteria for the data mining analysis model to analyze the corrected preprocessed data are as follows: select features that are highly correlated with the target variable, that is, features that can predict the target variable well; and select features with an importance index higher than the threshold based on the trained data mining analysis model and the feature importance index.

[0115] The working principle and beneficial effects of the above technical solution are as follows: The model acquisition submodule in this embodiment uses historical data as the training and testing sets to establish a data mining analysis model, and simultaneously achieves wireless communication with the monitoring equipment through an interface. The data processing submodule acquires data collected by the monitoring equipment, obtains preprocessed data based on the data, and removes mismatched data according to the correspondence between the monitoring equipment's location and attribute information, resulting in corrected preprocessed data. The result output submodule sends the corrected preprocessed data to the data mining analysis model using a Zigbee device. The data mining analysis model analyzes the corrected preprocessed data to obtain analysis results such as various indicators, trends, and anomalies of methanol data during the operation of methanol-fueled ships. The model acquisition submodule of the above solution establishes a data mining analysis model, which can use historical data for prediction and analysis, achieves wireless communication with the monitoring equipment, and can acquire real-time data. By establishing an analysis model, accurate prediction and analysis of methanol-fueled ship data can be performed. Simultaneously, the real-time acquired data can provide the latest operational status, supporting further analysis and decision-making. The data processing submodule preprocesses and cleans and corrects the data collected by monitoring equipment, improving data quality and accuracy. The corrected preprocessed data provides more accurate and reliable input to the data mining analysis model. By eliminating mismatched data, errors and biases are reduced, improving the accuracy of the analysis results. The results output submodule uses Zigbee devices to wirelessly transmit data, sending the preprocessed data to the data mining analysis model and receiving the analysis results. The analysis results provide important information such as various indicators, trends, and anomalies of methanol data during the operation of methanol-fueled ships. These results can be used to monitor the ship's operating status, predict faults, and take corresponding measures to ensure the ship's safety and reliability.

[0116] In summary, the model acquisition submodule, data processing submodule, and result output submodule of this embodiment are each responsible for different tasks in the data analysis module. By establishing an analysis model, preprocessing data, and acquiring analysis results, accurate, reliable, and real-time data analysis results for methanol-fueled ships can be provided to achieve the monitoring of ship safety and operational status.

[0117] Example 5: Figure 5 As shown, based on Example 4, the model acquisition submodule provided in this embodiment of the invention includes:

[0118] The interval division unit is responsible for obtaining the total pressure output range of methanol fuel, dividing the total pressure output range into multiple equal division points, with the distance between adjacent division points being a preset value; at the same time, it obtains various data from monitoring equipment at key locations during the safe operation of methanol fuel.

[0119] The data aggregation unit is responsible for monitoring the pressure gauge values ​​and monitoring equipment values ​​at the grid division nodes, mapping the pressure gauge values ​​and monitoring equipment values ​​to the division points one by one, and aggregating the data to obtain the data mining analysis model of the grid division nodes.

[0120] The model judgment unit is responsible for training the data mining analysis model using historical data as the training set, and then testing the data mining analysis model using the test set. If the test achieves the target result, it will communicate wirelessly with the monitoring equipment through the interface; if the test does not achieve the target result, it will continue to train the data mining analysis model.

[0121] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the interval division unit obtains the total pressure output range of methanol fuel, divides the total pressure output range equally, and obtains multiple division points with a preset distance between adjacent division points. Simultaneously, it obtains various data from monitoring equipment at key locations during the safe operation of methanol fuel. The data aggregation unit monitors the pressure gauge values ​​and monitoring equipment values ​​at the grid division nodes, mapping the pressure gauge values ​​and monitoring equipment values ​​one-to-one with the division points, and aggregating the data to obtain the data mining analysis model for the grid division nodes. The model judgment unit uses historical data as a training set to train the data mining analysis model. After training, it uses a test set to test the data mining analysis model. If the test achieves the target result, wireless communication with the monitoring equipment is achieved through an interface; if the test does not achieve the target result, the data mining analysis model continues to be trained. The interval division unit in the above solution determines the range of the total pressure output of methanol fuel and divides it equally into multiple division points. It obtains monitoring equipment data at key locations; through the division points, the total pressure output range of methanol fuel can be better analyzed and predicted; the monitoring equipment data at key locations can provide real-time information for further analysis and decision-making. The data aggregation unit maps pressure gauge and monitoring device values ​​to equally divided points and aggregates the data to obtain a data mining analysis model for grid-divided nodes. Through data aggregation, a data mining analysis model can be established to analyze data from different grid-divided nodes, providing more refined analysis results to help understand and predict pressure conditions during the operation of methanol-fueled ships. The model evaluation unit, through training and testing, determines whether the data mining analysis model has achieved the preset target results, as well as the model's accuracy and reliability. The accuracy and reliability of the model are crucial factors in ensuring the analysis results. Through training and testing, the model's performance can be evaluated, and adjustments and improvements can be made as needed. Simultaneously, through wireless communication with the monitoring equipment, data can be acquired in real time for analysis and decision-making.

[0122] In summary, the interval division unit, data aggregation unit, and model judgment unit in this embodiment are each responsible for different tasks in the model acquisition submodule. Through the division points, data aggregation, and model training, an accurate, reliable, and real-time data mining and analysis model can be obtained, which can be used to analyze and predict the pressure and key location data of methanol fuel-powered ships. This helps to monitor the ship's operating status in real time, predict problems, and take corresponding measures to ensure the safety and reliability of the ship.

[0123] Example 6: As Figure 6 As shown, based on Embodiment 5, the model judgment unit provided in this embodiment of the invention includes:

[0124] The data identification subunit is responsible for obtaining real-time status data of the monitoring equipment from the data mining and analysis model, and inputting the real-time status data into the target BO-LSTM communication equipment status monitoring network model for identification to obtain the real-time status data of the communication equipment.

[0125] The status judgment subunit is responsible for judging the real-time status data of the monitoring equipment. If it is judged to be a serious fault of the monitoring equipment or a general fault of the communication equipment, it generates equipment fault maintenance measures based on the real-time status data of the monitoring equipment and sends the equipment fault maintenance measures to the server of the data mining analysis model, and at the same time issues an early warning to the server; if it is judged to be a minor fault of the monitoring equipment, it obtains the minor fault factors of the monitoring equipment based on the real-time status data of the monitoring equipment.

[0126] The instruction operation subunit is responsible for monitoring whether the device is judged to have a minor fault or no fault. The data mining analysis model issues an instruction to establish wireless communication. The monitoring device receives the instruction and feeds it back to the data mining analysis model. At this point, the wireless communication between the data mining analysis model and the monitoring device is established.

[0127] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the data identification subunit data mining analysis model obtains the real-time status data of the monitoring equipment and inputs the real-time status data into the target BO-LSTM communication equipment status monitoring network model for identification to obtain the real-time status data of the communication equipment; the status judgment subunit judges the real-time status data of the monitoring equipment. If it is judged to be a serious fault of the monitoring equipment or a general fault of the communication equipment, it generates equipment fault maintenance measures based on the real-time status data of the monitoring equipment and sends the equipment fault maintenance measures to the server of the data mining analysis model, and at the same time issues an early warning to the server; if it is judged to be a minor fault of the monitoring equipment, it obtains the minor fault factors of the monitoring equipment based on the real-time status data of the monitoring equipment; the instruction operation subunit, when the monitoring equipment is judged to be a minor fault or no fault, the data mining analysis model issues an instruction to establish wireless communication. The monitoring equipment receives the instruction and feeds back to the data mining analysis model. At this point, the wireless communication between the data mining analysis model and the monitoring equipment is established. The data identification subunit of the above scheme identifies real-time status data of the communication equipment through the target BO-LSTM communication equipment status monitoring network model. This real-time status data reflects the current operating status of the communication equipment, including fault conditions and health status. By identifying and acquiring this data, subsequent fault diagnosis and maintenance measures can be formulated. The status judgment subunit performs fault diagnosis based on the real-time status data, generates equipment fault maintenance measures, and issues early warnings. Timely assessment of equipment fault conditions allows for appropriate maintenance measures to prevent further deterioration and ensure normal equipment operation. Simultaneously, early warnings can promptly notify relevant personnel for handling, reducing the impact of equipment faults on ship operations. The command operation subunit establishes a wireless communication connection between the data mining analysis model and the monitoring equipment through command operations. This wireless connection enables real-time data transmission and remote control of the monitoring equipment, facilitating real-time monitoring of equipment operating status, remote configuration and adjustment, and improving ship operating efficiency and reliability.

[0128] In summary, the data identification subunit, status judgment subunit, and instruction operation subunit of this embodiment are each responsible for different tasks in the model judgment unit. By identifying real-time status data, judging equipment failure conditions, and establishing wireless communication connections, maintenance measures, early warnings, and remote control can be taken in a timely manner to ensure the normal operation of monitoring equipment and improve the safety and reliability of ships.

[0129] Example 7: Figure 7 As shown, based on Embodiment 4, the data processing submodule provided in this embodiment of the invention includes:

[0130] The preprocessing unit is responsible for performing preprocessing operations such as noise removal and missing value processing based on the acquired data;

[0131] The matching and judgment unit is responsible for correcting data based on the location and attribute information of the monitoring equipment: matching the collected data with the corresponding location and attribute information according to the correspondence between the location and attribute information of the monitoring equipment; if the location of a certain monitoring equipment does not match the data, the data is discarded;

[0132] The data input unit is responsible for obtaining and correcting the data after the operation, and then inputting it into the data mining analysis model for analysis.

[0133] The working principle and beneficial effects of the above technical solution are as follows: The preprocessing unit in this embodiment performs noise removal and missing value processing based on the acquired data; the matching judgment unit corrects the data according to the location and attribute information of the monitoring equipment: matching the collected data with the corresponding location and attribute based on the correspondence between the location and attribute information of the monitoring equipment; if a monitoring equipment location does not match the data, the data is discarded; the data input unit obtains the data after the correction operation and uses it as input to the data mining analysis model for analysis. The preprocessing unit in the above solution improves the quality and usability of the data by removing noise and processing missing values, reducing the impact of errors and missing values ​​in the data on subsequent analysis; the preprocessing operation can clean and transform the data, eliminate outliers and noise, and fill in missing values, making the data more accurate and complete, which helps improve the accuracy and reliability of data analysis and helps discover potential patterns and trends. The matching and judgment unit monitors the correspondence between the location and attribute information of monitoring equipment, matching the collected data with the corresponding location and attributes to ensure data accuracy and consistency. Data correction eliminates data errors caused by location and attribute mismatches, ensuring data reliability and consistency, improving the accuracy of subsequent analysis, and avoiding misjudgments and erroneous conclusions due to mismatched data. The data input unit takes the corrected data as input to the data mining analysis model for further analysis and modeling. Inputting the corrected preprocessed data into the data mining analysis model improves the model's accuracy and reliability, helps discover patterns and trends in the data, and predicts and analyzes various indicators, trends, and anomalies in methanol data during the operation of methanol-fueled ships, providing support for ship operation monitoring and decision-making.

[0134] In summary, the preprocessing unit, matching judgment unit, and data input unit in this embodiment are each responsible for different tasks in the data processing submodule. Through preprocessing, correction, and input operations, the quality and accuracy of the data can be improved, the consistency and reliability of the data can be ensured, and accurate and reliable input data can be provided for the data mining analysis model to further analyze and predict methanol data of methanol-fueled ships.

[0135] Example 8: As Figure 8As shown, based on Example 4, the result output submodule provided in this embodiment of the invention includes:

[0136] The feature extraction unit is responsible for receiving the corrected preprocessed data as input to the data mining and analysis model, extracting features from the input data, and extracting features that are useful for the analysis results from the corrected preprocessed data.

[0137] The feature analysis unit is responsible for analyzing the extracted features by the data mining and analysis model to obtain various indicators, trends and anomalies of methanol data during the operation of methanol-fueled ships. The analysis results are association rules.

[0138] Among them, the indicator association rules are as follows:

[0139] {High methanol consumption} ≥ {Low methanol efficiency}: When methanol consumption is high, methanol efficiency is low;

[0140] {High methanol production}≥{Long ship travel time}: When methanol production is high, ship travel time is long.

[0141] {High methanol consumption} ≥ {High emissions}: When methanol consumption is high, emissions are also high.

[0142] Trend association rules:

[0143] {Increase in methanol consumption} ≥ {Increase in methanol production}: When methanol consumption increases, methanol production will also increase;

[0144] {Reduced ship operating time} ≥ {Increased methanol efficiency}: When ship operating time is reduced, methanol efficiency will also increase;

[0145] Abnormal situation association rules:

[0146] {Abnormally high methanol consumption} ≥ {Increased risk of methanol leakage}: When methanol consumption is abnormally high, the risk of methanol leakage will also increase.

[0147] {Abnormally low methanol efficiency} ≥ {Abnormally high emissions}: When methanol efficiency is abnormally low, emissions will also be abnormally high.

[0148] The icon output unit is responsible for presenting the analysis results to the user through visual charts based on the analysis results.

[0149] The working principle and beneficial effects of the above technical solution are as follows: The feature extraction unit's data mining analysis model receives corrected preprocessed data as input, performs feature extraction on the input data, and extracts features useful for the analysis results from the corrected preprocessed data; the feature analysis unit's data mining analysis model analyzes the extracted features to obtain analysis results such as various indicators, trends, and anomalies of methanol data during the operation of methanol-fueled ships, and the analysis results are association rules; the chart output unit presents the analysis results to the user through visual charts. The purpose of feature extraction in the above solution is to transform the raw data into more representative and interpretable features to better support the subsequent analysis process; through feature extraction, the dimensionality of the data can be reduced, redundant information removed, and key features that affect the analysis results extracted. The feature analysis unit uses data mining techniques and algorithms to mine patterns, regularities, and relationships in the data, helping users understand and discover hidden information in the data. The chart output unit's visual charts can more intuitively display the distribution, trends, and relationships of the data, helping users better understand and interpret the analysis results. Through chart output, users can quickly obtain information, discover patterns, and support decision-making and action.

[0150] In summary, the feature extraction unit in this embodiment can reduce the dimensionality of data and extract features useful for the analysis results, helping users better understand and apply the data. The feature analysis unit reveals the correlation between different data indicators through association rules, helping users discover patterns and trends in the data, supporting decision-making and optimization. The chart output unit presents the analysis results to users intuitively through visual charts, providing better data interpretation and decision support. The functions and effects of these units work together to help users gain a deeper understanding of the operation of methanol-fueled ships, identify potential problems, optimize methanol usage, and predict future trends. Simultaneously, the visualization of the analysis results presents them to users in a more understandable and applicable way, improving users' data awareness and decision-making abilities. The data mining analysis model can analyze the corrected preprocessed data and obtain analysis results on various indicators, trends, and anomalies of methanol data during the operation of methanol-fueled ships. These results can be provided to users to help understand the ship's operation, identify potential problems, and optimize operational strategies. Association rules are extracted from the corrected preprocessed data through the data mining analysis model. Association rules help users understand the relationships between different methanol data indicators, trends, and anomalies, as well as their impact on ship operations and the environment. Presenting these relationships through visualizations and charts allows for a more intuitive understanding and application of the analysis results. It's important to note that the specific association rules will vary depending on the definition of the problem, the characteristics of the data, and the chosen analytical model.

[0151] Example 9: As Figure 9 As shown, based on Embodiment 1, the alarm output module provided in this embodiment of the invention includes:

[0152] The threshold comparison submodule is responsible for receiving analysis results from the data analysis module, including abnormal methanol concentration and leakage risk. Based on the received analysis results, it determines whether a preset alarm threshold has been reached. When the analysis results exceed or reach a certain alarm threshold, it is considered that there is a potential safety risk or abnormal situation.

[0153] The action execution submodule is responsible for triggering the corresponding alarm action when the analysis results reach the alarm threshold.

[0154] The alarm action includes issuing an audible alarm: issuing a high-volume audible alarm through a sound device or siren;

[0155] Sending alert information: Sending alert information via the terminal, such as via SMS, email, and APP push notifications;

[0156] Trigger the automatic control system: Depending on the situation, the automatic control system can be triggered, such as shutting down relevant equipment and cutting off the methanol supply, to avoid further safety risks;

[0157] The positioning and analysis submodule is responsible for obtaining the location coordinates of the alarm-issuing device when an alarm is triggered. The location coordinates are obtained by associating them with the location information of the monitoring device. The alarm content is analyzed to obtain fault prediction results.

[0158] The working principle and beneficial effects of the above technical solution are as follows: The threshold comparison submodule of this embodiment receives the analysis results from the data analysis module, which include abnormal methanol concentration and leakage risk, etc.; based on the received analysis results, it determines whether a preset alarm threshold has been reached. When the analysis results exceed or reach a certain alarm threshold, it is considered that there is a potential safety risk or abnormal situation; the action execution submodule triggers the corresponding alarm action when the analysis results reach the alarm threshold; the alarm action includes: issuing a sound alarm: issuing a high-volume sound alarm through a sound device or siren; sending alarm information: sending alarm information through a terminal, such as SMS, email, and APP push; triggering the automatic control system: depending on the situation, the automatic control system can be triggered, such as shutting down relevant equipment and cutting off the methanol supply, to avoid further safety risks; the positioning and analysis submodule obtains the location coordinates of the alarm-issuing device when the alarm is triggered, and the location coordinates are realized by associating with the location information of the monitoring device; the alarm content is analyzed to obtain the fault prediction result. The threshold comparison submodule of the above solution monitors the analysis results of methanol data in real time and compares them with the preset threshold to determine whether there is a safety risk or abnormal situation, promptly detect potential dangers, improve safety, and reduce potential risks. The action execution submodule triggers alarm actions, such as issuing audible alarms, sending alarm messages, or triggering the automatic control system. In the event of a safety risk or abnormal situation, it promptly notifies relevant personnel or takes appropriate measures to ensure the safe operation of the vessel. The positioning and analysis submodule acquires the location coordinates of the alarm equipment, achieving location tracking. It further analyzes the alarm content to obtain fault prediction results, quickly and accurately locating the alarm equipment, providing location information to relevant personnel for action, and providing reference information through fault prediction results to support maintenance and management decisions.

[0159] In summary, through the collaborative operation of the above sub-modules, the alarm output module in this embodiment can achieve functions such as real-time monitoring, alarm action triggering, location positioning, and fault prediction; thereby improving safety, reducing potential risks, responding promptly to abnormal situations, and ensuring the safe operation of the vessel. Simultaneously, through alarm action and location positioning functions, relevant personnel can quickly understand the alarm situation and take corresponding actions, improving emergency response capabilities; the fault prediction results from the location and analysis sub-modules can provide a reference for maintenance and management decisions, further optimizing vessel operation.

[0160] Example 10: As Figure 10 As shown, based on Example 9, the threshold comparison submodule provided in this embodiment of the invention includes:

[0161] The data verification unit is responsible for collecting historical methanol concentration and leakage risk data, observing the distribution characteristics of the data by drawing histograms, and performing normality tests on the data to determine whether it conforms to the normal distribution assumption.

[0162] If the data conforms to the normal distribution assumption, the mean and standard deviation of the data are calculated, and according to the properties of the normal distribution, a threshold is set as the mean plus or minus a certain number of standard deviations to include most of the normal data.

[0163] If the data does not conform to the normal distribution assumption, an outlier detection algorithm is used to identify data points that deviate significantly from the normal data, and a threshold is set based on the distribution characteristics of the outliers.

[0164] The threshold determination unit is responsible for identifying data points that deviate significantly from normal data using density-based methods; determining the threshold for outliers or abnormal trends based on the outlier detection results; and selecting the threshold based on the distribution characteristics of the outliers.

[0165] The threshold adjustment unit is responsible for using a portion of historical observations as a validation set to verify whether the set threshold can accurately identify anomalies; and adjusting the threshold based on the validation results.

[0166] The working principle and beneficial effects of the above technical solution are as follows: The data verification unit in this embodiment collects observed values ​​of historical methanol concentration and leakage risk data. By plotting histograms to observe the distribution characteristics of the data, it performs a normality test to determine whether the data conforms to the normal distribution assumption. If the data conforms to the normal distribution assumption, the mean and standard deviation of the data are calculated, and based on the properties of the normal distribution, a threshold is set as the mean plus or minus a certain number of standard deviations to include most normal data. If the data does not conform to the normal distribution assumption, a method based on outlier detection is used to identify data points that deviate significantly from normal data, and a threshold is set based on the distribution characteristics of the outliers. The threshold determination unit uses a density-based method to identify data points that deviate significantly from normal data. Based on the outlier detection results, a threshold for outliers or abnormal trends is determined. A threshold is set based on the distribution characteristics of outliers. The threshold adjustment unit uses a portion of historical observations as a validation set to verify whether the set threshold can accurately identify abnormal situations. Based on the validation results, the threshold is adjusted. The data verification unit in the above solution determines whether the data conforms to the normal distribution assumption, providing a basis for subsequent threshold setting. The threshold determination unit identifies outliers and anomalies, sets reasonable thresholds to facilitate subsequent alarm judgments and action triggering. The threshold adjustment unit adjusts the thresholds based on the verification results to improve accuracy and reliability.

[0167] In summary, this embodiment analyzes the distribution characteristics of historical data and performs normality tests to understand the distribution of methanol concentration and leakage risk data, which helps determine the basic characteristics of the data and provides a basis for subsequent threshold setting. The threshold determination unit identifies data points that deviate significantly from normal data through outlier detection and density-based methods, and sets thresholds for outliers or abnormal trends. This helps to accurately determine whether there are safety risks or abnormal situations, and provides an accurate basis for subsequent alarm triggering and handling. The threshold adjustment unit verifies whether the set threshold can accurately identify abnormal situations and further optimizes the threshold setting, which helps to improve the accuracy and reliability of the alarm system, promptly detect potential hazards, and reduce potential risks.

[0168] Through the collaborative work of the above units, the threshold comparison submodule in this embodiment can analyze and judge the data on methanol concentration and leakage risk, set reasonable thresholds, improve safety and reduce potential risks, detect abnormal situations in a timely manner, and provide accurate judgment basis for the alarm output module; thereby improving the safety and reliability of ship operation and ensuring the safe operation of the ship and the safety of the crew.

[0169] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A security and monitoring system for a methanol fuel powered marine vessel, characterized in that, Include: The parameter acquisition module is responsible for setting up combustible gas detectors, liquid leak detectors, and oxygen concentration sensors at key locations on methanol-fueled ships to acquire data during the methanol fuel operation process. The data analysis module is responsible for analyzing the acquired data to obtain the analysis results of methanol data during the operation of methanol-fueled ships. The alarm output module is responsible for triggering an alarm when the analysis results reach the alarm threshold, acquiring the location coordinates of the alarm monitoring device, analyzing the alarm content, and obtaining fault prediction results. The parameter acquisition module includes: The component screening submodule is responsible for obtaining the path model of methanol fuel from storage to combustion and discharge. Based on the operating conditions of the preset key components in the path model during normal operation, and combined with historical safety accident data, the preset key components are screened to obtain the screened key components, which are then designated as the first category of key locations. The region determination submodule is responsible for collecting 3D point cloud data of the structure of methanol-fueled vessels, acquiring the inspection point set of methanol-fueled vessels, segmenting the 3D point cloud data of the structure to obtain new 3D point cloud data of the structure, constructing a fenced area based on the new 3D point cloud data of the structure, and determining the installation area of ​​the monitoring equipment based on the new 3D point cloud data of the structure and the fenced area; and selecting the second type of key location from the installation area based on the positional weight of the structure of the methanol-fueled vessel and the distance to key components and pipelines in the path model. The location integration submodule is responsible for integrating the first and second types of key locations according to the identification of the path model and the 3D point cloud data of the structure, to obtain the key locations of the monitoring equipment installed on the methanol fuel-powered ship, and marking them according to the location and attributes of the monitoring equipment. The location integration submodule includes: The equipment labeling unit is responsible for acquiring attribute information, including equipment type, sensor type, and monitoring parameters, for each monitoring device; and labeling the monitoring devices with icons based on the acquired location and attribute information. The relationship establishment unit is responsible for obtaining location, attribute information and icons from the electronic data spreadsheet. In the electronic data spreadsheet, it finds the column used to store the location and attribute information of the monitoring equipment, and associates the column with the corresponding column in the electronic data spreadsheet to establish a data relationship. The autofill cell is responsible for automatically filling the content of the spreadsheet using formulas based on data relationships. Specifically, for location information, the INDEX formula is used to look up and obtain the corresponding location coordinates; for attribute information, the VLOOKUP formula is used to look up and obtain the corresponding attribute values. For icons, use conditional formatting to automatically set the corresponding icon based on the attribute value.

2. The security and monitoring system for a methanol-fueled marine vessel of claim 1, wherein, The data analysis module includes: The model acquisition submodule is responsible for using historical data as training and testing sets to build a data mining and analysis model, and at the same time, it realizes wireless communication with the monitoring equipment through an interface. The data processing submodule is responsible for acquiring data collected by monitoring equipment, obtaining preprocessed data based on the data, removing mismatched data according to the correspondence between the location and attribute information of the monitoring equipment, and obtaining corrected preprocessed data. The output module is responsible for sending the corrected preprocessed data to the data mining analysis model using a Zigbee device. The data mining analysis model analyzes the corrected preprocessed data to obtain the analysis results of various indicators, trends and anomalies of methanol data during the operation of methanol-fueled ships.

3. The security and monitoring system for a methanol-fueled marine vessel of claim 2, wherein, The model acquisition submodule includes: The interval division unit is responsible for obtaining the total pressure output range of methanol fuel, dividing the total pressure output range into multiple equal division points, with the distance between adjacent division points being a preset value; at the same time, it obtains various data from monitoring equipment at key locations during the safe operation of methanol fuel. The data aggregation unit is responsible for monitoring the pressure gauge values ​​and monitoring equipment values ​​at the grid division nodes, mapping the pressure gauge values ​​and monitoring equipment values ​​to the division points one by one, and aggregating the data to obtain the data mining analysis model of the grid division nodes. The model judgment unit is responsible for training the data mining analysis model using historical data as the training set, and then testing the data mining analysis model using the test set. If the test achieves the target result, it will communicate wirelessly with the monitoring equipment through the interface; if the test does not achieve the target result, it will continue to train the data mining analysis model.

4. The security and monitoring system for a methanol-fueled marine vessel of claim 3, wherein, The model judgment unit includes: The data identification subunit is responsible for acquiring real-time status data of the monitoring equipment, inputting the real-time status data into the target BO-LSTM communication equipment status monitoring network model for identification, and obtaining the real-time status data of the communication equipment. The status judgment subunit is responsible for judging the real-time status data of the monitoring equipment. If it is judged to be a serious fault of the monitoring equipment or a general fault of the communication equipment, it generates equipment fault maintenance measures based on the real-time status data of the monitoring equipment and sends the equipment fault maintenance measures to the server of the data mining analysis model, and at the same time issues an early warning to the server; if it is judged to be a minor fault of the monitoring equipment, it obtains the minor fault factors of the monitoring equipment based on the real-time status data of the monitoring equipment. The instruction operation subunit is responsible for monitoring whether the device is judged to have a minor fault or no fault. The data mining analysis model issues an instruction to establish wireless communication. The monitoring device receives the instruction and feeds it back to the data mining analysis model. At this point, the wireless communication between the data mining analysis model and the monitoring device is established.

5. The security and monitoring system for a methanol-fueled marine vessel of claim 2, wherein, The data processing submodule includes: The preprocessing unit is responsible for performing preprocessing operations such as noise removal and missing value processing based on the acquired data; The matching and judgment unit is responsible for correcting data based on the location and attribute information of the monitoring equipment: matching the collected data with the corresponding location and attribute information according to the correspondence between the location and attribute information of the monitoring equipment; if the location of a certain monitoring equipment does not match the data, the data is discarded; The data input unit is responsible for obtaining and correcting the data after the operation, and then inputting it into the data mining analysis model for analysis.

6. The security and monitoring system for a methanol-fueled marine vessel of claim 2, wherein, The results output submodule contains: The feature extraction unit is responsible for receiving the corrected preprocessed data as input to the data mining and analysis model, extracting features from the input data, and extracting features that are useful for the analysis results from the corrected preprocessed data. The feature analysis unit is responsible for analyzing the extracted features by the data mining and analysis model to obtain various indicators, trends and anomalies of methanol data during the operation of methanol-fueled ships. The analysis results are association rules. The icon output unit is responsible for presenting the analysis results to the user through visual charts based on the analysis results.

7. The security and monitoring system for a methanol-fueled marine vessel of claim 1, wherein, Alarm output module, including: The threshold comparison submodule is responsible for receiving analysis results from the data analysis module, including abnormal methanol concentration and leakage risk. Based on the received analysis results, it determines whether a preset alarm threshold has been reached. When the analysis results exceed or reach a certain alarm threshold, it is considered that there is a potential safety risk or abnormal situation. The action execution submodule is responsible for triggering the corresponding alarm action when the analysis results reach the alarm threshold. The positioning and analysis submodule is responsible for obtaining the location coordinates of the alarm-issuing device when an alarm is triggered. The location coordinates are obtained by associating them with the location information of the monitoring device. The alarm content is analyzed to obtain fault prediction results.

8. The security and monitoring system for a methanol-fueled marine vessel of claim 7, wherein, The threshold comparison submodule includes: The data verification unit is responsible for collecting historical methanol concentration and leakage risk data, observing the distribution characteristics of the data by drawing histograms, and performing normality tests on the data to determine whether it conforms to the normal distribution assumption. The threshold determination unit is responsible for identifying data points that deviate from the normal data using a density-based method. Based on the outlier detection results, determine the threshold for outliers or abnormal trends; select a threshold based on the distribution characteristics of outliers. The threshold adjustment unit is responsible for using a portion of historical observations as a validation set to verify whether the set threshold can accurately identify anomalies; and adjusting the threshold based on the validation results.

Images