Intelligent optical cable marine engine room management method and system

Abstract

The invention discloses an intelligent optical cable marine engine room management method and system, and the method comprises the steps: collecting the operation state data of each device in a marine engine room in real time through employing an Internet of Things sensor, transmitting the operation state data to a file module in real time, and carrying out the regular calling of the data, so as to adjust the monitoring parameters of each Internet of Things sensor; performing equipment health assessment on the operation state data by adopting an economical efficiency analysis tool, a performance degradation analysis tool and an equipment operation analysis tool, and generating a health assessment report; and generating a coping strategy for abnormal data in the health assessment report based on the expert knowledge base, and matching corresponding historical events and historical maintenance methods thereof in the archive module. According to the invention, comprehensive health assessment is carried out on each device in the ship by using a multi-dimensional analysis tool, the fault prediction accuracy is improved, a coping strategy is rapidly generated in combination with an expert knowledge base and historical data, the decision-making efficiency is improved, the intelligence level of a ship cabin system is promoted, and the safety, environmental protection, economical efficiency and reliability of ship management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship information management, and in particular to an intelligent optical cable ship cabin management method and system. Background Art

[0002] With the intelligent transformation and digital transformation of the shipping industry, the Internet of Things will become a major driving force for ship intelligence. From a demand perspective, the Internet of Things first meets the need for sensor recognition and information reading, followed by the transmission and sharing of this information through the network. Then, as the number of connected objects increases, system management and information data analysis will be brought about. Finally, it will transform the traditional operation and management model of the shipping industry and realize the iterative upgrade of ship intelligence systems.

[0003] Although the existing ship engine room management system has achieved equipment monitoring and data collection to a certain extent, it still has the following significant shortcomings: 1. Information island problem Existing systems often employ decentralized management, with each subsystem (such as generator sets and main propulsion systems) operating independently. This prevents efficient data sharing and results in poor overall coordination. For example, there's a lack of coordinated analysis between generator set data and the operating status of the main propulsion system, making global optimization difficult.

[0004] 2. Insufficient real-time performance and accuracy Traditional monitoring systems rely on manual inspections and periodic data reporting, which can be time-consuming. For example, equipment anomalies may take hours to be discovered, and manual recording is prone to errors, hindering the timeliness of fault diagnosis.

[0005] 3. Limited level of intelligence Existing systems lack in-depth data analysis capabilities and can only provide basic alarm functions, unable to predict equipment performance degradation or optimize operating strategies. For example, fuel efficiency analysis often relies on static thresholds and cannot be dynamically adjusted to adapt to different operating conditions.

[0006] 4. Weak ship-shore coordination capabilities Shore-based support is typically provided through offline reporting or wired communications, resulting in delayed knowledge base updates and limited access to real-time decision support for crew members. For example, troubleshooting relies on personal experience and lacks a standardized case library.

[0007] 5. Lack of environmental protection and economic optimization Existing technologies rarely integrate real-time optimization of energy consumption and emissions, making it difficult to meet increasingly stringent environmental protection requirements. For example, emissions control often relies on post-processing rather than dynamic adjustment of operating parameters.

[0008] 6. Low data utilization efficiency Historical data is often used for post-analysis, without forming a closed-loop feedback mechanism. For example, equipment maintenance records are not systematically used to improve health analysis models, resulting in frequent recurring failures.

[0009] In summary, the current ship engine room management system has obvious deficiencies in terms of integration, real-time performance, intelligence and collaborative capabilities. It is urgently needed to achieve data fusion, intelligent analysis and ship-shore linkage through the Internet of Things and cloud platform technologies to improve safety, environmental protection and operational efficiency. Summary of the Invention

[0010] The technical problem to be solved by the present invention is to provide an intelligent optical cable ship cabin management method and system, promote the intelligence level of the ship cabin system, and improve the safety, environmental protection, economy and reliability of ship management.

[0011] In order to solve the above technical problems, the technical solution adopted by the present invention is: A smart optical cable ship cabin management method includes the following steps: S1. Using IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmitting the operating status data to an archive module in real time, regularly calling the operating status data in the archive module, and adjusting the monitoring parameters of each IoT sensor in real time; S2. Using an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; S3. Generate a response strategy for the abnormal data in the health assessment report based on the expert knowledge base, and match the corresponding historical events and their historical maintenance methods in the archive module.

[0012] In order to solve the above technical problems, another technical solution adopted by the present invention is: An intelligent optical cable ship cabin management system, including a status monitoring module, a health analysis module, a decision support module and an archive module; The status monitoring module is used to use IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmit the operating status data to the archive module in real time, regularly call the operating status data in the archive module, and adjust the monitoring parameters of each IoT sensor in real time; The health analysis module is used to use an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; The auxiliary decision-making module is used to generate a response strategy for abnormal data in the health assessment report based on the expert knowledge base; The archive module is used to match corresponding historical events and historical maintenance methods based on the abnormal data.

[0013] The beneficial effects of the present invention are: providing an intelligent optical cable ship engine room management method and system, by using Internet of Things sensors to collect the operating status data of various equipment in the ship engine room in real time, ensuring the comprehensiveness and timeliness of monitoring, and at the same time using multi-dimensional analysis tools, namely economic analysis tools, performance degradation analysis tools and equipment operation analysis tools to conduct a comprehensive health assessment of various equipment in the ship, improving the accuracy of fault prediction, and finally combining expert knowledge base and historical data to quickly generate response strategies, reduce human judgment errors, improve decision-making efficiency, and overall promote the intelligence level of the ship engine room system, improve the safety, environmental protection, economy and reliability of ship management; in addition, the sensor parameters are calibrated according to historical data to reduce false alarms and missed alarms, so as to adjust the monitoring frequency for high-risk equipment and improve resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a method for managing an intelligent optical cable ship engine room according to an embodiment of the present invention; Figure 2 This is a schematic structural diagram of an intelligent optical cable ship cabin management system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the monitoring process of various devices in a ship's engine room by a status monitoring module in an intelligent optical cable ship's engine room management system according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the health analysis process of a health analysis module in an intelligent optical cable ship cabin management system according to an embodiment of the invention; Figure 5 This is a schematic diagram of the specific flow of each module of an intelligent optical cable ship cabin management system according to an embodiment of the invention. DETAILED DESCRIPTION

[0015] To illustrate the technical content, achieved objectives and effects of the present invention in detail, the following description is given in conjunction with the embodiments and accompanying drawings.

[0016] Please refer to Figure 1 , a smart optical cable ship cabin management method, comprising the steps of: S1. Using IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmitting the operating status data to an archive module in real time, regularly calling the operating status data in the archive module, and adjusting the monitoring parameters of each IoT sensor in real time; S2. Using an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; S3. Generate a response strategy for the abnormal data in the health assessment report based on the expert knowledge base, and match the corresponding historical events and their historical maintenance methods in the archive module.

[0017] From the above description, it can be seen that the beneficial effects of the present invention are: providing an intelligent optical cable ship cabin management method, by using Internet of Things sensors to collect the operating status data of various equipment in the ship cabin in real time, ensuring the comprehensiveness and timeliness of monitoring, and at the same time using multi-dimensional analysis tools, namely economic analysis tools, performance degradation analysis tools and equipment operation analysis tools to conduct a comprehensive health assessment of various equipment in the ship, thereby improving the accuracy of fault prediction. Finally, combined with the expert knowledge base and historical data, a response strategy is quickly generated to reduce human judgment errors and improve decision-making efficiency, thereby promoting the overall intelligence level of the ship cabin system and improving the safety, environmental protection, economy and reliability of ship management; in addition, the sensor parameters are calibrated according to historical data to reduce false alarms and missed alarms, so as to adjust the monitoring frequency for high-risk equipment and improve resource utilization efficiency.

[0018] Furthermore, the step S2 is specifically as follows: S21. Calculating the fuel consumption rate of the oil-consuming equipment based on the operating status data within a preset period using an economic analysis tool to obtain a fuel economy curve; S22. Using a performance degradation analysis tool to analyze the operating status data within the preset period for degradation of core components of each device under different operating conditions, associating the analysis results with degradation models of corresponding components, using the degradation models to quantify the analysis results, establishing a multiple linear regression model based on the quantified index results of each degradation model, and using the multiple linear regression model to predict the degradation rate of the corresponding component to obtain the operating condition distribution of each core component of the device; S23. Using an equipment operation analysis tool to collect statistics on the ship's speed, power, and fuel efficiency of the operation status data within the preset period, and generate a visual report; S24. Generate a health assessment report based on the fuel economy curve, the operating condition distribution, and the visualization report, and mark data in the health assessment report that exceeds a preset reference value as abnormal data.

[0019] As can be seen from the above description, the fuel consumption rate is calculated through the economic analysis tool to generate a fuel economy curve, which helps optimize ship energy efficiency and reduce operating costs. At the same time, through operating condition distribution analysis and degradation models, component performance is quantified to detect potential faults in advance and reduce sudden equipment damage. It can also generate visual reports to intuitively display the operating status of the equipment, making it easier for crew members to quickly grasp key parameters. Abnormal data can be marked with preset reference values, triggering alarm mechanisms in a timely manner to improve safety.

[0020] Furthermore, the step S3 is specifically as follows: S31. issuing a corresponding abnormal event alarm based on the abnormal data, and calling an expert knowledge base to associate a response strategy for the abnormal event, wherein the expert knowledge base is a ship knowledge base pre-constructed based on historical data-based ship operation and maintenance knowledge; S32. Extract the temporal, spatial, and semantic features of the abnormal event, and match historical events and their corresponding historical maintenance methods in the archive module whose correlation with the abnormal event is greater than a preset correlation by using a rule engine matching method, a time series window analysis method, a topological dependency reasoning method, or a machine learning model. Generate a list of historical events and their corresponding historical maintenance methods based on the correlation from high to low. S33: Output the response strategy and the historical event list and its history maintenance method.

[0021] As can be seen from the above description, the use of expert knowledge bases to provide standardized solutions can shorten fault handling time and improve ship operation reliability. At the same time, historical events are associated through time, space, and semantic features, and combined with rule engines, time series analysis, topological reasoning, and machine learning, while improving the accuracy of fault diagnosis and enhancing the ability to solve complex problems.

[0022] Furthermore, after step S3, the following steps are further included: S4. Obtain records of handling the abnormal event using the response strategy or the historical maintenance method, and feed the records back to the archive module and the expert knowledge base.

[0023] From the above description, we can see that the knowledge base is continuously optimized through the feedback mechanism to improve the accuracy of future decisions. At the same time, the processed records are stored in the archive module to enrich the historical case library and provide a more comprehensive reference basis for subsequent fault diagnosis.

[0024] Please refer to Figures 2 to 5 , an intelligent optical cable ship cabin management system, including a status monitoring module, a health analysis module, a decision support module and an archive module; The status monitoring module is used to use IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmit the operating status data to the archive module in real time, regularly call the operating status data in the archive module, and adjust the monitoring parameters of each IoT sensor in real time; The health analysis module is used to use an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; The auxiliary decision-making module is used to generate a response strategy for abnormal data in the health assessment report based on the expert knowledge base; The archive module is used to match corresponding historical events and historical maintenance methods based on the abnormal data.

[0025] From the above description, it can be seen that the beneficial effects of the present invention are: based on the same technical concept, in conjunction with the above-mentioned intelligent optical cable ship engine room management method, an intelligent optical cable ship engine room management system is provided, which uses Internet of Things sensors to collect real-time operating status data of various equipment in the ship engine room to ensure the comprehensiveness and timeliness of monitoring, and at the same time uses multi-dimensional analysis tools, namely economic analysis tools, performance degradation analysis tools and equipment operation analysis tools to conduct comprehensive health assessments of various equipment in the ship to improve the accuracy of fault prediction. Finally, combined with expert knowledge base and historical data, response strategies are quickly generated to reduce human judgment errors and improve decision-making efficiency, which overall promotes the intelligence level of the ship engine room system and improves the safety, environmental protection, economy and reliability of ship management; in addition, sensor parameters are calibrated according to historical data to reduce false alarms and missed alarms, so as to adjust the monitoring frequency for high-risk equipment and improve resource utilization efficiency.

[0026] Furthermore, the health analysis module is specifically used to: Using an economic analysis tool to calculate the fuel consumption rate of the oil-consuming equipment based on the operating status data within a preset period to obtain a fuel economy curve; Using a performance degradation analysis tool to analyze the operating status data within the preset period for the degradation of the core components of each device under different operating conditions, correlating the degradation models of the corresponding components based on the analysis results, using the degradation models to quantify the analysis results, establishing a multiple linear regression model based on the quantified index results of each degradation model, using the multiple linear regression model to predict the degradation rate of the corresponding component, and obtaining the operating condition distribution of each core component of the device; Using an equipment operation analysis tool to collect statistics on the ship's speed, power and fuel efficiency of the operation status data within the preset period, and generate a visual report; A health assessment report is generated based on the fuel economy curve, the operating condition distribution and the visual report, and data in the health assessment report that exceeds a preset reference value is marked as abnormal data.

[0027] As can be seen from the above description, the fuel consumption rate is calculated through the economic analysis tool to generate a fuel economy curve, which helps optimize ship energy efficiency and reduce operating costs. At the same time, through operating condition distribution analysis and degradation models, component performance is quantified to detect potential faults in advance and reduce sudden equipment damage. It can also generate visual reports to intuitively display the operating status of the equipment, making it easier for crew members to quickly grasp key parameters. Abnormal data can be marked with preset reference values, triggering alarm mechanisms in a timely manner to improve safety.

[0028] Furthermore, the auxiliary decision module is specifically used to: Based on the abnormal data, a corresponding abnormal event alarm is issued, and an expert knowledge base is called to associate and output a response strategy for the abnormal event, wherein the expert knowledge base is a ship knowledge base pre-constructed based on historical data to accumulate ship operation and maintenance knowledge; The archive module is specifically used for: The temporal features, spatial features and semantic features of the abnormal event are extracted, and historical events and their historical maintenance methods in the archive module whose correlation with the abnormal event is greater than a preset correlation are matched through a rule engine matching method, a time series window analysis method, a topological dependency reasoning method or a machine learning model. A list of historical events and their corresponding historical maintenance methods are generated from high to low according to the correlation, and the list of historical events and their historical maintenance methods are output.

[0029] As can be seen from the above description, the use of expert knowledge bases to provide standardized solutions can shorten fault handling time and improve ship operation reliability. At the same time, historical events are associated through time, space, and semantic features, and combined with rule engines, time series analysis, topological reasoning, and machine learning, while improving the accuracy of fault diagnosis and enhancing the ability to solve complex problems.

[0030] Furthermore, the auxiliary decision module is also used to: Obtain records of handling the abnormal event using the response strategy or the historical maintenance method, and feed the records back to the archive module and the expert knowledge base.

[0031] From the above description, we can see that the knowledge base is continuously optimized through the feedback mechanism to improve the accuracy of future decisions. At the same time, the processed records are stored in the archive module to enrich the historical case library and provide a more comprehensive reference basis for subsequent fault diagnosis.

[0032] The present invention provides an intelligent optical cable ship cabin management method and system, which are mainly used in scenarios where the operating status of various equipment in the ship cabin is monitored in real time and abnormal conditions are reported in real time and handled promptly and effectively. The following is a detailed description with reference to specific embodiments: Please refer to Figure 1 , embodiment 1 of the present invention is: A smart optical cable ship cabin management method, such as Figure 1 As shown, the steps include: S1. Use IoT sensors to collect real-time operating status data of each device in the ship's engine room.

[0033] In this embodiment, the main focus is on intelligent perception of the entire ship's status, including monitoring of the operating conditions of generator sets, main propulsion systems, auxiliary engines, boilers, power distribution systems, and auxiliary systems, and feeding back data in real time to the engine room control center via Ethernet, so that early warning alerts can be issued in time for abnormal situations based on pre-set reference values.

[0034] S2. Use economic analysis tools, performance degradation analysis tools, and equipment operation analysis tools to perform equipment health assessment on the operating status data, and upload the health assessment results to the cloud platform to generate a health assessment report. In this embodiment, the alarm distribution analysis tool can also be used to further implement abnormal alarms based on the health analysis results. Among them, economic analysis tools, performance degradation analysis tools and equipment operation analysis tools are all support tools that can provide effective understanding of equipment performance and abnormal status.

[0035] S3. Generate response strategies for abnormal data in health assessment reports based on the expert knowledge base, and match corresponding historical events and their historical maintenance methods in the archive module.

[0036] That is, in this embodiment, the operating status data of each device in the ship's engine room is collected in real time by using Internet of Things sensors to ensure the comprehensiveness and timeliness of monitoring. At the same time, multi-dimensional analysis tools, namely economic analysis tools, performance degradation analysis tools and equipment operation analysis tools, are used to conduct a comprehensive health assessment of each device in the ship to improve the accuracy of fault prediction. Finally, combined with the expert knowledge base and historical data, a response strategy is quickly generated to reduce human judgment errors and improve decision-making efficiency. As a whole, the intelligent level of the ship's engine room system is promoted, and the safety, environmental protection, economy and reliability of ship management are improved.

[0037] In this embodiment, step S1 further includes: The operating status data is transmitted to the archive module in real time, and the operating status data in the archive module is called regularly to adjust the monitoring parameters of each IoT sensor in real time.

[0038] In this embodiment, adjusting and monitoring the real-time parameters of the IoT system is key to ensuring efficient device operation, data accuracy, and system reliability. The specific adjustment steps can be as follows: 1. Clarify key monitoring parameter targets ① Parameter type: Determine the physical quantities to be monitored (such as temperature, humidity, wind speed, location, etc.) and logical parameters (such as device status, network latency, etc.); ② Real-time requirements: define the sampling frequency of parameters (e.g., once per second) and response thresholds (e.g., triggering an alarm when the temperature exceeds 50 degrees); ③ Data usage: Determine the data usage (such as early warning, optimization control, and historical analysis) to guide subsequent storage and processing strategies.

[0039] 2. Data Parameter Transmission and Adjustment By deploying data acquisition communication protocols, device parameters can be remotely configured (such as adjusting sensor sampling frequency) to achieve data processing and storage.

[0040] 3. Implementation Monitoring and Verification For example, deploy a local monitoring system to collect server indicators and monitor the data network transmission status.

[0041] 4. Data Parameter Optimization and Maintenance For example, historical alarm logs can be analyzed through big data learning models to locate high-frequency fault types, and thresholds can be dynamically adjusted based on statistical results (for example, the summer ambient temperature benchmark is increased by 5°C).

[0042] That is, sensor parameters are calibrated based on historical data to reduce false positives and missed positives, so as to adjust the monitoring frequency for high-risk equipment and improve resource utilization efficiency.

[0043] The second embodiment of the present invention is: A smart optical cable ship cabin management method, based on the above embodiment 1, in this embodiment, step S2 is specifically as follows: S21. Use economic analysis tools to calculate the fuel consumption rate of oil-consuming equipment (such as generators) based on the operating status data within a preset period to obtain a fuel economy curve. At the same time, the places in the fuel economy curve that deviate from the normal range can be marked, thereby quickly locating abnormal data.

[0044] The fuel usage of oil-using equipment can be monitored by installing a set of volumetric flow meters or mass flow meters at the inlet and outlet of the fuel pipelines of the ship's daily oil-using equipment. The fuel consumption difference can be used to measure the fuel consumption of the machines during ship operation for individual machines and the overall fuel consumption, thereby achieving real-time monitoring of the ship's fuel consumption and improving the ship's economic benefits.

[0045] For the obtained fuel usage, the main monitoring parameters can be displayed at a glance. The parameters may include the fuel flow meter consumption, instantaneous fuel consumption, cumulative fuel consumption, etc. of the main energy-consuming equipment (including generators, important oil pumps, etc.), as well as the generator set power, speed, load, instantaneous consumption and other parameters of the generator set.

[0046] In this embodiment, the calculation steps of the fuel economy curve are as follows: ① Calculate the specific fuel consumption (SFOC): SFOC (g / kWH) = fuel consumption (g / h) / main engine output power (kW); For example: if the main engine power is 5000kW and the energy consumption is 1000kg per hour, then SFOC=1000×1000 / 5000=200g / kWh.

[0047] ②Normalized load: Convert the host power into a percentage load (e.g. 50% load = 50% of the host rated power).

[0048] ③Draw a curve: (1) Coordinate axis definition X-axis: Host load (%), usually ranging from 25% to 100%; Y-axis: Specific fuel consumption (SFOC, g / kWh).

[0049] (2) Generate curve The load and SFOC data are imported by data acquisition, and a scatter plot is generated in the intelligent system and fitted into a smooth curve.

[0050] (3) General curve judgment The fuel efficiency-load curve of a typical diesel main engine is "U-shaped": Low load (<40%): incomplete combustion, high SFOC (low efficiency); Optimal efficiency range (70%-85%): lowest SFOC (highest efficiency); Overload (>90%): Mechanical loss increases and SFOC rises.

[0051] By inputting the route plan file, the system automatically generates a speed plan, providing feasible recommended economic speed and main propulsion motor speed auxiliary decision-making suggestions for ship energy efficiency management, with the goal of saving fuel (that is, the local optimal oil / gas consumption per nautical mile of the current ship's navigation). Combined with the main propulsion system data, equipment operation data, fuel consumption data, speed data, slip rate data, draft data, wind speed and direction data, and surge data (meteorological information on the route in the next 96 hours), local fine-tuning optimization suggestions for the main propulsion motor are given to achieve dynamic speed optimization throughout the ship's entire voyage.

[0052] S22. Use a performance degradation analysis tool to analyze the degradation of the core components of each device under different working conditions based on the operating status data within a preset period, associate the degradation models of the corresponding components based on the analysis results, use the degradation models to quantify the analysis results, establish a multiple linear regression model based on the quantified indicator results of each degradation model, use the multiple linear regression model to predict the degradation rate of the corresponding components, and obtain the working condition distribution of the core components of each device.

[0053] In this embodiment, the performance degradation analysis tool provides a performance degradation analysis method for each sub-condition of the equipment's operating state and the performance of its core components. Users can compile and view the distribution of equipment operating conditions within a specified time period, providing a data basis for analyzing the degradation of core components and performance changes under different operating conditions. The component degradation rate calculation process can be illustrated as follows: 1. Data Collection 1. Sensor data: equipment operating status data collected in step S1 (such as host power, speed, temperature, pressure, vibration, fuel consumption, etc.); 2. System data: alarm records, electronic logs, operation records, etc.

[0054] 2. Working condition parameter definition and classification 1. Selection of key working condition parameters: Load level (such as the percentage of host power to rated power) Speed range (such as low speed, medium speed, high speed) Temperature / pressure range (such as cooling water temperature, lubricating oil pressure) Vibration spectrum (e.g., vibration amplitude at a specific frequency) 2. Working condition classification: Divide continuous parameters into discrete intervals (for example, host load is divided into 0-25%, 25-50%, 50-75%, and 75-100%).

[0055] 3. Time distribution statistics 1. Calculate the operating time percentage of each working condition: Calculate the cumulative operating time or proportion of the equipment in each operating range (such as the host operating load).

[0056] 2. Time Series Pattern Analysis: Identify high-frequency switching conditions or long-term steady-state conditions.

[0057] 4. Associated Component Decay Model 1. Quantification of recession indicators: Efficiency decrease (such as abnormal increase in SFOC), increased vibration frequency, abnormal temperature, etc.

[0058] 2. Working condition-degradation correlation analysis: Correlation analysis: Calculate the correlation coefficient between operating parameters and degradation indicators; Regression model: Build a multivariate linear regression model and combine it with the AI learning model to predict the decline rate.

[0059] 5. Visual Report 1. Pie chart / bar chart: shows the time proportion of each working condition; 2. Time series stacked chart: dynamically display changes in working conditions; 3. Decline trend chart: Overlay the operating condition distribution and decline index in the same chart to facilitate observation of their correlation.

[0060] 6. Case Application Prediction of cable ship main engine turbocharger degradation and load distribution: (1) Data collection: main engine load, speed, exhaust temperature, and vibration frequency in the past 6 months.

[0061] (2) Principle: The system statistics show that the operating time within the load range of 70-100% accounts for more than 60%. At the same time, it was found that the frequency of turbine speed exceeding the limit increased under high load, and the vibration amplitude increased by 15%.

[0062] (3) System diagnosis and prediction: High load conditions accelerate the expansion of fatigue cracks in turbine blades. It is recommended to moderately reduce the load to reduce the degree of wear and arrange for turbine blade inspections.

[0063] S23. Use equipment operation analysis tools to collect statistics on ship speed, power and fuel efficiency of operation status data within a preset period and generate visual reports.

[0064] The ship's speed, power, and fuel efficiency are the core parameters for evaluating its operating status. The calculation process can be as follows: 1. Parameter calculation formula ①Power P (kW) = 2π·Torque (Nm)·Speed (rpm) / 60000; ② Fuel efficiency (SFOC): SFOC (g / kWh) = fuel consumption (g / h) / power (kW).

[0065] ③Typical relationship between fuel efficiency and speed: At low speeds, combustion is incomplete and the SFOC is high; Optimal efficiency speed range (usually 70%-90% of rated speed); When overloaded, SFOC increases due to increased mechanical losses.

[0066] 2. Data Collection and Processing 1. Speed: Hall sensor or magnetoelectric sensor (rpm).

[0067] 2. Power: Shaft power meter (torque flange) or electric power meter (generator output).

[0068] 3. Fuel consumption: collected by mass flow meter.

[0069] 3. Analysis Algorithm 1. Speed-power curve: Horizontal axis: speed (rpm); vertical axis: power (kW); rated speed (100% MCR).

[0070] 2. Speed-fuel efficiency curve: Horizontal axis: speed (rpm); vertical axis: SFOC (g / kWh); Mark the lowest SFOC point - economic speed zone, for example, SFOC = 190g / kWh at 1800rpm, and compare the efficiency curves under different loads, 50% and 100%, to identify the best efficiency point.

[0071] 3. Three-dimensional relationship (speed-power-SFOC): The random forest regression mathematical model algorithm is used to output curve graphics.

[0072] S24. Generate a health assessment report based on the fuel economy curve, operating condition distribution, and visualization report, and mark the data in the health assessment report that exceeds a preset reference value as abnormal data.

[0073] That is, in this embodiment, the fuel consumption rate is calculated through the economic analysis tool to generate a fuel economy curve, which helps optimize the ship's energy efficiency and reduce operating costs. At the same time, the component performance is quantified through operating condition distribution analysis and degradation models, potential faults are discovered in advance, and sudden equipment damage is reduced. Visual reports can also be generated to intuitively display the equipment's operating status, making it easier for crew members to quickly grasp key parameters. Abnormal data can be marked with preset reference values, and the alarm mechanism can be triggered in time to improve safety.

[0074] In this embodiment, step S3 is specifically as follows: S31. Issue corresponding abnormal event alarms based on abnormal data, and call the expert knowledge base to associate the response strategies for abnormal events. The expert knowledge base is a ship knowledge base that is pre-built based on historical data to precipitate ship operation and maintenance knowledge. It can use the massive historical data transmitted to the cloud platform to establish an expert knowledge base to precipitate the operation and maintenance knowledge of the main equipment of the ship, forming a complete knowledge system of resistance values. When an alarm occurs in the ship's engine room, it can provide possible auxiliary decision-making based on the expert knowledge base in a timely manner to help the crew solve difficult problems. At the same time, it supports the crew to summarize and enter the problems solved each time, stating the cause of the fault, solution, precautions, etc., to enrich and improve the expert knowledge base.

[0075] S32. Extract the temporal features, spatial features, and semantic features of abnormal events, and match historical events and their historical maintenance methods in the archive module whose correlation with abnormal events is greater than a preset correlation through rule engine matching method, time series window analysis method, topological dependency reasoning method, or machine learning model, and generate a list of historical events and their corresponding historical maintenance methods according to the correlation from high to low.

[0076] The association is based on historical big data, and the specific steps are as follows: 1. The core steps of association: 1. Data collection and preprocessing (preconditions) Purpose: Prepare clean, structured data extracts for association analysis; reduce data noise and avoid false associations.

[0077] Key operations: Deduplication: Duplicate alarms are merged (e.g., a device reports the same error multiple times within 10 seconds); Time alignment: unify timestamps from multiple data sources to avoid incorrect associations due to time deviations; Field completion: Supplement contextual information such as the cluster to which the device belongs and service dependencies.

[0078] 2. Feature extraction (the basis of association analysis) Its main function is to extract the correlation features of the alarm when the trigger conditions are met for subsequent analysis. The extracted semantic, topological and other features and association rules are the basis of model analysis.

[0079] Key Features: ① Time characteristics: alarm trigger time, duration, and periodic pattern.

[0080] ②Spatial characteristics: physical location and logical topology.

[0081] ③Semantic features: alarm type, etc.

[0082] 3. Correlation Analysis Function: Identify the correlation between alarms through rules, statistics or model methods, and convert the results of correlation analysis into language output that can be understood by personnel.

[0083] step: ①Rule engine matching: ② Timing window analysis: ③Topological dependency reasoning: ④AI learning model reasoning.

[0084] 4. Result output Convert the analysis results into visual graphs.

[0085] S33. Output the response strategy and the list of historical events and their historical maintenance method.

[0086] This means using the expert knowledge base to provide standardized solutions, shorten troubleshooting time, and improve ship operation reliability. It also uses temporal, spatial, and semantic features to correlate historical events, and combines rule engines, time series analysis, topological reasoning, and machine learning to improve the accuracy of fault diagnosis while enhancing the ability to solve complex problems. Furthermore, after step S3, the following steps are also included: S4. Obtain records of handling abnormal events using response strategies or historical maintenance methods, and feed the records back to the archive module and expert knowledge base.

[0087] That is, through the feedback mechanism, the knowledge base is continuously optimized to improve the accuracy of future decisions. At the same time, the processed records are stored in the archive module to enrich the historical case library and provide a more comprehensive reference basis for subsequent fault diagnosis. At the same time, the archive module supports retrieval. It can display the current event and historical event list in different tables according to the current status of the abnormal event of the alarm. The list supports filtering according to the alarm level, occurrence time, equipment name, alarm event name, etc. After the archive module matches the associated data of the abnormal event that caused the alarm, it can automatically match the possible cause of the event and the maintenance activity suggestion based on mechanistic knowledge. At the same time, it supports the rapid matching and retrieval function of similar alarm cases. By uploading a large amount of data to the cloud platform, standardized data files are formed, and daily engine logs and daily event lists are generated to facilitate shore-based personnel to search and query archive data.

[0088] Please refer to Figures 2 to 4 , the third embodiment of the present invention is: An intelligent optical cable ship cabin management system, such as Figure 2 As shown, it includes status monitoring module, health analysis module, decision support module and archive module.

[0089] Among them, the status monitoring module is used to collect the operating status data of various equipment in the ship's engine room in real time using IoT sensors.

[0090] In this embodiment, the main focus is on intelligent perception of the entire ship's status, such as Figure 3 As shown, it includes operating status monitoring of generator sets, main propulsion systems, auxiliary engines, boilers, power distribution systems, and auxiliary systems, and feeds data back to the engine room control center in real time via Ethernet, so that early warning reminders can be issued in time for abnormal situations based on pre-set reference values.

[0091] The health analysis module is used to use economic analysis tools, performance degradation analysis tools and equipment operation analysis tools to evaluate the equipment health based on the operation status data, and upload the health evaluation results to the cloud platform to generate a health evaluation report, such as Figure 4As shown, in this embodiment, an alarm distribution analysis tool can be used to further implement abnormal alarms based on the health analysis results.

[0092] Among them, economic analysis tools, performance degradation analysis tools and equipment operation analysis tools are all support tools that can provide effective understanding of equipment performance and abnormal status.

[0093] The auxiliary decision-making module is used to generate response strategies for abnormal data in health assessment reports based on the expert knowledge base.

[0094] The archive module is used to match corresponding historical events and their historical maintenance methods based on abnormal data.

[0095] That is, in this embodiment, the operating status data of each device in the ship's engine room is collected in real time by using Internet of Things sensors to ensure the comprehensiveness and timeliness of monitoring. At the same time, multi-dimensional analysis tools, namely economic analysis tools, performance degradation analysis tools and equipment operation analysis tools, are used to conduct a comprehensive health assessment of each device in the ship to improve the accuracy of fault prediction. Finally, combined with the expert knowledge base and historical data, a response strategy is quickly generated to reduce human judgment errors and improve decision-making efficiency. As a whole, the intelligent level of the ship's engine room system is promoted, and the safety, environmental protection, economy and reliability of ship management are improved.

[0096] In this embodiment, the status monitoring module is further used to: The operating status data is transmitted to the archive module in real time, and the operating status data in the archive module is called regularly to adjust the monitoring parameters of each IoT sensor in real time.

[0097] That is, sensor parameters are calibrated based on historical data to reduce false positives and missed positives, so as to adjust the monitoring frequency for high-risk equipment and improve resource utilization efficiency.

[0098] Please refer to Figure 5 , the fourth embodiment of the present invention is: An intelligent optical cable ship engine room management system, based on the above-mentioned embodiment 3, in this embodiment, the health analysis module is specifically used to: Use economic analysis tools to calculate the fuel consumption rate of fuel-consuming equipment (such as generators) based on operating status data within a preset period to generate a fuel economy curve. Departures from the normal range in the fuel economy curve can also be marked, allowing for quick identification of abnormal data.

[0099] The fuel usage of oil-using equipment can be monitored by installing a set of volumetric flow meters or mass flow meters at the inlet and outlet of the fuel pipelines of the ship's daily oil-using equipment. The fuel consumption difference can be used to measure the fuel consumption of the machines during ship operation for individual machines and the overall fuel consumption, thereby achieving real-time monitoring of the ship's fuel consumption and improving the ship's economic benefits.

[0100] For the obtained fuel usage, the main monitoring parameters can be displayed at a glance. The parameters may include the fuel flow meter consumption, instantaneous fuel consumption, cumulative fuel consumption, etc. of the main energy-consuming equipment (including generators, important oil pumps, etc.), as well as the generator set power, speed, load, instantaneous consumption and other parameters of the generator set.

[0101] In this embodiment, the calculation steps of the fuel economy curve are as follows: ① Calculate the specific fuel consumption (SFOC): SFOC (g / kWH) = fuel consumption (g / h) / main engine output power (kW); For example: if the main engine power is 5000kW and the energy consumption is 1000kg per hour, then SFOC=1000×1000 / 5000=200g / kWh.

[0102] ②Normalized load: Convert the host power into a percentage load (e.g. 50% load = 50% of the host rated power).

[0103] ③Draw a curve: (1) Coordinate axis definition X-axis: Host load (%), usually ranging from 25% to 100%; Y-axis: Specific fuel consumption (SFOC, g / kWh).

[0104] (2) Generate curve The load and SFOC data are imported by data acquisition, and a scatter plot is generated in the intelligent system and fitted into a smooth curve.

[0105] (3) General curve judgment The fuel efficiency-load curve of a typical diesel main engine is "U-shaped": Low load (<40%): incomplete combustion, high SFOC (low efficiency); Optimal efficiency range (70%-85%): lowest SFOC (highest efficiency); Overload (>90%): Mechanical loss increases and SFOC rises.

[0106] By inputting the route plan file, the system automatically generates a speed plan, providing feasible recommended economic speed and main propulsion motor speed auxiliary decision-making suggestions for ship energy efficiency management, with the goal of saving fuel (that is, the local optimal oil / gas consumption per nautical mile of the current ship's navigation). Combined with the main propulsion system data, equipment operation data, fuel consumption data, speed data, slip rate data, draft data, wind speed and direction data, and surge data (meteorological information on the route in the next 96 hours), local fine-tuning optimization suggestions for the main propulsion motor are given to achieve dynamic speed optimization throughout the ship's entire voyage.

[0107] A performance degradation analysis tool is used to analyze the degradation of the core components of each device under different working conditions based on the operating status data within a preset period. The degradation models of the corresponding components are associated with the analysis results, and the degradation models are used to quantify the analysis results. A multiple linear regression model is established based on the quantified indicator results of each degradation model. The multiple linear regression model is used to predict the degradation rate of the corresponding components to obtain the working condition distribution of the core components of each device.

[0108] In this embodiment, the performance degradation analysis tool provides a performance degradation analysis method for each sub-condition of the equipment's operating state and the performance of its core components. Users can compile and view the distribution of equipment operating conditions within a specified time period, providing a data basis for analyzing the degradation of core components and performance changes under different operating conditions. The component degradation rate calculation process can be illustrated as follows: 1. Data Collection 1. Sensor data: equipment operating status data collected in step S1 (such as host power, speed, temperature, pressure, vibration, fuel consumption, etc.); 2. System data: alarm records, electronic logs, operation records, etc.

[0109] 2. Working condition parameter definition and classification 1. Selection of key working condition parameters: Load level (such as the percentage of host power to rated power) Speed range (such as low speed, medium speed, high speed) Temperature / pressure range (such as cooling water temperature, lubricating oil pressure) Vibration spectrum (e.g., vibration amplitude at a specific frequency) 2. Working condition classification: Divide continuous parameters into discrete intervals (for example, host load is divided into 0-25%, 25-50%, 50-75%, and 75-100%).

[0110] 3. Time distribution statistics 1. Calculate the operating time percentage of each working condition: Calculate the cumulative operating time or proportion of the equipment in each operating range (such as the host operating load).

[0111] 2. Time Series Pattern Analysis: Identify high-frequency switching conditions or long-term steady-state conditions.

[0112] 4. Associated Component Decay Model 1. Quantification of recession indicators: Efficiency decrease (such as abnormal increase in SFOC), increased vibration frequency, abnormal temperature, etc.

[0113] 2. Working condition-degradation correlation analysis: Correlation analysis: Calculate the correlation coefficient between operating parameters and degradation indicators; Regression model: Build a multivariate linear regression model and combine it with the AI learning model to predict the decline rate.

[0114] 5. Visual Report 1. Pie chart / bar chart: shows the time proportion of each working condition; 2. Time series stacked chart: dynamically display changes in working conditions; 3. Decline trend chart: Overlay the operating condition distribution and decline index in the same chart to facilitate observation of their correlation.

[0115] 6. Case Application Prediction of cable ship main engine turbocharger degradation and load distribution: (1) Data collection: main engine load, speed, exhaust temperature, and vibration frequency in the past 6 months.

[0116] (2) Principle: The system statistics show that the operating time within the load range of 70-100% accounts for more than 60%. At the same time, it was found that the frequency of turbine speed exceeding the limit increased under high load, and the vibration amplitude increased by 15%.

[0117] (3) System diagnosis and prediction: High load conditions accelerate the expansion of fatigue cracks in turbine blades. It is recommended to moderately reduce the load to reduce the degree of wear and arrange for turbine blade inspections.

[0118] The equipment operation analysis tool is used to collect statistics on ship speed, power and fuel efficiency of the operating status data within a preset period, and generate visual reports.

[0119] The ship's speed, power, and fuel efficiency are the core parameters for evaluating its operating status. The calculation process can be as follows: 1. Parameter calculation formula ①Power P (kW) = 2π·Torque (Nm)·Speed (rpm) / 60000; ② Fuel efficiency (SFOC): SFOC (g / kWh) = fuel consumption (g / h) / power (kW).

[0120] ③Typical relationship between fuel efficiency and speed: At low speeds, combustion is incomplete and the SFOC is high; Optimal efficiency speed range (usually 70%-90% of rated speed); When overloaded, SFOC increases due to increased mechanical losses.

[0121] 2. Data Collection and Processing 1. Speed: Hall sensor or magnetoelectric sensor (rpm).

[0122] 2. Power: Shaft power meter (torque flange) or electric power meter (generator output).

[0123] 3. Fuel consumption: collected by mass flow meter.

[0124] 3. Analysis Algorithm 1. Speed-power curve: Horizontal axis: speed (rpm); vertical axis: power (kW); rated speed (100% MCR).

[0125] 2. Speed-fuel efficiency curve: Horizontal axis: speed (rpm); vertical axis: SFOC (g / kWh); Mark the lowest SFOC point - economic speed zone, for example, SFOC = 190g / kWh at 1800rpm, and compare the efficiency curves under different loads, 50% and 100%, to identify the best efficiency point.

[0126] 3. Three-dimensional relationship (speed-power-SFOC): The random forest regression mathematical model algorithm is used to output curve graphics.

[0127] Generate a health assessment report based on the fuel economy curve, operating condition distribution and visual report, and mark the data in the health assessment report that exceeds the preset reference value as abnormal data.

[0128] That is, in this embodiment, the fuel consumption rate is calculated through the economic analysis tool to generate a fuel economy curve, which helps optimize the ship's energy efficiency and reduce operating costs. At the same time, the component performance is quantified through operating condition distribution analysis and degradation models, potential faults are discovered in advance, and sudden equipment damage is reduced. Visual reports can also be generated to intuitively display the equipment's operating status, making it easier for crew members to quickly grasp key parameters. Abnormal data can be marked with preset reference values, and the alarm mechanism can be triggered in time to improve safety.

[0129] In this embodiment, the auxiliary decision module is specifically used to: Based on abnormal data, corresponding abnormal event alarms are issued, and the expert knowledge base is called to associate the response strategies of abnormal events and output them. The expert knowledge base is a ship knowledge base that is pre-built based on the ship operation and maintenance knowledge accumulated based on historical data.

[0130] The archive module is specifically used for: Extract the temporal, spatial, and semantic features of abnormal events, and match historical events and their historical maintenance methods in the archive module whose correlation with abnormal events is greater than the preset correlation through rule engine matching method, time series window analysis method, topological dependency reasoning method, or machine learning model. Generate a list of historical events and their corresponding historical maintenance methods from high to low according to the correlation, and output the list of historical events and their historical maintenance methods.

[0131] The association is based on historical big data, and the specific steps are as follows: 1. The core steps of association: 1. Data collection and preprocessing (preconditions) Purpose: Prepare clean, structured data extracts for association analysis; reduce data noise and avoid false associations.

[0132] Key operations: Deduplication: Duplicate alarms are merged (e.g., a device reports the same error multiple times within 10 seconds); Time alignment: unify timestamps from multiple data sources to avoid incorrect associations due to time deviations; Field completion: Supplement contextual information such as the cluster to which the device belongs and service dependencies.

[0133] 2. Feature extraction (the basis of association analysis) Its main function is to extract the correlation features of the alarm when the trigger conditions are met for subsequent analysis. The extracted semantic, topological and other features and association rules are the basis of model analysis.

[0134] Key Features: ① Time characteristics: alarm trigger time, duration, and periodic pattern.

[0135] ②Spatial characteristics: physical location and logical topology.

[0136] ③Semantic features: alarm type, etc.

[0137] 3. Correlation Analysis Function: Identify the correlation between alarms through rules, statistics or model methods, and convert the results of correlation analysis into language output that can be understood by personnel.

[0138] step: ①Rule engine matching: ② Timing window analysis: ③Topological dependency reasoning: ④AI learning model reasoning.

[0139] 4. Result output Convert the analysis results into visual graphs.

[0140] That is, it uses the expert knowledge base to provide standardized solutions, shorten fault handling time, and improve ship operation reliability; at the same time, it also associates historical events through time, space, and semantic features, and combines rule engines, timing analysis, topological reasoning, and machine learning to improve the accuracy of fault diagnosis while enhancing the ability to solve complex problems.

[0141] In addition, the decision support module is also used to: Capture records of handling abnormal events using response strategies or historical maintenance methods, and feed the records back into the archive module and expert knowledge base.

[0142] That is, through the feedback mechanism, the knowledge base is continuously optimized to improve the accuracy of future decisions. At the same time, the processed records are stored in the archive module to enrich the historical case library and provide a more comprehensive reference basis for subsequent fault diagnosis. At the same time, the archive module supports retrieval. It can display the current event and historical event list in different tables according to the current status of the abnormal event of the alarm. The list supports filtering according to the alarm level, occurrence time, equipment name, alarm event name, etc. After the archive module matches the associated data of the abnormal event that caused the alarm, it can automatically match the possible cause of the event and the maintenance activity suggestion based on mechanistic knowledge. At the same time, it supports the rapid matching and retrieval function of similar alarm cases. By uploading a large amount of data to the cloud platform, standardized data files are formed, and daily engine logs and daily event lists are generated to facilitate shore-based personnel to search and query archive data.

[0143] On the basis of the above, in this embodiment, if Figure 5 As shown in FIG, the data transmission relationship among the supplementary status monitoring module, health analysis module, decision support module and archive module is supplemented, that is, how the collaboration between the four modules is achieved is specifically explained.

[0144] (1) Status Monitoring Module → Health Analysis Module Transmission content: pre-processed real-time sensor data (such as temperature, pressure, vibration, position, etc.) and abnormal indicators.

[0145] Collaboration: The status monitoring module pushes data to the health analysis module in real time or periodically, triggering health assessments. Data may be transmitted via a message queue (such as Kafka) for high throughput, ensuring timely analysis.

[0146] (2) Health Analysis Module → Decision Support Module Transmitted content: health assessment reports (such as system health scores), fault warnings (such as bearing wear), remaining life predictions (such as engine life), and root cause analysis.

[0147] Collaboration Mechanism: The health analysis module notifies the auxiliary decision-making module through APIs or event-driven methods (such as webhooks) to generate response strategies. For example, if an abnormality in the lubrication system is detected, the decision-making process is immediately triggered.

[0148] (3) Decision-making support module → Archives module Transmission content: The decision module proactively queries historical maintenance methods, similar failure cases, spare parts inventory, and operating manuals.

[0149] Collaboration mechanism: Decision support retrieves archives through database query interfaces (such as SQL or Elasticsearch), combines real-time data with historical information to generate optimization suggestions (such as giving priority to verified maintenance solutions).

[0150] (4) Archives Module → Health Analysis Module Transmitted content: historical health data, model training datasets, failure mode libraries, and maintenance records.

[0151] Collaboration mechanism: The health analysis module regularly extracts data from archives for machine learning model iteration (such as LSTM prediction model optimization) to improve analysis accuracy.

[0152] (5) Health Analysis Module → Archives Module Transmission content: storage health reports, analysis model parameters, fault characteristics and trend analysis results.

[0153] Collaboration mechanism: Through batch writing or real-time storage (such as the time series database InfluxDB), a complete historical health record is built to support long-term trend analysis.

[0154] (6) Decision support module → Health analysis module Transmission content: Feedback on decision execution results (such as system status after maintenance) and model adjustment suggestions (such as updating fault thresholds).

[0155] Collaborative mechanism: Decision-making results are fed back to the health analysis module, and the analysis logic is dynamically optimized (such as adjusting the alarm threshold) to form a closed-loop learning.

[0156] (7) Status Monitoring Module → Archive Module Transmission content: raw sensor data, pre-processed data, and device operation logs.

[0157] Collaboration mechanism: Regularly archive data through ETL tools to support subsequent audits, compliance checks and big data analysis.

[0158] (8) Archive Module → Status Monitoring Module Transmission content: historical normal data range, equipment calibration benchmark.

[0159] Collaboration mechanism: The condition monitoring module uses archival data to calibrate sensors (such as comparing historical temperature curves) to reduce false alarms.

[0160] (9) Decision-making support module → Status monitoring module Transmission content: Dynamic monitoring parameter adjustment instructions (such as increasing the sampling frequency of a specific sensor).

[0161] Collaboration mechanism: For high-risk components, the decision-making module issues instructions to focus monitoring and improve detection efficiency.

[0162] In summary, the present invention provides a smart optical cable ship engine room management method and system, which aims to promote the intelligence level of ship engine room systems and improve the safety, environmental protection, economy and reliability of ships. It has the following beneficial effects: 1. Improve safety: By collecting operating status data of various equipment in the cabin through sensors, potential safety hazards can be discovered in a timely manner and corresponding alarm information can be issued to ensure the comprehensiveness and timeliness of monitoring.

[0163] 2. Improve environmental protection: According to the actual operating conditions of the ship, energy consumption and emission control can be optimized to reduce the impact on the environment.

[0164] 3. Improve economic efficiency: Through detailed analysis of various functions of the ship, the operating costs of the ship can be reduced and the economic benefits can be improved.

[0165] 4. Improve reliability: Intelligently monitor equipment status in real time, predict equipment failures, and provide maintenance recommendations, thereby improving the reliability of ship operations.

[0166] 5. Improve working conditions: Combine expert knowledge base and historical data to quickly generate response strategies, reduce human judgment errors, improve decision-making efficiency, and reduce the workload of crew members.

[0167] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's description and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A smart optical cable ship cabin management method, characterized in that: Including steps: S1. Using IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmitting the operating status data to an archive module in real time, regularly calling the operating status data in the archive module, and adjusting the monitoring parameters of each IoT sensor in real time; S2. Using an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; S3. Generate a response strategy for the abnormal data in the health assessment report based on the expert knowledge base, and match the corresponding historical events and their historical maintenance methods in the archive module.

2. The intelligent optical cable ship cabin management method according to claim 1 is characterized in that: The step S2 is specifically as follows: S21. Calculating the fuel consumption rate of the oil-consuming equipment based on the operating status data within a preset period using an economic analysis tool to obtain a fuel economy curve; S22. Using a performance degradation analysis tool to analyze the operating status data within the preset period for degradation of core components of each device under different operating conditions, associating the analysis results with degradation models of corresponding components, using the degradation models to quantify the analysis results, establishing a multiple linear regression model based on the quantified index results of each degradation model, and using the multiple linear regression model to predict the degradation rate of the corresponding component to obtain the operating condition distribution of each core component of the device; S23. Using an equipment operation analysis tool to collect statistics on the ship's speed, power, and fuel efficiency of the operation status data within the preset period, and generate a visual report; S24. Generate a health assessment report based on the fuel economy curve, the operating condition distribution, and the visualization report, and mark data in the health assessment report that exceeds a preset reference value as abnormal data.

3. The intelligent optical cable ship cabin management method according to claim 1 is characterized in that: The step S3 is specifically as follows: S31. issuing a corresponding abnormal event alarm based on the abnormal data, and calling an expert knowledge base to associate a response strategy for the abnormal event, wherein the expert knowledge base is a ship knowledge base pre-constructed based on historical data-based ship operation and maintenance knowledge; S32. Extract the temporal, spatial, and semantic features of the abnormal event, and match historical events and their corresponding historical maintenance methods in the archive module whose correlation with the abnormal event is greater than a preset correlation by using a rule engine matching method, a time series window analysis method, a topological dependency reasoning method, or a machine learning model. Generate a list of historical events and their corresponding historical maintenance methods based on the correlation from high to low. S33: Output the response strategy and the historical event list and its history maintenance method.

4. The intelligent optical cable ship cabin management method according to claim 3 is characterized in that: After step S3, the following steps are also included: S4. Obtain records of handling the abnormal event using the response strategy or the historical maintenance method, and feed the records back to the archive module and the expert knowledge base.

5. An intelligent optical cable ship cabin management system, characterized in that: Including status monitoring module, health analysis module, decision support module and archive module; The status monitoring module is used to use IoT sensors to collect operating status data of various devices in the ship's engine room in real time, transmit the operating status data to the archive module in real time, regularly call the operating status data in the archive module, and adjust the monitoring parameters of each IoT sensor in real time; The health analysis module is used to use an economic analysis tool, a performance degradation analysis tool, and an equipment operation analysis tool to perform an equipment health assessment on the operation status data and generate a health assessment report; The auxiliary decision-making module is used to generate a response strategy for abnormal data in the health assessment report based on the expert knowledge base; The archive module is used to match corresponding historical events and historical maintenance methods based on the abnormal data.

6. The intelligent optical cable ship cabin management system according to claim 5, characterized in that: The health analysis module is specifically used to: Using an economic analysis tool to calculate the fuel consumption rate of the oil-consuming equipment based on the operating status data within a preset period to obtain a fuel economy curve; Using a performance degradation analysis tool to analyze the operating status data within the preset period for the degradation of the core components of each device under different operating conditions, correlating the degradation models of the corresponding components based on the analysis results, using the degradation models to quantify the analysis results, establishing a multiple linear regression model based on the quantified index results of each degradation model, using the multiple linear regression model to predict the degradation rate of the corresponding component, and obtaining the operating condition distribution of each core component of the device; Using an equipment operation analysis tool to collect statistics on the ship's speed, power and fuel efficiency of the operation status data within the preset period, and generate a visual report; A health assessment report is generated based on the fuel economy curve, the operating condition distribution and the visual report, and data in the health assessment report that exceeds a preset reference value is marked as abnormal data.

7. The intelligent optical cable ship cabin management system according to claim 5, characterized in that: The auxiliary decision module is specifically used to: Based on the abnormal data, a corresponding abnormal event alarm is issued, and an expert knowledge base is called to associate and output a response strategy for the abnormal event, wherein the expert knowledge base is a ship knowledge base pre-constructed based on historical data to accumulate ship operation and maintenance knowledge; The archive module is specifically used for: The temporal features, spatial features and semantic features of the abnormal event are extracted, and historical events and their historical maintenance methods in the archive module whose correlation with the abnormal event is greater than a preset correlation are matched through a rule engine matching method, a time series window analysis method, a topological dependency reasoning method or a machine learning model. A list of historical events and their corresponding historical maintenance methods are generated from high to low according to the correlation, and the list of historical events and their historical maintenance methods are output.

8. The intelligent optical cable ship cabin management system according to claim 7, characterized in that: The auxiliary decision module is also used for: Obtain records of handling the abnormal event using the response strategy or the historical maintenance method, and feed the records back to the archive module and the expert knowledge base.

Images