Ship electric power intelligent operation and maintenance platform based on digital twinning

Abstract

The invention belongs to the technical field of power system operation and maintenance, and particularly discloses a digital twinning-based ship power intelligent operation and maintenance platform, which comprises a data acquisition layer, a digital twinning model layer, a data analysis and processing layer, an intelligent decision and control layer and a visual display layer, the data acquisition layer comprises sensors and environment sensors which are mounted on equipment of a ship power system, and is used for acquiring equipment operation parameters and ship surrounding environment information; the digital twinborn model layer constructs a three-dimensional digital twinborn model of the ship power system; the data analysis and processing layer cleans and preprocesses the collected data, and analyzes and mines the data by using machine learning and deep learning algorithms. The intelligent decision and control layer automatically generates operation and maintenance decisions and suggestions according to a data analysis result, and gives an alarm and provides an emergency strategy when a fault or an abnormality occurs; and the visual display layer displays the system operation state, the fault information and the operation and maintenance decision in the forms of graphs, charts and reports.

Description

Technical Field

[0001] This invention relates to the field of power system operation and maintenance technology, specifically to a ship power intelligent operation and maintenance platform based on digital twins. Background Technology

[0002] Ship electrical systems are a critical component of vessels, and their reliability and stability directly impact navigational safety and normal operation. Traditional ship electrical system maintenance relies primarily on manual inspections and periodic maintenance, which suffers from low efficiency, high costs, and an inability to detect potential faults in a timely manner. Moreover, due to the complex and variable operating environment of ships, electrical systems face various uncertainties, making traditional maintenance methods insufficient to meet the demands for efficient and precise maintenance of ship electrical systems. Summary of the Invention

[0003] The purpose of this invention is to provide a digital twin-based intelligent operation and maintenance platform for ship power systems. By constructing a digital twin model of the ship's power system and combining it with real-time data acquisition and analysis, the platform enables intelligent operation and maintenance of the ship's power system, thereby improving operation and maintenance efficiency and reliability and reducing operation and maintenance costs.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a ship power intelligent operation and maintenance platform based on digital twins, comprising a data acquisition layer, a digital twin model layer, a data analysis and processing layer, an intelligent decision-making and control layer, and a visualization display layer.

[0005] The data acquisition layer includes sensors installed on various devices in the ship's electrical system, as well as environmental sensors, used to collect equipment operating parameters and information about the ship's surrounding environment.

[0006] The digital twin model layer constructs a three-dimensional digital twin model of the ship's power system and updates and corrects the model in real time based on the collected real-time data.

[0007] The data analysis and processing layer cleans and preprocesses the collected data, and uses machine learning and deep learning algorithms to analyze and mine the data to achieve fault diagnosis, equipment life prediction, and performance evaluation.

[0008] The intelligent decision-making and control layer automatically generates operation and maintenance decisions and suggestions based on data analysis results, issues alarms and provides emergency strategies when there is a fault or anomaly, and can remotely control equipment.

[0009] The visualization layer displays system operating status, fault information, and maintenance decisions in the form of graphics, charts, and reports, and provides an interactive interface for personnel to operate and query.

[0010] This enables digital management of the entire lifecycle of ship electrical systems, improving operation and maintenance efficiency by over 40%. A five-layer architecture forms a closed-loop control logic of "perception, modeling, analysis, decision-making, and interaction."

[0011] As a preferred embodiment of the present invention, the device operating parameters in the data acquisition layer include, but are not limited to, current, voltage, temperature, humidity, and vibration.

[0012] Current is used to accurately collect the current values ​​of various devices in the ship's power system, distinguishing the magnitude, direction, and changes of current in different lines and devices; voltage is used to monitor the voltage stability of the ship's power system, including the voltage values ​​of different busbars and the range of voltage fluctuations; temperature is used to monitor the temperature of key equipment in real time, including generators, transformers, and motors; humidity is used because the humidity of the ship's environment has a significant impact on the insulation performance of power equipment. Excessive humidity may cause insulation materials to become damp, reducing insulation performance and increasing the risk of leakage; vibration is used to monitor the vibration of equipment through vibration sensors. Abnormal vibration may indicate mechanical failure of the equipment, and analyzing vibration signals can help detect potential problems in advance.

[0013] Multi-physical quantity collaborative monitoring enables fault identification to achieve a completeness of 98%. A vibration monitoring system is constructed based on the ISO-18436 standard.

[0014] As a preferred embodiment of the present invention, the three-dimensional digital twin model of the digital twin model layer accurately maps the physical structure and electrical connection relationship of the ship's power system, and can reflect the dynamic changes of the system in real time.

[0015] The physical structure is a three-dimensional digital twin model that accurately represents the physical characteristics of the shape, size, and location of each device in the ship's power system; the electrical connection relationship is to accurately represent the electrical connections between the devices in the power system, including the circuit topology and current flow; and the model's status is updated in a timely manner based on real-time data collected by the data acquisition layer.

[0016] The deviation between the model and the actual system state is controlled within ±0.5%. A unified multi-domain model is constructed using Modelica, with a data refresh cycle of ≤100ms.

[0017] As a preferred embodiment of the present invention, the data analysis and processing layer uses an anomaly detection algorithm to identify abnormal operating data of power equipment to determine potential faults, and predicts the remaining service life of the equipment based on the equipment's historical operating data and current status.

[0018] Anomaly detection algorithms identify outliers in power equipment operating data; potential faults are identified by analyzing detected anomalies using historical fault data and expert knowledge to determine the type and severity of potential faults; and the remaining service life (RUL) of equipment is predicted by collecting historical operating data, including operating time, load conditions, and maintenance records, and combining this data with the current operating status. Machine learning or deep learning algorithms are then used to build an equipment life prediction model, which can predict the remaining service life of the equipment, providing a basis for maintenance and replacement. This achieves 72-hour advance warning of major faults, with a RUL prediction error of ≤5%.

[0019] As a preferred embodiment of the present invention, the operation and maintenance decisions and suggestions generated by the intelligent decision and control layer include maintenance plans, repair schemes, and emergency handling measures, which can provide corresponding solutions according to different fault levels and equipment statuses.

[0020] The maintenance plan is to develop a reasonable maintenance plan based on the equipment's operating status and life prediction results; the repair plan is to generate a detailed repair plan when a fault or potential fault is detected in the equipment; the emergency response measures are to develop corresponding emergency response measures for different types of faults and emergencies; and the graded solutions provide different levels of solutions based on the fault level and the equipment's condition.

[0021] This reduces unplanned downtime by 60%. It utilizes FMEA-based fault tree analysis combined with dynamic Bayesian network decision-making.

[0022] As a preferred embodiment of the present invention, the visualization layer notifies maintenance personnel of maintenance decisions and suggestions via SMS and email, displays information through visualization tools, and develops an interactive interface for maintenance personnel to operate and query. The interactive interface supports multi-dimensional data query and analysis.

[0023] When the system generates operation and maintenance decisions and suggestions, it promptly notifies relevant operation and maintenance personnel via SMS and email. Visualization tools, including dashboards, charts, and maps, are used to intuitively display the system's operating status, fault information, and operation and maintenance decisions to operation and maintenance personnel. An interactive interface is developed for operation and maintenance personnel to operate and query. Operation and maintenance personnel can enter keywords and filter conditions through the interface to query the information they need. The interactive interface supports multi-dimensional data query and analysis functions.

[0024] Alarm messages are delivered within 5 seconds, and real-time rendering of 100,000 data points is supported. Alarms are pushed using the MQTT protocol, and 3D visualization is implemented on the browser side using WebGL.

[0025] As a preferred embodiment of the present invention, the data acquisition layer and the digital twin model layer interact through a data transmission interface to ensure that the acquired data is accurately and timely transmitted to the digital twin model layer.

[0026] The data transmission interface adopts a standardized data transmission interface to ensure compatibility and interoperability between the data acquisition layer and the digital twin model layer. During the data transmission process, data verification and error correction mechanisms are used to ensure data accuracy. The data transmission process is optimized to reduce data transmission latency. High-speed communication networks and data caching technology are used to enable the acquired data to be transmitted to the digital twin model layer in a timely manner so that the model can be updated in real time.

[0027] Data transmission packet loss rate <0.001%. Multi-source data synchronization is achieved using the IEEE 1588 precise time protocol.

[0028] As a preferred embodiment of the present invention, the data analysis and processing layer can also analyze the energy consumption of the ship's power system and provide energy-saving optimization suggestions to reduce the ship's operating costs.

[0029] Energy consumption analysis involves collecting and analyzing energy consumption data from the ship's electrical system, including the energy consumption of different equipment and changes in energy consumption over different time periods. By analyzing the energy consumption data, the equipment and processes with high energy consumption are identified, as well as the patterns of energy consumption changes. Energy-saving optimization suggestions are provided based on the results of the energy consumption analysis. When proposing energy-saving optimization suggestions, the costs required to implement the suggestions and the expected energy-saving effects are evaluated.

[0030] Overall energy efficiency is improved by 8-12%, and the load distribution of generator sets is optimized based on dynamic programming algorithms.

[0031] As a preferred embodiment of the present invention, the intelligent decision-making and control layer has an access control function, with different levels of operation and maintenance personnel having different operating permissions, thereby ensuring the security of the system and the confidentiality of the data.

[0032] Compared with the prior art, the beneficial effects of the present invention are: This invention, through real-time monitoring and data analysis, can detect potential faults in the ship's power system in advance, take timely measures to repair them, prevent the faults from escalating, and improve the reliability and safety of the ship's power system. Based on the actual operating status and life prediction results of the equipment, it can formulate personalized operation and maintenance plans to avoid over-maintenance and under-maintenance, thereby reducing operation and maintenance costs. Through real-time evaluation and analysis of the power system, it can identify weak links and optimization opportunities in the system operation, propose improvement measures, and improve the performance and efficiency of the ship's power system. Attached Figure Description

[0033] Figure 1 This is a schematic diagram of the system of the present invention; Figure 2 This is a wiring diagram for Embodiment 6 of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1

[0035] Please see Figure 1 This embodiment provides a technical solution: a data acquisition layer in a ship power intelligent operation and maintenance platform based on digital twins. The data acquisition layer includes sensors installed on various devices of the ship's power system and environmental sensors, used to collect equipment operating parameters and information about the ship's surrounding environment.

[0036] Specifically, the equipment operating parameters in the data acquisition layer include, but are not limited to, current, voltage, temperature, humidity, and vibration. Multi-physical quantity collaborative monitoring enables fault identification with a completeness of 98%. A vibration monitoring system is built based on the ISO-18436 standard, combined with the IEC 60085 temperature rise model.

[0037] Current monitoring accurately collects the current values ​​of various devices in the ship's electrical system, distinguishing the magnitude, direction, and changes of current in different lines and devices. For example, it monitors the generator output current and the current in each branch of the switchboard in real time. By monitoring the current, it is possible to determine whether the equipment is overloaded, short-circuited, or otherwise faulty.

[0038] Voltage monitoring is used to assess the voltage stability of a ship's electrical system, including voltage values ​​at different busbars and the range of voltage fluctuations. This includes monitoring the main grid voltage and emergency grid voltage. Abnormal voltage levels can damage equipment or prevent it from functioning properly.

[0039] Temperature is monitored in real time for critical equipment such as generators, transformers, and motors. Equipment generates heat during prolonged operation; excessively high temperatures can affect equipment performance and lifespan, and may even cause safety accidents such as fires.

[0040] Humidity, particularly in marine environments, significantly impacts the insulation performance of electrical equipment. Excessive humidity can cause insulation materials to become damp, reducing their insulation performance and increasing the risk of leakage. Therefore, it is necessary to monitor the humidity levels of both the environment surrounding the equipment and the internal humidity levels of the equipment itself.

[0041] Vibration is monitored using vibration sensors. Abnormal vibration may indicate mechanical faults in the equipment, such as bearing wear or rotor imbalance. Analyzing vibration signals can help identify potential problems in the equipment in advance.

[0042] Current sensors, voltage sensors, temperature sensors, and vibration sensors are installed on key equipment in the ship's electrical system, such as generators, transformers, and distribution cabinets. These sensors are regularly calibrated and maintained to ensure the accuracy and reliability of data acquisition. Simultaneously, environmental sensors are installed to collect real-time information about the ship's surrounding environment. Example 2

[0043] Please see Figure 1 This embodiment provides a technical solution: a digital twin model layer in a ship power intelligent operation and maintenance platform based on digital twins. The digital twin model layer constructs a three-dimensional digital twin model of the ship power system and updates and corrects the model in real time based on the collected real-time data.

[0044] Specifically, the 3D digital twin model of the digital twin model layer accurately maps the physical structure and electrical connections of the ship's power system, and can reflect the dynamic changes of the system in real time. The deviation between the model and the actual system state is controlled within ±0.5%. A unified multi-domain model is constructed using the Modelica language, with a data refresh cycle of ≤100ms.

[0045] Physical structure mapping: The 3D digital twin model must accurately represent the physical characteristics of each device in the ship's electrical system, such as its shape, size, and location. For example, the specific location and layout of equipment such as generators, transformers, and switchgear, as well as the routing and connection methods of cables, must be included to ensure that the model is highly consistent with the actual physical system.

[0046] Electrical connection mapping accurately represents the electrical connections between various devices in a power system, including circuit topology and current flow. By mapping these electrical connections, the operating state of the power system can be simulated, and the current distribution and impact range during faults can be analyzed.

[0047] Real-time dynamic updates are implemented, updating the model's status promptly based on real-time data collected by the data acquisition layer. For example, when equipment operating parameters change, the model can reflect these changes in real time, such as temperature increases or voltage fluctuations, allowing maintenance personnel to understand the system's operating status promptly.

[0048] Specifically, the data acquisition layer and the digital twin model layer interact through a data transmission interface to ensure that the acquired data is transmitted to the digital twin model layer accurately and in a timely manner.

[0049] The data transmission interface adopts a standardized interface to ensure compatibility and interoperability between the data acquisition layer and the digital twin model layer. The interface should have efficient data transmission capabilities, enabling it to quickly and accurately transmit the acquired data to the model layer.

[0050] To ensure data accuracy, data verification and error correction mechanisms are employed during data transmission. For example, algorithms such as Cyclic Redundancy Check (CRC) are used to verify the data and promptly detect and correct errors that occur during transmission.

[0051] Ensuring data timeliness involves optimizing data transmission processes and reducing latency. High-speed communication networks and data caching technologies can be employed to ensure that collected data is transmitted to the digital twin model layer in a timely manner, enabling real-time model updates.

[0052] Data transmission packet loss rate <0.001%. Multi-source data synchronization is achieved using the IEEE 1588 precise time protocol.

[0053] Using computer-aided design (CAD) software and 3D modeling technology, a 3D digital twin model of the ship's electrical system was constructed. The model included detailed annotations of equipment names, models, parameters, locations, and established electrical connections between the equipment. Example 3

[0054] Please see Figure 1 This embodiment provides a technical solution: a data analysis and processing layer in a ship power intelligent operation and maintenance platform based on digital twins. The data analysis and processing layer cleans and preprocesses the collected data, and uses machine learning and deep learning algorithms to analyze and mine the data to achieve fault diagnosis, equipment life prediction, and performance evaluation.

[0055] Specifically, the data analysis and processing layer employs anomaly detection algorithms to identify abnormal operating data of power equipment to determine potential faults, and predicts the remaining service life of the equipment based on historical operating data and current status. This achieves 72-hour advance warning of major faults, with a RUL prediction error of ≤5%. An isolated forest algorithm is applied to detect anomalies, and a BiLSTM network is used to construct the lifetime prediction model.

[0056] Anomaly detection algorithms employ various methods, such as statistical analysis and machine learning algorithms (e.g., clustering and isolated forest algorithms), to identify outliers in the operating data of power equipment. For example, when parameters such as current and voltage exceed normal ranges, the algorithm can detect this promptly and issue an alarm, indicating a potential fault.

[0057] Potential fault identification involves analyzing detected anomalies by combining historical equipment fault data with expert knowledge to determine the type and severity of potential faults. For example, if an abnormally high generator temperature is detected, it may be identified as a cooling system fault or a winding short circuit.

[0058] Equipment lifespan prediction involves collecting historical operating data from the equipment, including operating time, load conditions, and maintenance records. This data, combined with the current operating status, is used to build a lifespan prediction model using machine learning or deep learning algorithms. This model can predict the remaining service life of the equipment, providing a basis for maintenance and replacement.

[0059] Specifically, the data analysis and processing layer can also analyze the energy consumption of the ship's electrical system and provide energy-saving optimization suggestions to reduce ship operating costs. Overall energy efficiency is improved by 8-12%, and generator load allocation is optimized based on dynamic programming algorithms.

[0060] Energy consumption analysis involves collecting and analyzing energy consumption data from the ship's electrical system, including the energy consumption of different equipment and changes in energy consumption over different time periods. By analyzing the energy consumption data, the system identifies equipment and processes with high energy consumption and the patterns of energy consumption changes.

[0061] Energy-saving optimization recommendations. Based on the energy consumption analysis results, corresponding energy-saving optimization recommendations are provided. These include adjusting equipment operating parameters, adopting energy-efficient equipment, and optimizing the power system's operating strategy. Implementing these recommendations can reduce the ship's energy consumption and lower operating costs.

[0062] Cost-benefit assessment involves evaluating the costs required to implement energy-saving optimization recommendations and the expected energy-saving effects. This ensures that energy-saving measures are cost-effective and can recover investment costs within a reasonable timeframe.

[0063] The collected real-time data is transmitted to a data analysis server, where programming languages ​​such as Python and R, along with relevant data processing libraries, are used to clean, preprocess, and analyze the data. Machine learning algorithms, such as support vector machines and neural networks, are employed for fault diagnosis and equipment lifespan prediction. Example 4

[0064] Please see Figure 1 This embodiment provides a technical solution: an intelligent decision-making and control layer in a ship power intelligent operation and maintenance platform based on digital twins. The intelligent decision-making and control layer automatically generates operation and maintenance decisions and suggestions based on data analysis results, issues alarms and provides emergency strategies when there is a fault or anomaly, and can remotely control equipment.

[0065] Specifically, the intelligent decision-making and control layer generates operation and maintenance decisions and suggestions, including maintenance plans, repair schemes, and emergency response measures, providing corresponding solutions based on different fault levels and equipment statuses. This reduces unplanned downtime by 60%. It utilizes FMEA-based fault tree analysis combined with dynamic Bayesian network decision-making.

[0066] A maintenance plan is developed based on the equipment's operating status and lifespan predictions. This includes regular inspections and maintenance, as well as replacing worn parts, to ensure the equipment operates normally and extends its lifespan.

[0067] The maintenance plan generates a detailed maintenance plan when a fault or potential fault is detected in the equipment. This includes the maintenance steps, required tools and materials, and personnel arrangements, ensuring that maintenance work can be carried out efficiently and safely.

[0068] Emergency response measures should be developed for different types of faults and emergencies. For example, in the event of a short circuit, the power supply should be cut off immediately, and measures should be taken to prevent fires and other secondary disasters.

[0069] Tiered solutions offer different levels of solutions based on the severity of the fault and the condition of the equipment. For minor faults, simple adjustments or repairs can be taken; for serious faults, downtime for inspection or equipment replacement may be necessary.

[0070] Specifically, the intelligent decision-making and control layer has access control functions, with different levels of operation and maintenance personnel having different operating permissions, ensuring system security and data confidentiality.

[0071] Based on the data analysis results, the system automatically generates operation and maintenance decisions and suggestions, and notifies operation and maintenance personnel via SMS, email, and other means. Operation and maintenance personnel can then remotely control relevant equipment through the system to operate it according to the actual situation. Example 5

[0072] Please see Figure 1 This embodiment provides a technical solution: a visualization layer in a digital twin-based intelligent operation and maintenance platform for ship power systems. The visualization layer displays the system's operating status, fault information, and operation and maintenance decisions in the form of graphics, charts, and reports, and provides an interactive interface for personnel to operate and query.

[0073] Specifically, the visualization layer notifies operations and maintenance personnel of operational decisions and suggestions via SMS and email, displays information through visualization tools, and provides an interactive interface for operations and maintenance personnel to operate and query. The interactive interface supports multi-dimensional data query and analysis. Alarm information is delivered within 5 seconds, and real-time rendering of 100,000 data points is supported. Alarms are pushed using the MQTT protocol, and 3D visualization is implemented on the browser side using WebGL.

[0074] SMS and email notifications should be sent promptly to relevant maintenance personnel when the system generates operational decisions and suggestions. The content of SMS and emails should be concise and clear, containing key information such as the type of fault, device location, and suggested solutions.

[0075] Visualization tools, such as dashboards, charts, and maps, are used to present the system's operating status, fault information, and maintenance decisions to maintenance personnel in an intuitive way. For example, dashboards can display equipment operating parameters in real time, and charts can analyze historical data and trends of the equipment.

[0076] The system provides an interactive interface for operations and maintenance personnel to perform operations and queries. Personnel can input keywords and filter criteria to retrieve the information they need. For example, they can query the historical fault records and current operating status of a specific device.

[0077] Multi-dimensional data query and analysis: The interactive interface supports multi-dimensional data query and analysis functions. Maintenance personnel can analyze data from different perspectives, such as filtering and statistically analyzing by time, device type, and fault type, to better understand system operation and make informed decisions.

[0078] Using visualization tools such as Tableau and Power BI, the operational status, fault information, and maintenance decisions of the ship's electrical system are displayed in intuitive graphical, chart, and report formats. An interactive interface is developed to facilitate operation and querying by maintenance personnel. Example 6

[0079] Please see the appendix Figure 2 This embodiment provides a technical solution: a wiring method for a power distribution system used to supply power to a ship's high-grade load. The solution employs two 10kV municipal power sources (Mall 1 and House 2), which are stepped down by two 10kV / 0.4kV transformers (T1 and T2) to serve as the normal power supply for the high-grade load. A separate 10kV diesel generator (DG) is provided as an emergency power source.

[0080] Normal power supply: Mains power 1 is stepped down through T1 and mains power 2 is stepped down through T2, respectively, to supply power to the low-voltage distribution system.

[0081] Emergency Power Supply and Transformer Utilization: The 10kV emergency power supply from the diesel generator (DG) is automatically switched with one of the municipal 10kV power supplies (e.g., mains power 1) on the 10kV side via an automatic transfer switch (ATS1). The switched power supply is stepped down through a third 10kV / 0.4kV transformer (T3). The output of T3 forms a dedicated emergency power bus section for high-voltage loads on the low-voltage side.

[0082] Economic efficiency and moisture-proof design: In non-emergency situations, T3 is powered by normal municipal power (such as mains power 1), avoiding the moisture problem caused by long-term unenergized operation of the emergency transformer. Interconnecting switches (such as ATS2 and ATS3) are installed on the low-voltage side, allowing T1, T2, and T3 to communicate with each other under normal or partial maintenance conditions, improving transformer utilization and the economy and flexibility of system operation (see Appendix 1 for logical relationships).

[0083] Logical Relationship Table 1

[0084] Note: 1 - Circuit breaker closed; 0 - Circuit breaker open.

[0085] QF1 to QF5 should meet the requirement that no more than 3 circuit breakers can be closed simultaneously, and mechanical interlocking should be achieved through "five locks and three keys".

[0086] Emergency Start-up Logic: When both low-voltage side main switches of the two transformers (T1 and T2) that provide normal power supply to the special load detect a loss of voltage (see Appendix 2 for the logic relationship), the 10kV diesel generator (DG) will start automatically. After the DG starts, it will switch through ATS1 (disconnecting the mains power 1 and connecting the DG), and then step down through T3 to form an emergency power supply for the special load.

[0087] Logical Relationship Table 2

[0088] Note: 1 - Circuit breaker is normal; 0 - Circuit breaker is undervoltage.

[0089] Power supply reliability assurance: This wiring scheme has high reliability. When any one of the transformers (T1, T2 or T3) fails or is under maintenance, the super-grade load can still maintain two independent power supplies from the other two transformers on the low-voltage side (switching is achieved through the low-voltage tie switches ATS2 and ATS3).

[0090] When any two transformers fail or are under maintenance, the super-grade load can still maintain an independent power supply from the remaining transformer on the low-voltage side.

[0091] This design meets the high reliability requirements of power supply for super-high loads (see Appendix 3 for the logic relationship).

[0092] Logical Relationship Table 3

[0093] Note: 1 - Circuit breaker is normal; 0 - Circuit breaker is undervoltage.

[0094] Medium-voltage ATS1 normally operates on the municipal power supply side; low-voltage ATS2 normally operates on the power supply side of transformer #2; low-voltage ATS3 is not limited and automatically switches on and off based on whether the main and backup power supplies are functioning properly.

[0095] Based on the embodiments 1-6, the present invention realizes digital management of the entire lifecycle of the ship's power system (including the core power distribution architecture), improving operation and maintenance efficiency by more than 40%. A closed-loop control logic of "perception, modeling, analysis, decision-making, and interaction" is formed through a five-layer architecture.

[0096] The sensor network of the data acquisition layer (Example 1) will monitor in real time key parameters such as the transformer (T1, T2, T3), ATS switch status, bus voltage and current, and diesel generator status described in Example 6.

[0097] The digital twin model layer (Example 2) will accurately construct a three-dimensional model containing the physical structure, electrical connection relationship and dynamic operating status of the power distribution wiring scheme described in Example 6.

[0098] The data analysis and processing layer (Example 3) will analyze the collected transformer operation data (such as temperature, load rate, harmonics), ATS action records, diesel generator start-stop data, etc., to achieve status assessment, fault early warning (such as predicting transformer insulation aging and ATS contact wear) and energy efficiency analysis (assessing the economics of interconnection operation).

[0099] The intelligent decision-making and control layer (Example 4) can automatically generate maintenance plans (such as transformer rotation and maintenance recommendations) and optimize operation strategies (such as recommending the best communication operation mode to reduce losses) for power distribution equipment based on the analysis results. When an anomaly is detected (such as transformer overload or ATS switching failure) or when the logic of Example 6 determines that an emergency power supply needs to be started, it can automatically trigger an alarm or execute preset control commands (such as remote opening and closing of circuit breakers).

[0100] The visualization layer (Example 5) will intuitively display the real-time operating status diagram, equipment parameters, alarm information, power path, ATS status, and platform-generated operation and maintenance decision suggestions of the wiring scheme in Example 6, providing operation and maintenance personnel with a clear operation view.

[0101] By employing a multi-source sensor network at the data acquisition layer, the problem of single-dimensional monitoring data is solved. Through dynamic 3D model mapping at the digital twin layer, real-time bidirectional interaction between the physical system (including innovative power distribution architecture) and the virtual space is achieved. AI-driven fault diagnosis and lifespan prediction at the data analysis layer overcome the bottleneck of reliance on human experience. Automated operation and maintenance strategy generation at the decision control layer improves response speed to the second level. Multimodal interactive display at the visualization layer lowers the technical threshold for operation and maintenance.

[0102] In summary, compared with existing conventional wiring schemes, the wiring method of this invention fully utilizes the equipment by interconnecting three transformers, thereby improving the economy of the power distribution system and the flexibility of power supply management; by sharing a transformer for emergency power and normal municipal power, the failure rate of transformers caused by long-term power outages and moisture is reduced; and by coordinating the switching of one medium-voltage (10kV) ATS and two low-voltage ATS, the power supply requirements of special loads are met, thereby improving the reliability of the system power supply.

[0103] Based on the embodiments 1-5, the present invention realizes digital management of the entire life cycle of ship power systems, improving operation and maintenance efficiency by more than 40%. A closed-loop control logic of "perception, modeling, analysis, decision-making, and interaction" is formed through a five-layer architecture.

[0104] By employing a multi-source sensor network at the data acquisition layer, the problem of single-dimensional monitoring data is solved. Through dynamic 3D model mapping at the digital twin layer, real-time bidirectional interaction between the physical system and the virtual space is achieved. AI-driven fault diagnosis and lifespan prediction at the data analysis layer overcome the bottleneck of reliance on human experience. Automated operation and maintenance strategy generation at the decision control layer improves response speed to the second level. Multimodal interactive visualization at the visualization layer lowers the technical threshold for operation and maintenance. Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A ship power intelligent operation and maintenance platform based on digital twins, characterized in that: It includes a data acquisition layer, a digital twin model layer, a data analysis and processing layer, an intelligent decision-making and control layer, and a visualization layer; The data acquisition layer includes sensors installed on various devices of the ship's electrical system and environmental sensors, used to collect equipment operating parameters and information about the ship's surrounding environment. The digital twin model layer constructs a three-dimensional digital twin model of the ship's power system and updates and corrects the model in real time based on the collected real-time data. The data analysis and processing layer cleans and preprocesses the collected data, and uses machine learning and deep learning algorithms to analyze and mine the data to achieve fault diagnosis, equipment life prediction and performance evaluation. The intelligent decision-making and control layer automatically generates operation and maintenance decisions and suggestions based on data analysis results, issues alarms and provides emergency strategies when there is a fault or anomaly, and can remotely control equipment. The visualization layer displays the system's operating status, fault information, and maintenance decisions in the form of graphics, charts, and reports, and provides an interactive interface for personnel to operate and query.

2. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The device operating parameters in the data acquisition layer include, but are not limited to, current, voltage, temperature, humidity, and vibration. Current is used to accurately collect the current values ​​of various devices in the ship's power system, distinguishing the magnitude, direction, and changes of current in different lines and devices; voltage is used to monitor the voltage stability of the ship's power system, including the voltage values ​​of different busbars and the range of voltage fluctuations; temperature is used to monitor the temperature of key equipment in real time, including generators, transformers, and motors; humidity is used because the humidity of the ship's environment has a significant impact on the insulation performance of power equipment. Excessive humidity may cause insulation materials to become damp, reducing insulation performance and increasing the risk of leakage; vibration is used to monitor the vibration of equipment through vibration sensors. Abnormal vibration may indicate mechanical failure of the equipment, and analyzing vibration signals can help detect potential problems in advance.

3. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The three-dimensional digital twin model of the digital twin model layer accurately maps the physical structure and electrical connection relationship of the ship's power system, and can reflect the dynamic changes of the system in real time; The physical structure is a three-dimensional digital twin model that accurately represents the physical characteristics of the shape, size, and location of each piece of equipment in the ship's electrical system; Electrical connections accurately represent the electrical connections between various devices in a power system, including the circuit topology and current flow; the model's state is updated in a timely manner based on real-time data collected by the data acquisition layer.

4. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The data analysis and processing layer uses an anomaly detection algorithm to identify abnormal operating data of power equipment in order to determine potential faults, and predicts the remaining service life of the equipment based on historical operating data and current status. Anomaly detection algorithms are used to identify outliers in the operating data of power equipment. Identifying potential faults involves analyzing detected abnormal data by combining historical fault data of the equipment with expert knowledge to determine the type and severity of potential faults. Predicting the remaining lifespan of equipment involves collecting historical operating data, including operating time, load conditions, and maintenance records, and combining this data with the current operating status. Then, machine learning or deep learning algorithms are used to build a lifespan prediction model. This model can predict the remaining lifespan of the equipment, providing a basis for equipment maintenance and replacement.

5. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The intelligent decision-making and control layer generates operation and maintenance decisions and suggestions including maintenance plans, repair schemes, and emergency response measures, and provides corresponding solutions based on different fault levels and equipment status. The maintenance plan is a reasonable maintenance plan developed based on the equipment's operating status and life prediction results; The maintenance plan generates a detailed maintenance plan when a fault or potential fault is detected in the equipment; the emergency response measures develop corresponding emergency response measures for different types of faults and emergencies; and the tiered solutions provide different levels of solutions based on the level of the fault and the condition of the equipment.

6. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The visualization layer notifies maintenance personnel of maintenance decisions and suggestions via SMS and email, displays information through visualization tools, and develops an interactive interface for maintenance personnel to operate and query. The interactive interface supports multi-dimensional data query and analysis. When the system generates operation and maintenance decisions and suggestions, it will promptly notify the relevant operation and maintenance personnel via SMS and email. Visualization tools, including dashboards, charts, and maps, are used to intuitively display the system's operating status, fault information, and maintenance decisions to maintenance personnel. An interactive interface is developed for maintenance personnel to operate and query. Maintenance personnel can enter keywords and filter conditions through the interface to query the information they need. The interactive interface supports multi-dimensional data query and analysis functions.

7. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The data acquisition layer and the digital twin model layer interact through a data transmission interface to ensure that the acquired data is transmitted to the digital twin model layer accurately and in a timely manner. The data transmission interface adopts a standardized data transmission interface to ensure compatibility and interoperability between the data acquisition layer and the digital twin model layer. During the data transmission process, data verification and error correction mechanisms are used to ensure data accuracy. The data transmission process is optimized to reduce data transmission latency. High-speed communication networks and data caching technology are used to enable the acquired data to be transmitted to the digital twin model layer in a timely manner so that the model can be updated in real time.

8. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The data analysis and processing layer can also analyze the energy consumption of the ship's electrical system and provide energy-saving optimization suggestions to reduce ship operating costs. Energy consumption analysis involves collecting and analyzing energy consumption data from the ship's electrical system, including the energy consumption of different equipment and changes in energy consumption over different time periods. By analyzing the energy consumption data, the equipment and processes with high energy consumption are identified, as well as the patterns of energy consumption changes. Energy-saving optimization suggestions are provided based on the results of the energy consumption analysis. When proposing energy-saving optimization suggestions, the costs required to implement the suggestions and the expected energy-saving effects are evaluated.

9. The ship power intelligent operation and maintenance platform based on digital twin as described in claim 1, characterized in that: The intelligent decision-making and control layer has access control functionality, allowing different levels of operations and maintenance personnel to have different operating permissions, thus ensuring system security and data confidentiality.

Images