Full-period management system and method considering ship equipment design-operation and maintenance-optimization

Abstract

The invention discloses a full-cycle management system and method considering ship equipment design-operation and maintenance-optimization. A digital gene identity system is given to equipment through unique two-dimensional code identification, full life cycle data is bound, a cloud-edge-end collaborative architecture is constructed, and design-operation and maintenance-optimization full-cycle multi-source data fusion and intelligent analysis are achieved. The system comprises an equipment digital identity management module, a cloud-side-end collaborative data acquisition module, a full-cycle data processing and data lake module, an intelligent analysis and decision generation module, a multi-role self-adaptive interaction module and a design feedback and optimization module, and a'production-use-maintenance-optimization 'full-life-cycle closed loop is formed. The problems that data entry is difficult, operation and maintenance depend on experience, design feedback lags and the like are solved, and the intelligent level and the industrial collaboration value of ship equipment operation and maintenance are improved.

Description

Technical Field

[0001] This invention relates to the field of ship equipment management technology, specifically to a full-cycle management system and method that considers ship equipment design, operation and maintenance, and optimization. It is applicable to the intelligent management of the entire life cycle of key equipment such as ship main engines and auxiliary engines, and realizes closed-loop collaboration of design, manufacturing, operation, maintenance and optimization. Background Technology

[0002] In the operation of critical equipment such as main engines and auxiliary machinery, production data (e.g., manufacturing processes, experimental parameters), operational data (e.g., speed, temperature), and maintenance records are often scattered across different systems, forming "information silos" that cannot be linked for analysis. This leads to low efficiency in operation, management, and maintenance, and a high rate of unplanned downtime. Maintenance decisions rely heavily on personnel experience and lack data-driven approaches. When a failure occurs, on-site personnel struggle to quickly obtain comprehensive equipment information and repair guidance, resulting in prolonged troubleshooting times and significant losses from unplanned downtime. Furthermore, designers often lack access to long-term operational performance and fault data under real-world conditions, leading to delayed or distorted information feedback, which hinders design optimization and slows product iteration.

[0003] Currently, most ship equipment management systems remain at the data collection and visualization stage. While some systems have achieved digitalized operation and maintenance or remote monitoring, they lack on-site personnel empowerment, multi-source collaboration, and data closure. Existing technologies suffer from insufficient integration of data analysis models with operation and maintenance workflows, failing to achieve a closed-loop system covering the entire lifecycle of "production-use-research-optimization." Equipment-driven precision operation and maintenance, as well as dynamic optimization mechanisms involving multi-terminal collaboration, are yet to be developed, resulting in low overall operation and maintenance efficiency and intelligence levels.

[0004] Among existing related patent technologies, such as the intelligent manufacturing high-efficiency collaborative cloud service platform for the shipbuilding industry disclosed in patent CN112288256A, although it realizes collaboration among shipyards, designers and other parties, it does not assign a unique digital identity to each device, resulting in insufficient accuracy of data association, and lacks a closed-loop feedback channel for operation and maintenance data to the design end, so design optimization lacks support from real working condition data; the intelligent integrated design method, system and cloud service platform for marine supporting equipment disclosed in patent CN114021260A focuses on data-driven design in the design stage, but does not build a cloud-edge-device collaborative data acquisition architecture, resulting in low efficiency of real-time data processing, and does not provide customized empowerment tools for operation and maintenance personnel, so troubleshooting relies on personnel experience and the response speed is slow.

[0005] Therefore, there is an urgent need for a ship equipment management system and method that can break down data barriers, achieve full-cycle data connectivity and intelligent analysis. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a full-cycle management system and method that considers the design, operation and maintenance and optimization of ship equipment. By assigning a unique digital identity card to the equipment, a cloud-edge-device collaborative architecture is constructed to realize the integration and intelligent analysis of full-cycle data, and finally form a closed loop of "production-use-maintenance-optimization" to support the digital transformation of ship equipment operation and maintenance.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: A full-cycle management system for ship equipment design, operation, and optimization includes an equipment digital identity management module, a cloud-edge-device collaborative data acquisition module, a full-cycle data processing and data lake module, an intelligent analysis and decision generation module, a multi-role adaptive interaction module, and a design feedback and optimization module. The equipment digital identity management module generates a unique identifier for each piece of ship equipment, serving as a digital identity card, which is bound to the equipment's factory data and enables rapid equipment identification and system access via scanning. The cloud-edge-device collaborative data acquisition module includes a cloud platform, edge computing nodes, and ship-end equipment, enabling layered collection, transmission, and preprocessing of equipment data. The full-cycle data processing and data lake module integrates and stores the equipment's design data. Manufacturing data, operational data, maintenance data, and environmental data are processed and integrated through anomaly data processing before being fed into the data lake. The intelligent analysis and decision generation module combines equipment theoretical models, historical data, and maintenance manuals to perform data mining and machine learning, enabling equipment health status assessment, fault prediction and identification, and automatically generating maintenance tasks or alarms. The multi-role adaptive interaction module dynamically pushes operation interfaces, data views, and fault handling guidance schemes that match the user's permissions and responsibilities based on the user's identity information. The design feedback and optimization module aggregates the full lifecycle data of a group of similar equipment, performs performance statistics and reliability analysis, generates design optimization suggestion reports, and feeds them back to the design end to guide the personalized and adaptive design of new products.

[0008] Furthermore, the unique identifier of the equipment digital identity management module is a QR code. The genetic ID card contains design parameters, manufacturing process, and full-cycle operation and maintenance data. After being treated for corrosion and wear resistance, the QR code is affixed to a conspicuous position on the equipment, making it easy for crew members and maintenance personnel to quickly identify the equipment on-site.

[0009] Furthermore, the cloud-edge-device collaborative data acquisition module adopts a distributed cloud computing architecture on its cloud platform. It receives pre-processed data uploaded by edge computing nodes via 5G or satellite communication, as well as some raw data that needs to be stored for a long time, to achieve centralized storage and in-depth analysis of device data.

[0010] Furthermore, the shipboard equipment of the cloud-edge-device collaborative data acquisition module includes built-in sensors, an added monitoring terminal, and handheld scanning and login system equipment for maintenance personnel, which is responsible for collecting real-time operating status data of the equipment and maintenance records of the maintenance personnel.

[0011] Furthermore, the edge computing nodes of the cloud-edge-device collaborative data acquisition module are deployed on the ship side and connected to ship-end equipment via CAN bus or industrial Ethernet to process the acquired data in real time, reducing data transmission volume and enabling rapid local response.

[0012] Furthermore, the full-cycle data processing and data lake module adopts a "data lake" architecture, which incorporates all types of data, including device digital identity data, cloud-edge-device collected operational data, intelligent analysis results, and maintenance records, into a unified storage system. Through data modeling technology, it establishes the correlation between device data and supports cross-cycle and multi-device data retrieval and analysis.

[0013] Furthermore, the intelligent analysis and decision generation module includes an equipment status assessment unit, a fault prediction and diagnosis unit, and an intelligent operation and maintenance management unit. The equipment status assessment unit uses machine learning algorithms to analyze equipment operating data and outputs a status report showing equipment health scores and performance degradation trends. The fault prediction and diagnosis unit combines fault tree analysis and vibration spectrum analysis to locate fault causes and provide early warnings of potential equipment faults. The intelligent operation and maintenance management unit automatically generates personalized operation and maintenance plans based on equipment status assessment results, fault warning information, and factors such as ship navigation plans and operation and maintenance manuals.

[0014] Furthermore, the multi-role adaptive interaction module provides customized interactive interfaces and functional permissions for three roles: crew, maintenance personnel, and engineers. These include a crew interaction terminal, a maintenance personnel interaction terminal, and an engineer interaction terminal. The crew interaction terminal, presented as a ship's central control terminal or mobile app, focuses on displaying real-time equipment status, simplified maintenance guidelines, and fault alarm prompts, allowing crew members to quickly view equipment health status and perform basic maintenance operations. The maintenance personnel interaction terminal, deployed on the shipping company's maintenance department management platform, supports centralized monitoring of equipment on multiple ships, maintenance plan approval, and spare parts management, achieving global control of fleet-level equipment maintenance. The engineer interaction terminal is an analysis platform for equipment design and manufacturing engineers, providing in-depth data mining tools for the entire equipment lifecycle, supporting engineers in extracting design optimization requirements from maintenance data.

[0015] Furthermore, the design feedback and optimization module realizes a closed loop of feedback from operation and maintenance data to the design end, and outputs design optimization suggestions based on "data of similar equipment groups": collect full-cycle operation and maintenance data of multiple similar equipment, extract the improvement direction of equipment design through statistical analysis and data mining technology, and feed back the design optimization suggestions to the equipment design team to promote iterative design of equipment and realize a closed-loop iteration of "design-operation and maintenance-optimization".

[0016] A full-cycle management method considering ship equipment design, operation, and optimization, based on the full-cycle management system considering ship equipment design, operation, and optimization as described in any one of claims 1-9, includes the following steps: S1: Equipment factory coding stage, generating and binding a unique QR code for each piece of ship equipment leaving the factory, and storing equipment design parameters and factory data in a data lake; S2: Data acquisition and synchronization stage, after equipment deployment, real-time acquisition of operational and environmental data through edge computing nodes, preprocessing and uploading to the cloud data lake, and performing abnormal data processing and correlation fusion on the data; S3: Intelligent analysis and task generation stage, the cloud platform combines the operation and maintenance manual with... Machine learning analyzes multi-source data to identify equipment anomalies or performance degradation trends, automatically generating predictive maintenance tasks or fault alarm work orders; S4: Task execution and guidance phase, maintenance personnel log in to the system by scanning a code on their terminal device, and the system pushes a customized interface based on the user's identity; maintenance personnel receive task reminders and complete maintenance or troubleshooting work according to the visual operation guidance provided by the system; S5: Data closure and feedback optimization phase, maintenance results data are recorded and synchronized back to the data lake, completing a single maintenance closure; at the same time, the system continuously aggregates and analyzes data from similar equipment groups, generates design optimization suggestions and feeds them back to the design department, completing a full-cycle optimization closure.

[0017] Compared with the prior art, the present invention has the following significant advantages: 1. Achieved seamless data connectivity throughout the entire lifecycle: Through unique digital identity cards and cloud-edge-device collaborative technology, information barriers between design, manufacturing, operation, and maintenance have been broken down, forming a complete data chain.

[0018] 2. Improved the level of intelligent operation and maintenance: Through data mining and machine learning algorithms, the transformation from "passive maintenance" to "proactive prediction" has been realized, which has greatly improved operation and maintenance efficiency and equipment reliability.

[0019] 3. A collaborative work ecosystem has been built: Through multi-role adaptive interaction, precise information services are provided to different users, improving the efficiency of cross-departmental and cross-role collaboration.

[0020] 4. A closed-loop optimization paradigm has been formed: terminal operation and maintenance data is fed back to the source design, forming a continuous improvement closed loop of "data-driven design" to accelerate product iteration and innovation. Attached Figure Description

[0021] Figure 1 is a schematic diagram of the overall architecture of the system of the present invention; Figure 2 is a flowchart of the operation and maintenance scenario of the auxiliary equipment of the system of the present invention. Detailed Implementation

[0022] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] Example 1: System Architecture Implementation like Figure 1 As shown, the ship equipment design-operation-optimization full-cycle management system architecture of the present invention achieves closed-loop management of the entire life cycle of ship equipment from design and operation to iterative optimization through the collaborative work of the equipment digital identity management module, cloud-edge-device collaborative data acquisition module, full-cycle data processing and data lake module, intelligent analysis and decision generation module, multi-role adaptive interaction module, and design feedback and optimization module.

[0024] Equipment Digital Identity Management Module: This module is used to establish a unique and comprehensive digital identity profile for each piece of ship equipment, and includes the following components: QR code identification: A unique QR code is used to bind basic equipment information (model, serial number, manufacturing process, design features, etc.). The code is affixed to a conspicuous position on the equipment before it leaves the factory, so that crew members and maintenance personnel can quickly identify the equipment on site.

[0025] Genetic ID Card: Construct a "digital genetic identity" for equipment, which includes full-lifecycle data such as design parameters (e.g., structural dimensions, material properties, rated operating conditions), manufacturing processes (e.g., processing accuracy, assembly process), and operation and maintenance history (e.g., maintenance records, fault history), stored in the system database as the "digital cornerstone" for full-lifecycle management of equipment.

[0026] Device-side system entry: By scanning the QR code, a system entry point is provided for local data collection, identity verification, and data upload functions, supporting interaction between the device and the management system.

[0027] Implementation steps: Before the equipment leaves the factory, the manufacturing system generates a unique QR code and genetic ID card for it; the physical carrier of the QR code is affixed to the equipment after being treated for corrosion and wear resistance; the equipment design and manufacturing data are entered into the database to form the genetic ID card, and bound to the hardware identifier at the equipment system entry point to complete the initialization of the equipment's digital identity.

[0028] Cloud-Edge-Device Collaborative Data Acquisition Module: This module enables layered acquisition, transmission, and preliminary processing of device data, and consists of the following parts: Ship end equipment: including built-in sensors (such as temperature sensors, vibration sensors, and pressure sensors) and additional monitoring terminals, responsible for collecting real-time operating status data of the equipment (such as speed, energy consumption, vibration amplitude, etc.).

[0029] Edge computing nodes: Industrial-grade edge servers deployed on the ship connect to shipboard equipment via CAN bus, industrial Ethernet, etc., to process the collected data in real time (such as outlier filtering, data normalization, and performance analysis), reducing data transmission volume and enabling rapid local response.

[0030] Cloud platform: Adopting a distributed cloud computing architecture (such as a big data platform based on Hadoop and Spark), it receives pre-processed data uploaded by edge computing nodes via 5G or satellite communication, as well as some raw data that needs to be stored for a long time, to achieve centralized storage and in-depth analysis of device data.

[0031] Implementation steps: Deploy edge computing nodes on the ship and complete the hardware connection and communication protocol configuration with the ship-side equipment; build the data receiving interface and storage architecture on the cloud platform; verify the stability and data consistency of the data transmission link "ship-side equipment → edge computing node → cloud platform" through test cases.

[0032] Full-cycle data processing and data lake module: This module constructs a unified storage and management hub for equipment full-cycle data, realizing the integration of data from multiple stages such as design, manufacturing, and operation and maintenance. The “data lake” architecture is adopted to incorporate all types of data (structured, semi-structured, and unstructured) such as device digital identity data, cloud-edge-device collected operational data, intelligent analysis results, and operation and maintenance records into a unified storage system.

[0033] By using data modeling technology, relationships between device data can be established (such as the relationship between "device identity - operation data - fault record - operation and maintenance plan"), supporting data retrieval and analysis across cycles and multiple devices.

[0034] Implementation steps: Build a data lake platform based on big data technology stack and define data classification rules (such as by device type, data format, etc.); complete the development and connection of data interfaces for each module to realize automatic data inflow and classified storage; verify the retrieval efficiency and data integrity of the data lake through data visualization tools.

[0035] Intelligent Analysis and Decision Generation Module: This module, based on data lake data, enables equipment status assessment, fault prediction, and intelligent operation and maintenance decision-making, and includes the following units: Equipment Status Assessment Unit: Employs machine learning algorithms (such as random forest and LSTM neural network) to analyze equipment operation data and output status reports such as equipment health scores and performance degradation trends.

[0036] Fault prediction and diagnosis unit: Combining fault tree analysis (FTA), vibration spectrum analysis and other technologies, it provides early warning of potential equipment faults and locates the causes of faults (such as bearing wear, circuit aging, etc.).

[0037] Intelligent Operation and Maintenance Management Unit: Based on equipment status assessment results, fault warning information, and factors such as ship navigation plans and operation and maintenance manuals, it automatically generates personalized operation and maintenance plans (such as maintenance time and maintenance procedures).

[0038] Implementation steps: Deploy the intelligent analysis algorithm model on the cloud platform and complete the model training and verification (based on historical equipment data or simulation data); develop the interface between the algorithm and the data lake and operation and maintenance decision output interface, and verify the accuracy of the "status assessment → fault diagnosis → operation and maintenance decision" process through simulated scenario testing.

[0039] Multi-role adaptive interaction module: This module provides customized interaction interfaces and functional permissions for three roles: crew members, maintenance personnel, and engineers. Crew interaction terminal: Presented in the form of ship's central control terminal or mobile APP, it focuses on displaying real-time equipment status, simple operation and maintenance guidance, fault alarm prompts, etc., and supports crew members to quickly view the health status of equipment and perform basic operation and maintenance operations.

[0040] Maintenance Interaction Terminal: A management platform deployed in the maintenance department of a shipping company, supporting centralized monitoring of equipment on multiple vessels, approval of maintenance plans, and overall management of spare parts, enabling global control of fleet-level equipment maintenance.

[0041] Engineer Interaction Platform: An analysis platform for equipment design / manufacturing engineers, providing in-depth data mining tools for the entire equipment lifecycle (such as data visualization, statistical analysis, and simulation verification interfaces), supporting engineers in extracting design optimization requirements from operation and maintenance data.

[0042] Implementation steps: Develop multi-role interactive interfaces for both web and mobile platforms, and configure functional modules according to role permissions; implement precise control of role permissions through an identity authentication system; select typical users to test the interaction process and optimize the usability of the interface.

[0043] Design Feedback and Optimization Module: This module implements a closed loop of feedback from operation and maintenance data to the design end, and outputs design optimization suggestions based on "data of similar equipment groups". Collect full-cycle operation and maintenance data (such as high-frequency failure points, performance bottlenecks, and operation and maintenance cost distribution) from multiple identical devices, and extract improvement directions for equipment design (such as structural reinforcement, material replacement, and control logic optimization) through statistical analysis and data mining techniques.

[0044] Design optimization suggestions are fed back to the equipment design team to drive iterative equipment design; the new design scheme is then integrated into the full life cycle management through the equipment digital identity management module to achieve a closed-loop iteration of "design-operation-optimization".

[0045] Implementation steps: Establish a data interface between the design and operation and maintenance system, define the format and cycle of data feedback; select a typical type of ship equipment, analyze the operation and maintenance data of its similar equipment group, output a design optimization report and verify its feasibility.

[0046] Example 2: Implementation of the Workflow in the Operation and Maintenance Scenario of System Auxiliary Equipment like Figure 2 As shown, the workflow of the system-assisted equipment operation and maintenance scenario of the present invention realizes intelligent assistance for the entire process of equipment from "routine preventive operation and maintenance" to "fault discovery-diagnosis-elimination" through the coordinated operation of real-time status monitoring, fault judgment, daily operation and maintenance branch, and fault handling branch.

[0047] Real-time status monitoring: The system continuously and frequently collects data on the physical operating status of the equipment through various sensor units deployed on the equipment (such as vibration sensors, temperature sensors, pressure sensors, and speed sensors). The collected parameters cover core indicators such as equipment vibration amplitude, surface temperature, medium pressure, operating speed, and load rate. Data is transmitted in real-time to the system's edge computing nodes, with a transmission frequency configurable from 1Hz to 10Hz to ensure real-time status monitoring.

[0048] Fault diagnosis phase: The system's edge computing nodes perform a two-dimensional fault diagnosis logic on the real-time collected device data: (1) Threshold comparison judgment: Compare the real-time data with the "normal operating threshold range" defined in the equipment design stage (e.g., the normal temperature range of a certain type of main bearing is 40℃~60℃). If the data exceeds the range, it is initially judged to be abnormal.

[0049] (2) Trend prediction judgment: The data is fitted with a trend by the embedded trained equipment performance analysis algorithm (such as LSTM neural network). If the predicted trend shows that the data will exceed the normal range in the short term, it is judged as a potential fault.

[0050] If any of the above judgments is "yes", the process will proceed to the "fault handling branch"; if all are "no", the process will proceed to the "routine maintenance branch".

[0051] Routine Maintenance Branch (when fault diagnosis is "No"): The system automatically retrieves equipment operating data (such as cumulative runtime, recent load changes), environmental data (such as temperature and humidity, salt spray concentration, and sea state level of the sea area where the ship is located), and associates it with the built-in maintenance knowledge base. This knowledge base contains equipment maintenance cycle rules (such as calibrating pressure gauges every 500 hours of operation), standard operating procedures (such as the steps for replacing fuel filters), spare parts life prediction models, and other knowledge items. Based on the above data and knowledge base, the system's "task generation module" uses rule engine technology to automatically generate a list of periodic or preventative maintenance tasks (i.e., a To-Do List). For example, tasks such as "check oil / water level," "calibrate pressure gauge," and "replace fuel filter" are included. Each task comes with an "operation guide" sub-module (including step descriptions, safety precautions, tool usage guidelines, etc.).

[0052] Crew members or maintenance personnel can view the To-Do List through the system's maintenance interface (such as a mobile app), perform maintenance tasks one by one according to the "Operation Guide," and mark the "Completion Status" (e.g., "Completed, oil level normal") after completing the task. This process ends after all tasks are marked.

[0053] Fault Handling Branch (When the fault judgment is "Yes"): The system activates the "Fault Diagnosis Module," combining the equipment's "digital genetic profile" (including design parameters, historical fault records, maintenance history, etc.) with real-time anomaly data. Fault Tree Analysis (FTA) or Case Reasoning (CBR) techniques are used to locate the root cause of the fault (e.g., "abnormal vibration → bearing wear," "abnormal pressure → fuel injector blockage," etc.). Simultaneously, a multi-channel alarm mechanism is triggered: local audible and visual alarms on the equipment, pop-up reminders via the maintenance app, and email / SMS notifications from the management terminal, ensuring timely response from relevant personnel (crew, maintenance). In conjunction with troubleshooting assistance, the system pushes a "Troubleshooting Assistance Information Package" to maintenance personnel, containing: Visual analysis of fault causes (such as the correlation between vibration spectrum and bearing wear characteristics); Standardized troubleshooting procedures (such as a step-by-step operation guide for "disassembling the bearing → inspecting the degree of wear → replacing the spare parts"). (3) List of required tools and spare parts and storage / acquisition paths (e.g., associated with the ship spare parts warehouse management system).

[0054] Maintenance personnel perform troubleshooting operations based on auxiliary information.

[0055] After troubleshooting is completed, the system performs a secondary monitoring of the equipment status. If the fault is resolved (abnormal data returns to normal thresholds and the trend is stable), the system automatically clears the alarm, and this process ends. If the fault is not resolved, the system pushes fault details (including unresolved abnormal data, diagnostic records, and troubleshooting operation logs) to the management terminal, which then dispatches professional engineers for remote technical support or on-site handling. After the engineer completes the handling, they manually (or through automatic system detection) trigger the "alarm clear" button, and this process ends.

[0056] Through the above-described embodiments, this invention enables full-cycle management of ship equipment from design to optimization, thereby improving the level of intelligent operation and maintenance and industrial efficiency.

Claims

1. A full-lifecycle management system considering ship equipment design, operation, and optimization, characterized in that, The system comprises four modules: Equipment Digital Identity Management, Cloud-Edge-Device Collaborative Data Acquisition, Full-Lifecycle Data Processing and Data Lake, Intelligent Analysis and Decision Generation, Multi-Role Adaptive Interaction, and Design Feedback and Optimization. The Equipment Digital Identity Management module generates a unique identifier for each piece of ship equipment, serving as a digital identity card linked to the equipment's factory data. Scanning this identifier enables rapid equipment identification and system access. The Cloud-Edge-Device Collaborative Data Acquisition module includes a cloud platform, edge computing nodes, and shipboard equipment, enabling layered data acquisition, transmission, and preprocessing. The Full-Lifecycle Data Processing and Data Lake module integrates and stores equipment design, manufacturing, operational, maintenance, and environmental data, processing and fusing abnormal data before transmitting it to the data lake. The Intelligent Analysis and Decision Generation module combines theoretical equipment models, historical data, and maintenance manuals to perform data mining and machine learning, achieving equipment health status assessment, fault prediction and identification, and automatically generating maintenance tasks or alarms. The Multi-Role Adaptive Interaction module dynamically pushes operation interfaces, data views, and fault handling guidance schemes matching the user's permissions and responsibilities based on the user's identity information. The design feedback and optimization module is used to aggregate the full lifecycle data of the same type of equipment group, perform performance statistics and reliability analysis, generate design optimization suggestion reports, and feed them back to the design end to guide the personalized and adaptive design of new products.

2. The full-cycle management system for ship equipment design, operation, and optimization as described in claim 1, characterized in that, The unique identifier of the equipment digital identity management module is a QR code. The genetic ID card contains full-cycle data on design parameters, manufacturing process, and operation and maintenance history. After being treated for corrosion and wear resistance, the QR code is affixed to a conspicuous position on the equipment to facilitate quick identification of the equipment by crew members and maintenance personnel on site.

3. The full-cycle management system considering ship equipment design-operation and maintenance-optimization as described in claim 1, characterized in that, The cloud-edge-device collaborative data acquisition module adopts a distributed cloud computing architecture on its cloud platform. It receives pre-processed data uploaded by edge computing nodes via 5G or satellite communication, as well as some raw data that needs to be stored for a long time, to achieve centralized storage and in-depth analysis of device data.

4. The full-cycle management system considering ship equipment design-operation and maintenance-optimization as described in claim 1, characterized in that, The shipboard equipment of the cloud-edge-device collaborative data acquisition module includes built-in sensors, an added monitoring terminal, and handheld scanning and login devices for maintenance personnel, which are responsible for collecting real-time operating status data of the equipment and maintenance records of the maintenance personnel.

5. The full-cycle management system for ship equipment design, operation, and optimization as described in claim 1, characterized in that, The edge computing nodes of the cloud-edge-device collaborative data acquisition module are deployed on the ship side and connected to ship-end equipment via CAN bus or industrial Ethernet to process the acquired data in real time, reducing data transmission volume and enabling rapid local response.

6. The full-cycle management system for ship equipment design, operation, and optimization as described in claim 1, characterized in that, The full-cycle data processing and data lake module adopts a "data lake" architecture, which incorporates all types of data, including device digital identity data, cloud-edge-device collected operational data, intelligent analysis results, and maintenance records, into a unified storage system. Through data processing modeling technology, it establishes the correlation between device data and supports cross-cycle and multi-device data retrieval and analysis.

7. The full-cycle management system considering ship equipment design-operation and maintenance-optimization as described in claim 1, characterized in that, The intelligent analysis and decision generation module includes an equipment status assessment unit, a fault prediction and diagnosis unit, and an intelligent operation and maintenance management unit. The equipment status assessment unit uses machine learning algorithms to analyze equipment operation data and outputs a status report on equipment health score and performance degradation trend. The fault prediction and diagnosis unit combines fault tree analysis and vibration spectrum analysis to locate the cause of faults and provide early warning of potential equipment faults. The intelligent operation and maintenance management unit automatically generates personalized operation and maintenance plans based on equipment status assessment results, fault warning information, and factors such as ship navigation plans and operation and maintenance manuals.

8. The full-cycle management system for ship equipment design, operation, and optimization as described in claim 1, characterized in that, The multi-role adaptive interaction module provides customized interactive interfaces and functional permissions for three roles: crew, maintenance personnel, and engineers. These include crew interaction terminals, maintenance personnel interaction terminals, and engineer interaction terminals. The crew interaction terminal, presented as a ship's central control terminal or mobile app, focuses on displaying real-time equipment status, simplified maintenance guidelines, and fault alarm prompts, allowing crew members to quickly view equipment health status and perform basic maintenance operations. The maintenance personnel interaction terminal, deployed on the shipping company's maintenance department management platform, supports centralized monitoring of equipment on multiple ships, maintenance plan approval, and spare parts management, achieving global control of fleet-level equipment maintenance. The engineer interaction terminal is an analysis platform for equipment design and manufacturing engineers, providing in-depth data mining tools for the entire equipment lifecycle, enabling engineers to extract design optimization requirements from maintenance data.

9. The full-cycle management system for ship equipment design, operation, and optimization as described in claim 1, characterized in that, The design feedback and optimization module realizes a closed loop of feedback from operation and maintenance data to the design end. Based on "data of similar equipment groups", it outputs design optimization suggestions: collects full-cycle operation and maintenance data of multiple similar equipment, extracts the improvement direction of equipment design through statistical analysis and data mining technology, and feeds back the design optimization suggestions to the equipment design team to promote iterative design of equipment and realize the closed-loop iteration of "design-operation and maintenance-optimization".

10. A full-cycle management method considering ship equipment design-operation and maintenance-optimization, based on the full-cycle management system considering ship equipment design-operation and maintenance-optimization as described in any one of claims 1-9, characterized in that, Includes the following steps: S1: Equipment factory coding stage, generate and bind a unique QR code for each piece of ship equipment leaving the factory, and store the equipment design parameters and factory data into the data lake; S2: Data acquisition and synchronization stage. After the equipment is deployed, the edge computing nodes collect operational data and environmental data in real time. After preprocessing, the data is uploaded to the cloud data lake for abnormal data processing and correlation fusion. S3: Intelligent analysis and task generation stage. The cloud platform combines the operation and maintenance manual and machine learning to perform data analysis on multi-source data, identify equipment abnormalities or performance degradation trends, and automatically generate predictive maintenance tasks or fault alarm work orders. S4: Task Execution and Guidance Phase. Maintenance personnel log in to the system by scanning a QR code on their terminal devices. The system pushes a customized interface based on the user's identity. Maintenance personnel receive task reminders and complete maintenance or troubleshooting work according to the visual operation guidance provided by the system. S5: Data Closure and Feedback Optimization Phase. Maintenance result data is recorded and synchronized back to the data lake, completing a single maintenance closure. At the same time, the system continuously aggregates and analyzes data from similar equipment groups, generates design optimization suggestions, and feeds them back to the design department, completing a full-cycle optimization closure.

Images