Intelligent state monitoring and fault early warning system for ship and ocean engineering equipment power system

Abstract

The invention relates to the technical field of ship and ocean engineering equipment, and discloses a ship and ocean engineering equipment power system intelligent state monitoring and fault early warning system which comprises a data acquisition module, a real-time monitoring module, an intelligent analysis module, a fault early warning module, a remote monitoring module and a feedback control module. The data acquisition module is used for acquiring key parameters of a power system in real time, including engine speed, oil temperature, water temperature, oil pressure, water pressure and vibration signals, and providing basic data support for the system; and the real-time monitoring module realizes visual display of data, intuitively reflects a system state in a chart form, and supports historical data query and analysis. The purpose of the intelligent state monitoring and fault early warning system for the ship and ocean engineering equipment power system is to realize real-time monitoring and fault early warning for the ship and ocean engineering equipment power system through advanced sensor technology and data processing and analysis technology.

Description

Technical Field

[0001] The present invention relates to the technical field of ships and marine engineering equipment, and in particular to an intelligent state monitoring and fault early warning system for power systems of ships and marine engineering equipment. Background Art

[0002] Traditional ship and marine engineering equipment power system status monitoring and fault warning methods rely too much on manual inspections and the operator's experience and judgment, which leads to a series of problems such as limited monitoring range, slow warning response and inefficient fault handling. With the rapid advancement of modern science and technology, especially the vigorous development of sensor technology, data processing technology and analysis technology, intelligent status monitoring and fault warning systems provide new solutions for the safe operation of ships and marine engineering equipment. These systems can collect and analyze various operating data of the power system in real time and accurately, and realize comprehensive monitoring and accurate warning of the system status through advanced algorithm models, thereby effectively avoiding safety hazards caused by manual misjudgment or untimely monitoring. The application of intelligent systems not only greatly improves the reliability and safety of the power system, but also reduces operation and maintenance costs, providing strong support for the efficient operation and sustainable development of ships and marine engineering equipment.

[0003] Due to the complex and changeable operating environment of ships and marine engineering equipment, sensors are easily affected by external interference, resulting in errors in the collected data, affecting the accuracy of subsequent analysis. Secondly, some current systems still use relatively simple threshold judgment or statistical methods, which are difficult to effectively capture the complex and changeable fault characteristics of the power system, resulting in high false alarm and missed alarm rates. Summary of the invention

[0004] The purpose of the present invention is to realize real-time monitoring and fault warning of power systems of ships and marine engineering equipment through advanced sensor technology, data processing and analysis technology, and to propose an intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] Intelligent status monitoring and fault warning system for power systems of ships and marine engineering equipment, including data acquisition module, real-time monitoring module, intelligent analysis module, fault warning module, remote monitoring module and feedback control module;

[0007] The data acquisition module is used to obtain key parameters of the power system in real time, including engine speed, oil temperature, water temperature, oil pressure, water pressure and vibration signals, providing basic data support for the system;

[0008] The real-time monitoring module realizes the visualization of data, intuitively reflects the system status in the form of charts, and supports historical data query and analysis;

[0009] The intelligent analysis module uses a deep learning algorithm to perform intelligent analysis on real-time monitoring data, accurately identify abnormal system conditions, and improve the accuracy of early warning;

[0010] The fault warning module adopts a variety of warning methods according to the analysis results to ensure timely and accurate transmission of warning information;

[0011] The remote monitoring module realizes remote monitoring and management of the power system, improving the flexibility and maintainability of the system;

[0012] The feedback control module automatically adjusts system parameters according to the analysis results to avoid or slow down the development of faults.

[0013] Based on the above technical solution, the present invention can also be improved as follows.

[0014] Furthermore, the data acquisition module adopts a high-precision, high-stability sensor array with a data acquisition accuracy of no less than ±0.1%. The sensor array can automatically adjust the sensor zero point and sensitivity to ensure the data acquisition accuracy in long-term stable operation. The real-time monitoring module adopts dynamic chart display technology, which can update the system status data in real time and support comparative analysis of historical data.

[0015] Furthermore, the data preprocessing submodule of the intelligent analysis module adopts filtering and noise reduction algorithms to remove noise interference in the original data. The feature extraction submodule adopts a deep learning network to automatically extract key features that reflect the system status. The pattern recognition submodule uses a trained deep learning model to perform pattern recognition on the extracted features to achieve intelligent judgment of the system status. The intelligent analysis module can continuously optimize the deep learning model based on historical data and real-time data.

[0016] Furthermore, the fault warning module adopts a hierarchical warning strategy to automatically determine the alarm priority according to the severity of the abnormal state and the maximum allowed response time of the operator, ensuring timely and accurate communication of warning information. At the same time, the warning module also supports customized warning rules to meet the needs of different application scenarios.

[0017] Furthermore, the remote monitoring module adopts communication technology to realize real-time transmission of real-time monitoring data and warning information, and supports multi-terminal access. At the same time, the remote monitoring module is provided with an equipment management submodule, and the operator remotely controls and configures the power system through the remote monitoring center.

[0018] Furthermore, during the data collection process, the system will perform real-time verification of the data collected by each sensor, and compare the data consistency of adjacent sensors or the same sensor at different time points through algorithms. At the same time, the system uses a redundant backup mechanism to collect and store each key data point multiple times to prevent data loss or damage.

[0019] Furthermore, the real-time monitoring module is also provided with an abnormal data intelligent identification submodule and an alarm function submodule. The system can monitor and analyze data in real time. Once abnormal data is found, which exceeds the normal range or the data fluctuates abnormally, the system will automatically trigger the alarm mechanism and remind the operator through sound and visual means. At the same time, the system will also record the abnormal data and its related information, the time of occurrence, and the type of abnormality in the log for subsequent analysis and processing.

[0020] Furthermore, in the data preprocessing stage, the system will enhance the original data, perform data amplification and data transformation to increase the diversity and richness of the data. The adaptive learning capability of the intelligent analysis module also includes a model automatic update submodule and a tuning submodule. The system can automatically collect new data samples regularly or as needed, and use these data samples to update and tune the deep learning model. By continuously optimizing the model parameters and structure, the system can maintain sensitivity and accuracy to the latest data and abnormal patterns.

[0021] Furthermore, the remote monitoring module also has a remote fault diagnosis submodule and an elimination function submodule, which can remotely diagnose and eliminate faults in the power system through the remote monitoring center. The system can provide online fault diagnosis tools, troubleshooting guides and expert support functions. At the same time, the system will also record key information and data during the fault handling process.

[0022] Compared with the prior art, the technical solution of this application has the following beneficial technical effects:

[0023] The data acquisition module of the present invention uses high-precision sensors and advanced signal processing technology to obtain key parameters of the power system in real time, including engine speed, oil temperature, water temperature, oil pressure, water pressure and vibration signals, etc., providing accurate and comprehensive basic data support for the system, which not only improves the accuracy of data acquisition, but also provides a reliable data basis for subsequent intelligent analysis and fault warning. Secondly, a deep learning algorithm is used to perform intelligent analysis on real-time monitoring data, which can accurately identify abnormal system conditions and significantly improve the accuracy of warning. At the same time, the fault warning module adopts a variety of warning methods based on the analysis results of the intelligent analysis module to ensure timely and accurate communication of warning information, effectively avoiding It avoids the omission or delay of warning information caused by a single warning method. In addition, it also realizes remote monitoring and management of the power system, allowing operation and maintenance personnel to view the system status, receive warning information, and respond quickly anytime and anywhere, which not only improves the flexibility and maintainability of the system, but also reduces operation and maintenance costs, and improves the operating efficiency of ships and marine engineering equipment. Finally, the feedback control module of the present invention automatically adjusts the system parameters according to the analysis results of the intelligent analysis module, which can avoid or slow down the development of faults, and further improve the reliability and safety of the power system. This automated feedback control mechanism not only reduces the need for manual intervention, but also improves the efficiency and accuracy of fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a system block diagram of the intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Combination Figure 1 As shown, the intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment of the present invention includes a data acquisition module, a real-time monitoring module, an intelligent analysis module, a fault warning module, a remote monitoring module and a feedback control module;

[0027] The data acquisition module is used to obtain key parameters of the power system in real time, including engine speed, oil temperature, water temperature, oil pressure, water pressure and vibration signals, providing basic data support for the system;

[0028] The real-time monitoring module realizes the visualization of data, intuitively reflects the system status in the form of charts, and supports historical data query and analysis;

[0029] The intelligent analysis module uses deep learning algorithms to perform intelligent analysis on real-time monitoring data, accurately identify abnormal system conditions, and improve the accuracy of early warnings;

[0030] The fault warning module uses a variety of warning methods based on the analysis results to ensure timely and accurate transmission of warning information;

[0031] The remote monitoring module enables remote monitoring and management of the power system, improving the flexibility and maintainability of the system;

[0032] The feedback control module automatically adjusts system parameters based on the analysis results to avoid or slow down the development of faults.

[0033] In a preferred embodiment, the present invention can be further configured as follows: the data acquisition module adopts a high-precision, high-stability sensor array, the data acquisition accuracy is not less than ±0.1%, the sensor array can automatically adjust the sensor zero point and sensitivity to ensure the data acquisition accuracy in long-term stable operation, the real-time monitoring module adopts dynamic chart display technology, can update the system status data in real time, and support the comparative analysis of historical data, the data acquisition module adopts a high-precision, high-stability sensor array, and the data acquisition accuracy is not less than ±0.1%. It is ensured that even in the case of complex and changeable operating environments of ships and marine engineering equipment, the data of key parameters of the power system can be stably and accurately collected. More importantly, the sensor array has the function of automatically adjusting the sensor zero point and sensitivity, which means that in the long-term operation process, even if the sensor drifts due to environmental factors or its own aging, it can automatically calibrate, thereby maintaining the high accuracy of data acquisition. This feature greatly improves the reliability of data and the accuracy of subsequent analysis, and provides a solid foundation for intelligent analysis and fault warning.

[0034] The real-time monitoring module uses dynamic chart display technology. This technology can not only update the system status data in real time, allowing users to grasp the latest status of the power system at any time, but also supports comparative analysis of historical data. By comparing current data with historical data, users can more easily identify abnormal changes in system status, so as to take measures in advance to avoid potential failures. This dynamic and intuitive monitoring method not only improves the timeliness of early warning response, but also enhances the user's perception and understanding of system status, providing a strong guarantee for the safe operation of ships and marine engineering equipment.

[0035] In a preferred embodiment, the present invention can be further configured as follows: the data preprocessing submodule of the intelligent analysis module adopts filtering and noise reduction algorithms to remove noise interference in the original data, the feature extraction submodule adopts a deep learning network to automatically extract key features reflecting the system state, the pattern recognition submodule uses a trained deep learning model to perform pattern recognition on the extracted features to achieve intelligent judgment of the system state, and the intelligent analysis module can continuously optimize the deep learning model based on historical data and real-time data. In view of the problem that sensor data is easily interfered with, the data preprocessing submodule of the intelligent analysis module adopts filtering and noise reduction algorithms. It can effectively remove noise interference in the original data and improve the purity and reliability of the data. Through precise data preprocessing, the intelligent analysis module can more accurately capture the real state of the power system operation, laying a solid foundation for subsequent feature extraction and pattern recognition. This not only improves the system's sensitivity to fault features, but also reduces the risk of false alarms and missed reports caused by data errors.

[0036] The intelligent analysis module also includes a feature extraction submodule and a pattern recognition submodule. The feature extraction submodule uses a deep learning network to automatically extract key features that reflect the system status from the preprocessed data. These features not only contain basic information about the operation of the power system, but also contain potential signs of failure. The pattern recognition submodule uses a trained deep learning model to perform pattern recognition on these extracted features to achieve intelligent judgment of the system status. Through the use of deep learning technology, the intelligent analysis module can more accurately identify the different states of the power system, including normal state, abnormal state and fault state, thereby providing more accurate early warning information. In addition, the intelligent analysis module can also continuously optimize the deep learning model based on historical data and real-time data, so that it can better adapt to changes in the power system and further improve the accuracy and reliability of early warnings.

[0037] In a preferred embodiment, the present invention can be further configured as follows: the fault warning module adopts a hierarchical warning strategy, automatically determines the priority of the alarm according to the severity of the abnormal state and the maximum allowable response time of the operator, and ensures the timely and accurate transmission of the warning information. At the same time, the warning module also supports custom warning rules to meet the needs of different application scenarios. In view of the problem of slow warning response, the fault warning module adopts a hierarchical warning strategy. This strategy automatically determines the priority of the alarm according to the severity of the abnormal state and the maximum allowable response time of the operator. This means that when a slight abnormality occurs in the power system, the warning module will issue a low-level warning to give the operator enough time to conduct preliminary inspections and preparations; and when the system state deteriorates or a failure is about to occur, the warning module will immediately issue a high-level warning to ensure that the operator can respond quickly and take effective measures. This hierarchical warning mechanism not only improves the timeliness and pertinence of the warning information, but also helps to optimize the operator's workflow and reduce safety hazards caused by untimely warning responses.

[0038] The early warning module also supports custom early warning rules. This function allows users to flexibly set early warning conditions and thresholds according to the specific characteristics of the power system and the operating environment. For example, on some key equipment, users may need to set more stringent early warning rules to ensure that any minor anomalies can be discovered and handled in a timely manner; on other equipment, users may want to relax early warning conditions to reduce unnecessary interference and false alarms. By customizing early warning rules, the early warning module can better adapt to various complex application scenarios and improve the accuracy and practicality of early warnings. In addition, this flexibility also helps users continuously optimize and adjust early warning strategies according to actual needs, further improving the overall performance and reliability of the system.

[0039] In a preferred embodiment, the present invention can be further configured as follows: the remote monitoring module adopts communication technology to realize the real-time transmission of real-time monitoring data and early warning information, and supports multi-terminal access. At the same time, the remote monitoring module is provided with an equipment management submodule, and the operator remotely controls and configures the power system through the remote monitoring center. In view of the problem of insufficient remote monitoring capability and information transmission delay, the remote monitoring module adopts advanced communication technology to realize the real-time transmission of real-time monitoring data and early warning information. It ensures that no matter where the power system is located, the operator can instantly obtain the latest status of the system through the remote monitoring center, so as to make a quick and accurate response. In addition, the remote monitoring module supports multi-terminal access, which means that the operator can not only monitor through fixed terminals (such as computers), but also grasp the system status anytime and anywhere through mobile devices (such as mobile phones, tablets), which greatly improves the flexibility and convenience of monitoring. This real-time, multi-terminal remote monitoring capability not only improves the response speed of the system, but also helps the operator to understand the system status more comprehensively and make more reasonable decisions.

[0040] The remote monitoring module also has an equipment management submodule. This function allows operators to remotely control the power system through the remote monitoring center, such as starting, stopping, adjusting parameters, etc., and remotely configure the system, such as setting warning rules and updating software. This remote control and configuration capability greatly improves the maintainability and flexibility of the system and reduces the time and cost consumption caused by on-site operations. At the same time, the equipment management submodule also supports remote query and analysis of the historical data of the power system, providing operators with richer data support, helping them to have a deeper understanding of system performance and optimize operation strategies.

[0041] In a preferred embodiment, the present invention can be further configured as follows: during the data collection process, the system will perform real-time verification on the data collected by each sensor, and compare the data consistency of adjacent sensors or the same sensor at different time points through algorithms. At the same time, the system adopts a redundant backup mechanism to perform multiple collections and storage on each key data point to prevent data loss or damage, thereby realizing the function of real-time verification of the data collected by each sensor during the data collection process. By comparing the consistency of data of adjacent sensors or the same sensor at different time points through algorithms, outliers and errors in the data are effectively identified and corrected, thereby improving the accuracy and reliability of the data. This real-time verification mechanism not only helps to reduce false alarms and missed alarms caused by sensor failures or external interference, but also provides more accurate data support for subsequent fault warnings and intelligent analysis. This improvement in data quality is crucial to ensuring the accuracy of power system status monitoring and the effectiveness of fault warnings.

[0042] The system also uses a redundant backup mechanism. This mechanism collects and stores each key data point multiple times. Even if a sensor or data storage link fails, the system status can be restored through other backup data, thus preventing data loss or damage. This redundant backup design not only improves the fault tolerance of the system, but also ensures the integrity and security of data during collection, transmission and storage. In addition, the multiple collected data can also be used for subsequent data analysis and fault diagnosis, providing operators with more comprehensive data support, helping them to more accurately judge the status of the power system, take preventive measures in time, and avoid potential safety hazards.

[0043] In a preferred embodiment, the present invention can be further configured as follows: the real-time monitoring module is also provided with an abnormal data intelligent identification submodule and an alarm function submodule. The system can monitor and analyze data in real time. Once abnormal data is found, it exceeds the normal range, and the data fluctuation is abnormal. The system will automatically trigger the alarm mechanism to remind the operator to pay attention through sound and visual methods. At the same time, the system will also record the abnormal data and its related information in the log. The time and type of abnormality are recorded for subsequent analysis and processing. The real-time monitoring module is provided with an abnormal data intelligent identification submodule. The system can monitor and analyze data in real time. Once abnormal data is found, such as exceeding the normal range, abnormal data fluctuation, etc., the system will automatically trigger the alarm mechanism immediately. This intelligent abnormal data recognition capability not only improves the system's sensitivity to abnormal states, but also greatly shortens the time interval from the occurrence of an abnormality to being identified, providing operators with more timely and accurate early warning information. This improvement in real-time and accuracy helps operators to respond quickly and take effective measures to prevent potential faults from further deteriorating, thereby ensuring the safe and stable operation of the power system.

[0044] The real-time monitoring module is also equipped with an alarm function submodule, and has the function of recording abnormal data and related information into the log. When the system identifies abnormal data, it will not only remind the operator through various means such as sound and vision, but also automatically record the time of occurrence of the abnormal data, the type of abnormality and other detailed information. This comprehensive abnormal data processing mechanism not only helps operators to quickly locate the source of the problem, but also provides valuable data support for subsequent data analysis and troubleshooting. In addition, by regularly analyzing the abnormal data log, operators can also discover the potential laws of system operation and provide a scientific basis for system optimization and improvement. This data-driven management method not only improves the reliability and stability of the system, but also reduces operation and maintenance costs and improves overall operational efficiency.

[0045] In a preferred embodiment, the present invention can be further configured as follows: in the data preprocessing stage, the system will enhance the original data, amplify the data, and transform the data to increase the diversity and richness of the data. The adaptive learning ability of the intelligent analysis module also includes a model automatic update submodule and a tuning submodule. The system can automatically collect new data samples regularly or according to demand, and use these data samples to update and tune the deep learning model. By continuously optimizing the model parameters and structure, the system can maintain sensitivity and accuracy to the latest data and abnormal patterns. In view of the problem of insufficient data preprocessing ability, enhanced processing of the original data is added in the data preprocessing stage, including data amplification and data transformation. By increasing the diversity and richness of the data, the problems of insufficient samples and incomplete features that may exist in the original data are effectively solved. Data amplification can generate more similar but not completely identical data samples by means of copying, rotating, scaling, etc., while data transformation can improve the distribution and feature expression of data by methods such as normalization, standardization, and principal component analysis. This data enhancement processing not only improves the quality and availability of the data, but also provides a richer and more comprehensive data foundation for subsequent intelligent analysis. This improvement in data preprocessing capabilities helps the system to more accurately identify and analyze the status of the power system, and improve the accuracy and reliability of fault warnings.

[0046] The intelligent analysis module has added adaptive learning capabilities, including model automatic update submodules and tuning submodules. This enables the system to automatically collect new data samples regularly or as needed, and use these data samples to update and tune the deep learning model. By continuously optimizing model parameters and structures, the system can maintain sensitivity and accuracy to the latest data and abnormal patterns. This adaptive learning capability not only improves the generalization ability of the model, but also enables the system to continuously learn and adapt to changes in the power system. In addition, the process of automatic model update and tuning can also reduce manual intervention, reduce operation and maintenance costs, and improve the automation and intelligence level of the system. The improvement of the adaptability of this intelligent analysis model helps the system identify potential faults more promptly and provide operators with more accurate early warning information, thereby ensuring the safe and stable operation of the power system.

[0047] In a preferred embodiment, the present invention can be further configured as follows: the remote monitoring module also has a remote fault diagnosis submodule and a troubleshooting submodule, and the power system is remotely diagnosed and troubleshooted through the remote monitoring center. The system can provide online fault diagnosis tools, troubleshooting guides and expert support functions. At the same time, the system will also record key information and data in the fault handling process. In view of the problem that the fault diagnosis is not timely enough, the remote monitoring module is added with a remote fault diagnosis submodule and an elimination function submodule. It enables the operator to remotely diagnose and troubleshoot the power system through the remote monitoring center, greatly shortening the response time of fault diagnosis and processing. The system not only provides online fault diagnosis tools that can quickly locate and analyze the source of the fault, but also provides a troubleshooting guide to help operators solve the problem efficiently step by step. More importantly, the system also integrates the expert support function. When encountering complex or difficult to solve faults, the operator can immediately obtain remote assistance from experts to ensure that the fault is handled professionally and accurately. This remote diagnosis and troubleshooting capability not only improves the efficiency of fault handling, but also reduces the losses caused by fault downtime, and ensures the continuous and stable operation of the power system.

[0048] The system is also designed with a fault handling process recording function. During the troubleshooting and handling process, the system will record key information and data in detail, including but not limited to the time of the fault, fault type, diagnosis process, solution measures taken, and handling results. This comprehensive record not only helps operators review and summarize fault handling experience and provide reference for future fault handling, but also facilitates management to audit and optimize the fault handling process to ensure the standardization and effectiveness of fault handling. In addition, fault handling records can also serve as an important reference for system maintenance and upgrades, helping technicians identify potential defects and improvement points in the system, thereby continuously improving the reliability and stability of the system.

[0049] The system first uses the data acquisition module to obtain key parameters of the power system in real time using a high-precision, high-stability sensor array, such as engine speed, oil temperature, water temperature, oil pressure, water pressure, and vibration signals. These data provide a solid foundation for the subsequent analysis of the system. During the data acquisition process, the system will perform real-time verification of the data collected by each sensor, and use algorithms to compare the consistency of data from adjacent sensors or the same sensor at different time points to ensure the accuracy and reliability of the data. At the same time, the system also uses a redundant backup mechanism to perform multiple acquisitions and storage of each key data point to prevent data loss or damage.

[0050] The collected data is then sent to the real-time monitoring module, which uses dynamic chart display technology to update system status data in real time, and intuitively reflects the system status in the form of charts, supporting the query and analysis of historical data. In addition, the real-time monitoring module also has an abnormal data intelligent identification submodule and an alarm function submodule, which can monitor and analyze data in real time. Once abnormal data is found, such as exceeding the normal range or abnormal data fluctuations, the system will automatically trigger the alarm mechanism, remind the operator through sound, vision and other methods, and record the abnormal data and related information (including occurrence time, abnormal type, etc.) in the log for subsequent analysis and processing.

[0051] The intelligent analysis module is the core part of the system. It uses deep learning algorithms to perform intelligent analysis on real-time monitoring data. In the data preprocessing stage, the system will enhance the original data, such as data amplification and data transformation, to increase the diversity and richness of the data. Subsequently, the feature extraction submodule uses the deep learning network to automatically extract key features that reflect the system status, and the pattern recognition submodule uses the trained deep learning model to perform pattern recognition on the extracted features to achieve intelligent judgment of the system status. The intelligent analysis module can also continuously optimize the deep learning model based on historical data and real-time data to improve the accuracy and efficiency of analysis.

[0052] When the intelligent analysis module identifies an abnormal state of the system, the fault warning module will be activated immediately. The module adopts a graded warning strategy to automatically determine the priority of the alarm according to the severity of the abnormal state and the maximum allowable response time of the operator to ensure the timely and accurate communication of the warning information. At the same time, the warning module also supports customized warning rules to meet the needs of different application scenarios.

[0053] The remote monitoring module realizes remote monitoring and management of the power system. Through communication technology, real-time monitoring data and early warning information can be transmitted to the remote monitoring center in real time, supporting multi-terminal access. Operators can remotely control and configure the power system through the remote monitoring center. In addition, the remote monitoring module also has equipment management submodules, remote fault diagnosis submodules, and troubleshooting submodules. The equipment management submodule allows operators to remotely control and configure the power system, while the remote fault diagnosis submodule can provide online fault diagnosis tools, troubleshooting guides, and expert support functions to help operators quickly locate and solve problems. At the same time, the system will also record key information and data during the fault handling process to provide a reference for subsequent fault analysis and system optimization.

[0054] Finally, the feedback control module automatically adjusts system parameters based on the analysis results of the intelligent analysis module to avoid or slow down the development of faults. This intelligent feedback control mechanism can further improve the stability and reliability of the system.

[0055] In summary, the intelligent status monitoring and fault warning system for the power system of ships and marine engineering equipment integrates functional modules such as high-precision data acquisition, real-time monitoring and analysis, intelligent warning, remote monitoring and fault diagnosis, and feedback control, thereby realizing comprehensive, real-time, and intelligent monitoring and management of the power system status, providing a strong guarantee for the safe and stable operation of ships and marine engineering equipment.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0057] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent status monitoring and fault warning system for power systems of ships and marine engineering equipment, characterized by: It includes data acquisition module, real-time monitoring module, intelligent analysis module, fault warning module, remote monitoring module and feedback control module; The data acquisition module is used to obtain key parameters of the power system in real time, including engine speed, oil temperature, water temperature, oil pressure, water pressure and vibration signals, providing basic data support for the system; The real-time monitoring module realizes the visualization of data, intuitively reflects the system status in the form of charts, and supports historical data query and analysis; The intelligent analysis module uses a deep learning algorithm to perform intelligent analysis on real-time monitoring data, accurately identify abnormal system conditions, and improve the accuracy of early warning; The fault warning module adopts a variety of warning methods according to the analysis results to ensure timely and accurate transmission of warning information; The remote monitoring module realizes remote monitoring and management of the power system, improving the flexibility and maintainability of the system; The feedback control module automatically adjusts system parameters according to the analysis results to avoid or slow down the development of faults.

2. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: The data acquisition module adopts a high-precision and high-stability sensor array with a data acquisition accuracy of no less than ±0.1%. The sensor array can automatically adjust the sensor zero point and sensitivity to ensure the data acquisition accuracy in long-term stable operation. The real-time monitoring module adopts dynamic chart display technology, which can update the system status data in real time and support comparative analysis of historical data.

3. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: The data preprocessing submodule of the intelligent analysis module adopts filtering and noise reduction algorithms to remove noise interference in the original data. The feature extraction submodule adopts a deep learning network to automatically extract key features that reflect the system status. The pattern recognition submodule uses a trained deep learning model to perform pattern recognition on the extracted features to achieve intelligent judgment of the system status. The intelligent analysis module can continuously optimize the deep learning model based on historical data and real-time data.

4. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: The fault warning module adopts a hierarchical warning strategy, automatically determines the alarm priority according to the severity of the abnormal state and the maximum allowable response time of the operator, and ensures timely and accurate communication of warning information. At the same time, the warning module also supports customized warning rules to meet the needs of different application scenarios.

5. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: The remote monitoring module adopts communication technology to realize real-time transmission of real-time monitoring data and warning information, and supports multi-terminal access. At the same time, the remote monitoring module is provided with an equipment management submodule, and the operator remotely controls and configures the power system through the remote monitoring center.

6. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: During the data collection process, the system will perform real-time verification of the data collected by each sensor, and compare the data consistency of adjacent sensors or the same sensor at different time points through algorithms. At the same time, the system uses a redundant backup mechanism to collect and store each key data point multiple times to prevent data loss or damage.

7. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 1 is characterized in that: The real-time monitoring module is also provided with an abnormal data intelligent identification submodule and an alarm function submodule. The system can monitor and analyze data in real time. Once abnormal data is found, which exceeds the normal range or the data fluctuates abnormally, the system will automatically trigger the alarm mechanism and remind the operator through sound and visual means. At the same time, the system will also record the abnormal data and its related information, the time of occurrence, and the type of abnormality in the log for subsequent analysis and processing.

8. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 3 is characterized in that: During the data preprocessing stage, the system will perform enhanced processing, data amplification, and data transformation on the original data to increase the diversity and richness of the data. The adaptive learning capability of the intelligent analysis module also includes a model automatic update submodule and a tuning submodule. The system can automatically collect new data samples regularly or as needed, and use these data samples to update and tune the deep learning model. By continuously optimizing model parameters and structure, the system can maintain sensitivity and accuracy to the latest data and abnormal patterns.

9. The intelligent state monitoring and fault warning system for power systems of ships and marine engineering equipment according to claim 5 is characterized in that: The remote monitoring module also has a remote fault diagnosis submodule and an elimination function submodule. The power system is remotely diagnosed and troubleshooted through the remote monitoring center. The system can provide online fault diagnosis tools, troubleshooting guides and expert support functions. At the same time, the system will also record key information and data during the fault handling process.

Images