Marine diesel engine monitoring and early warning method and system based on data processing
The ship diesel engine monitoring system predicts faults through data analysis and adaptive mechanisms, addressing the lack of early warning in existing systems to enhance safety and efficiency.
Patent Information
- Application Number
- CN202411564415.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-11-05
AI Technical Summary
Existing ship diesel engine monitoring systems lack the capability for early warning of potential faults, leading to downtime risks and safety concerns during navigation.
A method and system for ship diesel engine monitoring that predicts failure risks by analyzing data propagation paths, identifying key monitoring parameters, setting thresholds, and using fault prediction models to provide early warnings and adaptive mechanisms.
Enables timely prediction and prevention of diesel engine faults, reducing the risk of accidents and improving navigation safety by providing an intuitive monitoring platform for operators.
Smart Images

Figure CN119062443A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of diesel engine status monitoring, and in particular to a ship diesel engine monitoring and early warning method and system based on data processing. Background Art
[0002] Ship diesel engine monitoring and early warning refers to the process of using various sensors and monitoring technologies to monitor the operating status of ship diesel engines in real time, and through data analysis and processing, timely discover potential faults and abnormalities, so as to give early warnings and take corresponding maintenance measures to ensure the reliable operation of the diesel engine and the safe navigation of the ship. The ship diesel engine monitoring and early warning system can improve the safety and economy of the ship, and reduce the navigation interruption and maintenance costs caused by faults. With the development of global trade and the growth of the marine economy, ships as important means of transportation have received more and more attention. The operating status of ship diesel engines as the main power unit of ships is crucial to the safety and economic operation of ships.
[0003] In the prior art, the method for monitoring and early warning of ship diesel engines mainly adopts intelligent algorithms to learn a large number of diesel engine fault characteristics, and locates the source of the diesel engine fault after the diesel engine fails through detailed classification of the fault characteristics. However, this method cannot issue early warning prompts to relevant personnel before the fault occurs, resulting in a lack of fault prediction capability for ship diesel engines, which is prone to downtime risks during operation, posing serious risks to ship navigation. Summary of the invention
[0004] In order to solve the above problems, the present invention provides a ship diesel engine monitoring and early warning method and system based on data processing, which can predict the failure risk of the ship diesel engine in advance and make corresponding adjustments to improve the safety of ship navigation.
[0005] In a first aspect, the present invention provides a marine diesel engine monitoring and early warning method based on data processing, comprising: Acquire a ship diesel engine to be monitored and its corresponding output device, analyze the data propagation path of the output device, identify the data transmission port of the data propagation path, set a data sensing node of the data transmission port, and set a data processing interface of the data sensing node, and configure the data monitoring device of the ship diesel engine in combination with the data transmission port, the data sensing node and the data processing interface; querying historical operating parameters of the ship diesel engine, identifying parameter types of the historical operating parameters, calculating correlation coefficients between the parameter types, identifying associated parameter combinations of the ship diesel engine based on the parameter types and the correlation coefficients, extracting key monitoring parameters from the associated parameter combinations, performing time series analysis on the key monitoring parameters, and obtaining time series analysis results; Analyze the change trend of the key monitoring parameter under the time series analysis result, set a normal threshold value of the change trend, and identify the abnormal parameter of the key monitoring parameter according to the normal threshold value, analyze the fault symptom of the ship diesel engine based on the abnormal parameter, identify the fault type corresponding to the fault symptom, extract the fault parameter characteristics of the key monitoring parameter under the fault type, and determine the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics; Based on the data monitoring device, real-time operating parameters of the ship diesel engine are collected, real-time key parameters in the real-time operating parameters are extracted, and alarm thresholds of the real-time key parameters are set; according to the alarm thresholds, the real-time fault source of the ship diesel engine is located; in combination with the fault prediction model and the real-time key parameters, the potential fault source of the ship diesel engine is identified; based on the real-time fault source, the deviation index of the potential fault source is calculated; and according to the deviation index, an adaptive mechanism of the fault prediction model is set; Identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine; set the fault diagnosis rules of the ship diesel engine according to the potential fault type and the potential fault degree; set the early warning mechanism of the fault diagnosis rules; combine the fault prediction model, the adaptive mechanism and the early warning mechanism to set the visual interactive interface of the ship diesel engine.
[0006] In a possible implementation manner of the first aspect, analyzing the data propagation path of the output device includes: identifying output parameters of the output device; Analyzing parameter attributes of the output parameter, and identifying an output mode of the output parameter according to the parameter attributes; Based on the output mode, analyzing the transmission link of the output parameter and determining the communication mode of the transmission link; identifying an output result of the output parameter according to the transmission link and the communication mode; In combination with the output method and the output result, the data propagation path of the output device is analyzed.
[0007] In a possible implementation manner of the first aspect, extracting the key monitoring parameter in the associated parameter combination includes: Identifying a combination type in the associated parameter combination; Based on the associated parameter combination, identifying a parameter type of the combination type; The contribution rate of the parameter type in the associated parameter combination is calculated using the following formula: ; in, represents the contribution rate of the ith parameter type in the associated parameter combination, n represents the total number of evaluation indicators of the parameter type, A represents all parameter types, Indicates the evaluation result value of the i-th parameter type in the q-th evaluation among all parameter types. Represents the total value of the evaluation results of all parameter types in the qth evaluation, q represents the evaluation index of the parameter type, and i represents the index of the parameter type; According to the contribution rate, key monitoring parameters in the associated parameter combination are extracted.
[0008] In a possible implementation manner of the first aspect, identifying the abnormal parameter of the key monitoring parameter according to the normal threshold includes: Locating a parameter output device of the key monitoring parameter; Based on the parameter output device, identifying the parameter type of the key monitoring parameter; analyzing the current operating conditions of the parameter output device; Identifying an acceptable variation range of the parameter type according to the normal threshold and the current operating condition; Based on the normal threshold and the acceptable abnormal variation range, setting the abnormal variation standard of the key monitoring parameter; Based on the abnormality standard, the abnormality parameters of the key monitoring parameters are identified.
[0009] In a possible implementation of the first aspect, analyzing the fault symptom of the ship diesel engine based on the abnormal parameter includes: Analyze the influencing factors of the abnormal parameters; Based on the influencing factors, identifying the variation range of the variation parameter; Analyzing the operation track of the ship diesel engine according to the abnormal variation range; Analyzing the risk status of the ship diesel engine under the operating trajectory; According to the risk status, the failure signs of the ship diesel engine are analyzed.
[0010] In a possible implementation manner of the first aspect, identifying the fault type corresponding to the fault symptom includes: Identify the manifestations of the fault symptoms; Extracting equipment operation data corresponding to the fault symptom according to the manifestation form; Identify abnormal components of the equipment operation data, and analyze the impact scope of the fault symptom based on the abnormal components; Analyzing the influencing factors of the abnormal components, and locating the output sources of the abnormal components according to the influencing factors; The fault type corresponding to the fault symptom is identified by combining the manifestation form, the impact scope and the output source.
[0011] In a possible implementation of the first aspect, determining a fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics includes: Based on the time series analysis result, extracting historical operation data of the ship diesel engine, and extracting historical parameter features of the historical operation data; Identifying the characteristic levels of the historical parameter characteristics and the fault parameter characteristics; identifying relevant features of the historical parameter features according to the feature level and the fault parameter characteristics; Performing dimensionality reduction processing on the relevant features to obtain a target fault feature set; Determining a fault prediction network of the ship diesel engine based on the time series analysis result and the target fault feature set; Based on the historical operation data and the target fault feature set, performing prediction training on the fault prediction network to obtain a prediction result; A fault prediction model of the ship diesel engine is determined according to the fault prediction network and the prediction result.
[0012] In a possible implementation of the first aspect, locating the real-time fault source of the ship diesel engine according to the alarm threshold includes: According to the alarm threshold, identifying the alarm type of the ship diesel engine; Query the parameter type corresponding to the alarm type; Analyzing the alarm cause of the ship diesel engine based on the parameter type; The real-time fault source of the ship diesel engine is located according to the parameter type and the alarm cause.
[0013] In a possible implementation of the first aspect, identifying a potential fault source of the ship diesel engine in combination with the fault prediction model and the real-time key parameter includes: Inputting the real-time key parameters into the fault prediction model, and extracting parameter features of the real-time key parameters; identifying the time series change trend of the parameter features; Based on the time series change trend, identifying the dynamic characteristics of the real-time key parameters; Determining the fault type of the ship diesel engine according to the dynamic characteristics and the time series change trend; According to the failure probability and the failure type, a potential failure source of the ship diesel engine is identified.
[0014] In a possible implementation manner of the first aspect, setting an adaptive mechanism of the fault prediction model according to the deviation index includes: According to the deviation index, identifying a prediction deviation object of the fault prediction model; Locating an output position of the prediction deviation object and identifying an output type of the output position; Extracting a normal output standard of the output type, and setting a dynamic adjustment range of the fault prediction model according to the normal output standard; Based on the dynamic adjustment range, an adaptive mechanism of the fault prediction model is set.
[0015] In a second aspect, the present invention provides a marine diesel engine monitoring and early warning system based on data processing, the system comprising: A data monitoring module, used to obtain a marine diesel engine to be monitored and its corresponding output device, analyze a data propagation path of the output device, identify a data transmission port of the data propagation path, set a data sensing node of the data transmission port, and set a data processing interface of the data sensing node, and configure a data monitoring device of the marine diesel engine in combination with the data transmission port, the data sensing node and the data processing interface; a key parameter extraction module, used to query the historical operating parameters of the marine diesel engine, identify the parameter types of the historical operating parameters, calculate the correlation coefficients between the parameter types, identify the associated parameter combinations of the marine diesel engine based on the parameter types and the correlation coefficients, extract the key monitoring parameters in the associated parameter combinations, perform time series analysis on the key monitoring parameters, and obtain time series analysis results; a fault prediction module, used for analyzing the change trend of the key monitoring parameter under the time series analysis result, setting a normal threshold value of the change trend, and identifying the abnormal parameter of the key monitoring parameter according to the normal threshold value, analyzing the fault symptom of the ship diesel engine based on the abnormal parameter, identifying the fault type corresponding to the fault symptom, extracting the fault parameter characteristics of the key monitoring parameter under the fault type, and determining the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics; A fault adaptive module, used to collect the real-time operating parameters of the ship diesel engine based on the data monitoring device, extract the real-time key parameters in the real-time operating parameters, and set the alarm threshold of the real-time key parameters, locate the real-time fault source of the ship diesel engine according to the alarm threshold, identify the potential fault source of the ship diesel engine in combination with the fault prediction model and the real-time key parameters, calculate the deviation index of the potential fault source based on the real-time fault source, and set the adaptive mechanism of the fault prediction model according to the deviation index; The result visualization module is used to identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine. According to the potential fault type and the potential fault degree, the fault diagnosis rules of the ship diesel engine are set, and the early warning mechanism of the fault diagnosis rules is set. In combination with the fault prediction model, the adaptive mechanism and the early warning mechanism, a visualization interactive interface of the ship diesel engine is set.
[0016] Compared with the prior art, the technical principle and beneficial effects of this solution are: The present invention first obtains the ship diesel engine to be monitored and its corresponding output device, analyzes the data propagation path of the output device, identifies the data transmission port of the data propagation path, sets the data sensing node of the data transmission port, and sets the data processing interface of the data sensing node. In combination with the data transmission port, the data sensing node and the data processing interface, the data monitoring device of the ship diesel engine is configured, which can better plan and allocate resources for monitoring, ensure that the monitoring covers all diesel engines and their output devices that need to be paid attention to, help to ensure the integrity and accuracy of the collected data, and thus improve the monitoring quality of the ship diesel engine; further, the historical operating condition parameters of the ship diesel engine are queried. The data are obtained by analyzing the parameter types of the historical operating parameters, and the parameter types of the historical operating parameters are identified, the correlation coefficients between the parameter types are calculated, and the associated parameter combinations of the ship diesel engine are identified based on the parameter types and the correlation coefficients, and the key monitoring parameters in the associated parameter combinations are extracted. The key monitoring parameters are analyzed in a time series to obtain the time series analysis results, so that the operation data of the diesel engine in different time periods can be obtained, and the key parameters that have the greatest impact on the operation status of the diesel engine can be identified, so that the complexity of the monitoring system can be reduced, and the focus can be placed on monitoring the most important parameters. By analyzing the trends and patterns of the key monitoring parameters of the ship diesel engine over time, the future behavior of the diesel engine can be predicted, and the problems of the diesel engine can be diagnosed. In addition, by analyzing the Analyze the change trend of the key monitoring parameter under the time series analysis result, set the normal threshold of the change trend, and identify the abnormal parameter of the key monitoring parameter according to the normal threshold, analyze the fault symptom of the ship diesel engine based on the abnormal parameter, identify the fault type corresponding to the fault symptom, extract the fault parameter characteristics of the key monitoring parameter under the fault type, determine the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics, and predict the type and severity of the fault that may occur in the future, and send out early warning signals in time to remind operators to take measures in time to avoid the occurrence of faults or reduce the consequences of faults, thereby reducing the risk of accidents. Therefore, the risk of failure is reduced; further, based on the data monitoring equipment, the real-time operating parameters of the ship diesel engine are collected, the real-time key parameters in the real-time operating parameters are extracted, and the alarm threshold of the real-time key parameters is set. According to the alarm threshold, the real-time fault source of the ship diesel engine is located, and the potential fault source of the ship diesel engine is identified by combining the fault prediction model and the real-time key parameters. Based on the real-time fault source, the deviation index of the potential fault source is calculated. According to the deviation index, the adaptive mechanism of the fault prediction model is set, which can timely discover and locate the possible fault source, improve the prediction accuracy and adaptability of the model, and enable it to better cope with the changing working conditions and environmental conditions;By identifying the potential fault type of the ship diesel engine and analyzing the potential fault degree of the ship diesel engine, setting the fault diagnosis rules of the ship diesel engine according to the potential fault type and the potential fault degree, and setting the early warning mechanism of the fault diagnosis rules, combining the fault prediction model, the adaptive mechanism and the early warning mechanism, and setting the visual interactive interface of the ship diesel engine, the actual problems of the diesel engine can be accurately diagnosed, misjudgment and missed judgment can be reduced, and the reliability and life of the ship diesel engine can be improved. An intuitive and efficient monitoring and management platform is provided, so that operators can understand the status of the diesel engine in real time, so as to take corresponding preventive measures in time and improve the operating efficiency and health of the ship diesel engine. Therefore, the ship diesel engine monitoring and early warning method based on data processing proposed in the present invention can predict the failure risk of the ship diesel engine in advance, make corresponding adjustments, and improve the safety of ship navigation. ; BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0019] Figure 1 A schematic diagram of a process flow of a marine diesel engine monitoring and early warning method based on data processing provided by an embodiment of the present invention; Figure 2 A module schematic diagram of a ship diesel engine monitoring and early warning system based on data processing provided by one embodiment of the present invention. DETAILED DESCRIPTION
[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0021] The embodiment of the present invention provides a ship diesel engine monitoring and early warning method based on data processing. The execution subject of the ship diesel engine monitoring and early warning method based on data processing includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the ship diesel engine monitoring and early warning method based on data processing can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.
[0022] See also Figure 1 FIG. 1 is a flow chart of a method for monitoring and early warning of a marine diesel engine based on data processing provided by an embodiment of the present invention. Figure 1 The marine diesel engine monitoring and early warning method based on data processing described in the invention includes: S1. Obtain the ship diesel engine to be monitored and its corresponding output device, analyze the data transmission path of the output device, identify the data transmission port of the data transmission path, set the data sensing node of the data transmission port, and set the data processing interface of the data sensing node, and configure the data monitoring equipment of the ship diesel engine in combination with the data transmission port, the data sensing node and the data processing interface.
[0023] By acquiring the ship diesel engine to be monitored and its corresponding output device, the embodiment of the present invention can better plan and allocate resources for monitoring, ensure that the monitoring covers all diesel engines and their output devices that need to be paid attention to, and help to ensure the integrity and accuracy of the collected data. The ship diesel engine refers to the core mechanical equipment installed on the ship as a propulsion power, usually a large low-speed two-stroke or multi-stroke diesel engine, and the output device refers to a device directly associated with the diesel engine and used to output power or signals, such as a combustion chamber.
[0024] Optionally, the ship diesel engine to be monitored and its corresponding output device may be obtained by using the manufacturer's manual.
[0025] Furthermore, the embodiment of the present invention can identify the key nodes from the sensor to the central processing system by analyzing the data propagation path of the output device, thereby optimizing the layout of the monitoring equipment. The data propagation path refers to the transmission route from the data collected by various sensors on the diesel engine to the final data processing and analysis system.
[0026] As an embodiment of the present invention, analyzing the data propagation path of the output device includes: identifying the output parameters of the output device; analyzing parameter attributes of the output parameters, and identifying the output mode of the output parameters based on the parameter attributes; based on the output mode, analyzing the transmission link of the output parameters, and determining the communication mode of the transmission link; identifying the output result of the output parameter based on the transmission link and the communication mode; and analyzing the data propagation path of the output device in combination with the output mode and the output result.
[0027] Among them, the output parameters refer to the data parameters collected by sensors or other monitoring equipment during the operation of the ship diesel engine, the output method refers to the carrier type of the output data parameters, such as sensors, the parameter attributes refer to the nature or type of the output parameters, the transmission link refers to the transmission path of the parameters from the sensor to the display or recording device, such as cables, wireless signals or other communication means, the communication method refers to the method of data transmission in the transmission link, such as analog signals, digital signals, wired communications or wireless communications, and the output result refers to the result of the output parameters after processing and analysis.
[0028] Optionally, according to the parameter type, the output mode identification of the output parameter can be obtained through a sensor device, based on the output mode, the transmission link analysis of the output parameter can be achieved by wireless communication means, the communication mode determination of the transmission link can be obtained through a data transmission protocol, and according to the transmission link and the communication mode, the output result identification of the output parameter can be achieved by data flow simulation.
[0029] The embodiment of the present invention can identify the data transmission port of the data propagation path and set appropriate monitoring equipment according to the output parameter type of the data transmission port, thereby improving the monitoring quality of the ship diesel engine. The data transmission port refers to the physical interface connecting the sensor or other data acquisition device with the central processing unit or the network, such as the digital signal port.
[0030] Optionally, the data transmission port identification of the data propagation path can be obtained through a programming tool, such as a Python tool.
[0031] Furthermore, the embodiment of the present invention can effectively configure the data monitoring equipment of the ship diesel engine by setting the data sensing node of the data transmission port and setting the data processing interface of the data sensing node, thereby ensuring that the operating status of the diesel engine is effectively monitored, and problems are discovered and solved in time, thereby improving the reliability and working efficiency of the diesel engine. The data sensing node refers to a sensor or data acquisition device installed on the ship diesel engine, and the data processing interface refers to a component or system used to perform preliminary processing of data during the process of transmitting data from the data sensing node to the central processing system.
[0032] Optionally, the data sensing node setting of the data transmission port can be acquired through a data acquisition module and a wireless sensor network node, and the data processing interface setting of the data sensing node can be implemented using a central processing unit of a ship diesel engine.
[0033] The embodiment of the present invention configures the data monitoring device of the ship diesel engine by combining the data transmission port, the data sensing node and the data processing interface, so as to build an efficient and reliable ship diesel engine monitoring system, and can collect, transmit, process and analyze the operating data of the diesel engine in real time, ensure that the operating status of the diesel engine is fully monitored, so as to timely discover and prevent potential problems and improve the reliability and efficiency of the diesel engine. The data monitoring device refers to a series of hardware and software components used to monitor the operating status of the diesel engine in real time, such as vibration sensors, pressure sensors and temperature sensors.
[0034] S2. Query the historical operating parameters of the ship diesel engine, identify the parameter types of the historical operating parameters, calculate the correlation coefficients between the parameter types, identify the associated parameter combinations of the ship diesel engine based on the parameter types and the correlation coefficients, extract the key monitoring parameters in the associated parameter combinations, perform time series analysis on the key monitoring parameters, and obtain time series analysis results.
[0035] The embodiment of the present invention can obtain the operating data of the diesel engine in different time periods and verify the accuracy and consistency of the current monitoring data by querying the historical operating parameters of the ship diesel engine and identifying the parameter types of the historical operating parameters. At the same time, by identifying the types of historical operating parameters, different types of data can be classified and managed to facilitate subsequent data processing and analysis. The historical operating parameters refer to the operating data recorded by the ship diesel engine in the past period of time, and the parameter type refers to the category after the historical operating parameters are classified.
[0036] Optionally, the historical operating condition parameter query of the ship diesel engine can be implemented using the historical data of the ship diesel engine operation, and the parameter type identification of the historical operating condition parameter can be obtained by setting the metadata field of the ship diesel engine operation parameter in the database.
[0037] Furthermore, the embodiment of the present invention can reveal the strength and direction of the linear relationship between different parameters by calculating the correlation coefficient between the parameter types, thereby helping the system to identify specific failure modes. The correlation coefficient refers to a statistic used to measure the strength and direction of the linear relationship between two variables.
[0038] In an optional embodiment of the present invention, the correlation coefficient between the parameter types is calculated using the following formula: ; Among them, R represents the correlation coefficient between parameter types, represents the jth sample in the parameter variable w, represents the average value of all samples in the parameter variable w, represents the jth sample in the parameter variable v, represents the average value of all samples in the parameter variable v, m represents the total number of parameter types, and j represents the index number of the sample in the parameter.
[0039] The embodiment of the present invention can identify the key parameters that have the greatest impact on the operating state of the diesel engine by identifying the associated parameter combination of the ship diesel engine based on the parameter type and the correlation coefficient. After determining the key parameters, the complexity of the monitoring system can be reduced and focus can be placed on monitoring the most important parameters, thereby improving the efficiency and reliability of the system. The associated parameter combination refers to a group of parameters that are interrelated and jointly affect the operating state of the diesel engine.
[0040] Optionally, based on the parameter type and the correlation coefficient, the identification of the associated parameter combination of the ship diesel engine can be obtained by a statistical analysis tool, such as an SPSS tool.
[0041] Furthermore, the embodiment of the present invention can simplify the entire monitoring system and reduce unnecessary data collection and processing by extracting key monitoring parameters from the associated parameter combination, and by monitoring these key parameters, potential faults can be discovered earlier and the accuracy of fault diagnosis can be improved. The key monitoring parameters refer to parameters that have an important impact on fault diagnosis, performance evaluation and maintenance decisions during the operation of the diesel engine, such as temperature parameters, vibration parameters and pressure parameters.
[0042] As an embodiment of the present invention, extracting the key monitoring parameters in the associated parameter combination includes: identifying the combination type in the associated parameter combination; based on the associated parameter combination, identifying the parameter type of the combination type; calculating the contribution rate corresponding to the parameter type in the associated parameter combination; and extracting the key monitoring parameters in the associated parameter combination based on the contribution rate.
[0043] The combination type refers to the classification of different parameter combinations, and the contribution rate refers to an indicator for measuring the role of a certain parameter in the associated parameter combination.
[0044] Optionally, the combination type identification in the associated parameter combination may be implemented by using model training. For example, in a decision tree model, different parameter combinations may be classified into different categories.
[0045] In an optional embodiment of the present invention, the contribution rate of the parameter type in the associated parameter combination is calculated using the following formula: ; in, represents the contribution rate of the ith parameter type in the associated parameter combination, n represents the total number of evaluation indicators of the parameter type, A represents all parameter types, Indicates the evaluation result value of the i-th parameter type in the q-th evaluation among all parameter types. It represents the total value of the evaluation results of all parameter types in the qth evaluation, q represents the evaluation index of the parameter type, and i represents the index of the parameter type.
[0046] The embodiment of the present invention performs time series analysis on the key monitoring parameters to obtain time series analysis results. By analyzing the trend and pattern of the key monitoring parameters of the ship diesel engine changing over time, the future behavior of the diesel engine can be predicted and problems with the diesel engine can be diagnosed. The time series analysis results refer to the trend results of the key monitoring parameters changing over time.
[0047] Optionally, the time series analysis of the key monitoring parameters can be implemented using Python's time series analysis tools, such as Statsmodels tools.
[0048] S3. Analyze the change trend of the key monitoring parameter under the time series analysis result, set a normal threshold of the change trend, and identify the abnormal parameters of the key monitoring parameter based on the normal threshold, analyze the fault symptoms of the ship diesel engine based on the abnormal parameters, identify the fault type corresponding to the fault symptoms, extract the fault parameter characteristics of the key monitoring parameter under the fault type, and determine the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics.
[0049] The embodiment of the present invention can more easily identify abnormal values or abnormal behaviors of parameters and identify specific patterns or periodic behaviors by analyzing the changing trends of the key monitoring parameters under the time series analysis results. The changing trends refer to the direction and patterns of the development of the key monitoring parameters over time.
[0050] Optionally, the change trend analysis of the key monitoring parameters under the time series analysis result can be implemented by using a time series decomposition method, such as an STL decomposition method.
[0051] Furthermore, the embodiment of the present invention sets a normal threshold value of the change trend and identifies the abnormal parameters of the key monitoring parameters based on the normal threshold value, so as to provide early warning of possible failures of the ship diesel engine, ensure that the system operates within a safe range, and prevent safety accidents caused by abnormal parameters. The normal threshold value refers to the limit threshold value for judging whether the key monitoring parameter exceeds the normal operating range, and the abnormal parameter refers to the abnormal parameter of the key monitoring parameter deviating from the normal operating range, such as the excessively high temperature of the ship diesel engine.
[0052] Optionally, the normal threshold setting of the change trend can be obtained by calculating the average value of the key monitoring parameters.
[0053] As an embodiment of the present invention, according to the normal threshold, the abnormal parameters of the key monitoring parameters are identified, including: locating the parameter output device of the key monitoring parameter; based on the parameter output device, identifying the parameter type of the key monitoring parameter; analyzing the current operating conditions of the parameter output device; according to the normal threshold and the current operating conditions, identifying the acceptable abnormal range of the parameter type; based on the normal threshold and the acceptable abnormal range, setting the abnormal standard of the key monitoring parameter; based on the abnormal standard, identifying the abnormal parameters of the key monitoring parameter.
[0054] Among them, the parameter output device refers to a device that can measure and output key monitoring parameters, the current operating conditions refer to the working status of the parameter output device at a specific moment, including environmental factors, load conditions, operating modes, etc., the acceptable variation range refers to the allowable fluctuation range of the key monitoring parameters without affecting the normal operation of the equipment, and the variation standard refers to the standard used to determine whether the key monitoring parameters have undergone abnormal changes.
[0055] Optionally, the current operating condition analysis of the parameter output device can be obtained through the log records of the ship diesel engine operation, and based on the normal threshold and the current operating conditions, the identification of the acceptable abnormal range of the parameter type can be achieved using the risk assessment results of the abnormal parameters.
[0056] The embodiment of the present invention can improve the safety of the ship diesel engine system and avoid unexpected shutdowns or safety accidents caused by failures by analyzing the failure signs of the ship diesel engine based on the abnormal parameters. The failure signs refer to abnormal signals or symptoms that appear before the ship diesel engine failure occurs, such as severe vibration of the diesel engine when it is working.
[0057] As an embodiment of the present invention, based on the abnormal parameters, the fault signs of the ship diesel engine are analyzed, including: analyzing the influencing factors of the abnormal parameters; based on the influencing factors, identifying the abnormal range of the abnormal parameters; according to the abnormal range, analyzing the operation trajectory of the ship diesel engine; analyzing the risk state of the ship diesel engine under the operation trajectory; according to the risk state, analyzing the fault signs of the ship diesel engine.
[0058] Among them, the influencing factors refer to various internal and external reasons that cause the abnormal parameters to deviate from the normal range, the abnormal range refers to the degree or interval of the abnormal parameters deviating from the normal value, the operating trajectory refers to the operating status and development trend of the abnormal parameters of the diesel engine during the abnormal process, and the risk status refers to the operating status of the ship diesel engine during the abnormal process.
[0059] Optionally, the analysis of influencing factors of the abnormal parameters can be obtained by analyzing data such as maintenance records, operation logs, and environmental condition records of the diesel engine. The identification of the abnormal range of the abnormal parameters based on the influencing factors can be achieved by determining the abnormal interval of the parameters through statistical analysis. The risk status analysis of the ship diesel engine under the operating trajectory can be obtained through a comprehensive analysis of the risk assessment model combined with the range of the abnormal parameters and historical fault data.
[0060] Furthermore, the embodiments of the present invention can detect potential problems of the diesel engine early and accurately locate the cause of the fault by identifying the fault type corresponding to the fault symptom, thereby guiding maintenance personnel to troubleshoot and repair the fault more quickly. The fault type refers to the specific problem category that may occur in the diesel engine, such as electrical fault, mechanical fault, etc.
[0061] As an embodiment of the present invention, identifying the fault type corresponding to the fault symptom includes: identifying the manifestation form of the fault symptom; extracting the equipment operation data corresponding to the fault symptom based on the manifestation form; identifying the abnormal components of the equipment operation data, and analyzing the influence scope of the fault symptom based on the abnormal components; analyzing the influence factors of the abnormal components, and locating the output source of the abnormal components based on the influence factors; and identifying the fault type corresponding to the fault symptom in combination with the manifestation form, the influence scope and the output source.
[0062] Among them, the manifestation form refers to the specific abnormal phenomenon or symptoms exhibited by the diesel engine before the failure occurs, the equipment operation data refers to the various monitoring data generated by the diesel engine during operation, such as temperature, pressure, vibration, fuel consumption, etc., the abnormal component refers to the specific data parameters or characteristics in the equipment operation data that deviate from the normal range, the impact range refers to the degree and scope of influence of the abnormal component on the overall operation of the diesel engine, the influencing factor refers to the specific cause or factor that causes the abnormal component to appear, and the output source refers to the specific source of the abnormal component.
[0063] Optionally, the identification of the manifestation of the fault signs can be obtained by real-time data collection by sensors installed on the diesel engine, and the identification of abnormal components in the equipment operation data can be achieved by identifying abnormal data points using statistical analysis methods, such as standard deviation statistics. Based on the influencing factors, the output source of the abnormal component can be located by identifying the abnormal source through a fault location tool, such as a fault diagnosis system.
[0064] The embodiment of the present invention extracts the fault parameter characteristics of the key monitoring parameters under the fault type, and can predict possible future problems based on the fault parameter characteristics and historical data, and perform maintenance in advance. By analyzing the key monitoring fault parameter characteristics, improper operations can be discovered, thereby optimizing the operating process and improving the stability and efficiency of the system. The fault parameter characteristics refer to the specific features exhibited by the key monitoring parameters under a fault state.
[0065] Optionally, the fault parameter characteristic extraction of the key monitoring parameter under the fault type can be implemented using TensorFlow.
[0066] Furthermore, the embodiment of the present invention determines the fault prediction model of the ship diesel engine based on the fault type and the fault parameter characteristics, so as to predict the type and severity of faults that may occur in the future, and promptly issue early warning signals to remind operators to take timely measures to avoid the occurrence of faults or mitigate the consequences of faults and reduce the risk of accidents. The fault prediction model refers to a model used to predict the possibility of diesel engine failures.
[0067] As an embodiment of the present invention, based on the time series analysis results and the fault parameter characteristics, a fault prediction model of the ship diesel engine is determined, including: based on the time series analysis results, extracting historical operation data of the ship diesel engine, and extracting historical parameter characteristics of the historical operation data; identifying the feature levels of the historical parameter characteristics and the fault parameter characteristics; according to the feature levels and the fault parameter characteristics, identifying related features of the historical parameter characteristics; performing dimensionality reduction processing on the related features to obtain a target fault feature set; based on the time series analysis results and the target fault feature set, determining a fault prediction network of the ship diesel engine; based on the historical operation data and the target fault feature set, performing prediction training on the fault prediction network to obtain a prediction result; and determining the fault prediction model of the ship diesel engine according to the fault prediction network and the prediction result.
[0068] Among them, the historical operation data refers to the operation data of the ship diesel engine in the past period of time, including records of various monitoring parameters; the historical parameter features refer to specific features extracted from the historical operation data, such as mean, standard deviation, maximum value, minimum value, trend, etc.; the feature level refers to the correspondence and importance between the historical parameter features and the fault parameter characteristics; the relevant features refer to features that are highly correlated with the fault parameter characteristics; the target fault feature set refers to a set of relevant features after dimensionality reduction processing; the fault prediction network refers to a neural network model constructed based on the time series analysis results and the target fault feature set; the prediction result refers to the prediction result obtained by the trained fault prediction network, such as fault probability or fault type.
[0069] Optionally, the historical parameter feature extraction of the historical operation data can be implemented using the convolution layer of a neural network model, the feature level identification of the historical parameter features and the fault parameter characteristics can be achieved through a feature matching method to identify the correspondence between the historical parameter features and the fault parameter characteristics, and based on the feature level and the fault parameter characteristics, the relevant feature identification of the historical parameter features can be achieved using a feature selection method, such as a recursive feature elimination method, and the dimensionality reduction processing of the relevant features can be obtained through a dimensionality reduction method, such as principal component analysis PCA, and the determination of the fault prediction network of the ship diesel engine based on the time series analysis results and the target fault feature set can be achieved using a neural network.
[0070] S4. Based on the data monitoring equipment, the real-time operating parameters of the ship diesel engine are collected, the real-time key parameters in the real-time operating parameters are extracted, and the alarm threshold of the real-time key parameters is set. According to the alarm threshold, the real-time fault source of the ship diesel engine is located. In combination with the fault prediction model and the real-time key parameters, the potential fault source of the ship diesel engine is identified. Based on the real-time fault source, the deviation index of the potential fault source is calculated. According to the deviation index, the adaptive mechanism of the fault prediction model is set.
[0071] The embodiment of the present invention collects the real-time operating parameters of the ship diesel engine based on the data monitoring device, so as to understand the current state of the diesel engine in real time, and timely discover the abnormal situation of the ship diesel engine in combination with historical data analysis. The real-time operating parameters refer to the various monitoring data collected in real time during the current operation of the diesel engine.
[0072] Furthermore, the embodiment of the present invention can monitor in real time and promptly discover potential faults by extracting real-time key parameters from the real-time working parameters and setting alarm thresholds for the real-time key parameters, thereby taking preventive measures to ensure the safe and stable operation of the ship diesel engine. The real-time key parameters refer to monitoring data that are collected in real time during the operation of the diesel engine and are critical to the system performance. The alarm threshold refers to a specific value set to determine whether the real-time key parameters exceed the normal range.
[0073] Optionally, the alarm threshold setting of the real-time key parameter can be obtained by determining a reasonable threshold range through historical data.
[0074] The embodiment of the present invention locates the real-time fault source of the ship diesel engine according to the alarm threshold, so as to timely discover and locate the possible source of the fault, thereby taking effective preventive and corrective measures. The real-time fault source refers to a potential problem area that is identified during the operation of the diesel engine because certain parameters exceed the predetermined alarm threshold.
[0075] As an embodiment of the present invention, the real-time fault source of the ship diesel engine is located according to the alarm threshold, including: identifying the alarm type of the ship diesel engine according to the alarm threshold; querying the parameter type corresponding to the alarm type; analyzing the alarm cause of the ship diesel engine based on the parameter type; and locating the real-time fault source of the ship diesel engine according to the parameter type and the alarm cause.
[0076] Among them, the alarm type refers to the specific category of alarm triggered according to the alarm threshold setting, such as overheating alarm, overpressure alarm, low oil pressure alarm, etc. The parameter type refers to the various parameter categories monitored during the operation of the ship diesel engine, such as temperature, pressure, speed, oil level, etc. The alarm cause refers to the specific cause that causes the occurrence of a specific alarm type.
[0077] Optionally, according to the alarm threshold, the alarm type identification of the ship diesel engine can be obtained by recording and querying the alarm type through the alarm log system, and the alarm cause analysis of the ship diesel engine based on the parameter type can be achieved using fault tree analysis.
[0078] Furthermore, the embodiment of the present invention identifies the potential fault source of the ship diesel engine by combining the fault prediction model and the real-time key parameters, and can compare and analyze the potential fault source with the real-time fault source to verify the prediction accuracy of the predicted fault model. The potential fault source refers to the possible diesel engine fault problem predicted by the fault prediction model based on the real-time operating parameters of the ship diesel engine.
[0079] As an embodiment of the present invention, the method of combining the fault prediction model and the real-time key parameters to identify the potential fault source of the ship diesel engine includes: inputting the real-time key parameters into the fault prediction model and extracting parameter characteristics of the real-time key parameters; identifying the time series change trend of the parameter characteristics; based on the time series change trend, identifying the dynamic characteristics of the real-time key parameters; determining the fault type of the ship diesel engine according to the dynamic characteristics and the time series change trend; and identifying the potential fault source of the ship diesel engine according to the fault probability and the fault type.
[0080] Among them, the parameter characteristics refer to the specific characteristics extracted from the real-time operation data of the ship diesel engine, the time series change trend refers to the pattern of the parameter characteristics changing over time, and the dynamic characteristics refer to the various characteristics and behaviors in the time series data of the parameter characteristics that change over time, including trends, periodicity, mutation points and other time dependencies in the time series data of the parameter characteristics.
[0081] Optionally, based on the time series change trend, the dynamic characteristic identification of the real-time key parameter can be obtained by utilizing the Bidirectional GRU layer of the fault prediction model.
[0082] The embodiment of the present invention calculates the deviation index of the potential fault source based on the real-time fault source, so as to quantify the difference between the potential fault source and the normal operating state, so as to better understand and evaluate the health status of the ship diesel engine. The deviation index refers to an indicator used to quantify the fault detection model's prediction of the operating state of the ship diesel engine.
[0083] In an optional embodiment of the present invention, based on the real-time fault source, the deviation index of the potential fault source is calculated using the following formula: ; in, Deviation index representing potential sources of failure, Indicates the result value of the lth detection parameter in the potential fault source, represents the average value of the detection parameter in the potential fault source, l represents the index of the detection parameter in the potential fault source, It represents the deviation between the result value of each detection parameter in the potential fault source and the average value, and h represents the total number of detection parameters in the potential fault source.
[0084] Furthermore, the embodiment of the present invention can improve the prediction accuracy and adaptability of the model by setting an adaptive mechanism of the fault prediction model according to the deviation index, so that it can better cope with changing working conditions and environmental conditions. The adaptive mechanism refers to a mechanism that enables the fault prediction model to automatically adjust its parameters and behaviors according to real-time data and environmental changes.
[0085] As an embodiment of the present invention, an adaptive mechanism of the fault prediction model is set according to the deviation index, including: identifying the prediction deviation object of the fault prediction model according to the deviation index; locating the output position of the prediction deviation object and identifying the output type of the output position; extracting the normal output standard of the output type, and setting the dynamic adjustment range of the fault prediction model according to the normal output standard; and setting the adaptive mechanism of the fault prediction model based on the dynamic adjustment range.
[0086] Among them, the prediction deviation object refers to a specific object in the fault prediction model where the prediction result deviates greatly from the actual result, the output location refers to the source of the parameter object that produces the deviation in the fault prediction model, the output type refers to the specific type of the fault prediction model output, the normal output standard refers to the expected value or range of the fault prediction model output type under normal operating conditions, and the dynamic adjustment range refers to the normal output standard and the actual operating conditions, which is an acceptable prediction value adjustment range set for the fault prediction model.
[0087] Optionally, based on the deviation index, the prediction deviation object identification of the fault prediction model can be achieved by utilizing the output log of the fault prediction model, and based on the normal output standard, the dynamic adjustment range setting of the fault prediction model can be obtained through the control theory analysis results of the ship diesel engine operating status.
[0088] S5. Identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine. According to the potential fault type and the potential fault degree, set the fault diagnosis rules of the ship diesel engine and set the early warning mechanism of the fault diagnosis rules. Combine the fault prediction model, the adaptive mechanism and the early warning mechanism to set the visual interactive interface of the ship diesel engine.
[0089] The embodiment of the present invention can take measures in advance to perform preventive maintenance by identifying the potential fault type of the ship diesel engine and analyzing the potential fault degree of the ship diesel engine, thereby avoiding the occurrence of faults or reducing the impact of faults. The potential fault type refers to the category of faults that may occur or have risks during the operation of the ship diesel engine, and the potential fault degree refers to an assessment of the severity and urgency of the possible faults of the ship diesel engine.
[0090] Optionally, the identification of potential fault types of the ship diesel engine can be achieved by using a fault prediction model, and the analysis of the potential fault degree of the ship diesel engine can be achieved by risk assessment results of potential fault types.
[0091] Furthermore, the embodiment of the present invention sets the fault diagnosis rules of the ship diesel engine according to the potential fault type and the potential fault degree, so as to more accurately diagnose the actual problems of the diesel engine, reduce misjudgments and missed judgments, and improve the reliability and life of the ship diesel engine. The fault diagnosis rules refer to guiding rules that help identify possible faults of the ship diesel engine.
[0092] As an embodiment of the present invention, the fault diagnosis rules of the ship diesel engine are set according to the potential fault type and the potential fault degree, including: setting the fault level of the ship diesel engine according to the potential fault type and the potential fault degree; identifying the fault characteristics corresponding to the potential fault type; setting the fault handling method of the ship diesel engine based on the fault characteristics; defining the fault response sequence of the ship diesel engine according to the fault level; and setting the fault diagnosis rules of the ship diesel engine in combination with the fault response sequence and the fault handling method.
[0093] Among them, the fault level refers to the classification of faults into different levels according to the potential fault type and potential fault degree, the fault feature refers to the features or symptoms related to a specific fault type, the fault handling method refers to the formulation of specific handling methods or steps for each fault feature, and the fault response order refers to determining the priority order of handling the fault according to the level of the fault.
[0094] Optionally, the fault feature identification corresponding to the potential fault type can be achieved by analyzing historical fault records. According to the fault level, the fault response sequence definition of the ship diesel engine can be obtained by formulating a response sequence according to the severity of the fault level.
[0095] The embodiment of the present invention sets an early warning mechanism for the fault diagnosis rule according to the potential fault type and the potential fault degree, thereby ensuring that the fault can be discovered and measures can be taken in time before it occurs to prevent the fault from further deteriorating. The early warning mechanism refers to a system for real-time monitoring of the operating status of the diesel engine and timely issuing an alarm when signs of potential faults are detected.
[0096] Optionally, according to the potential fault type and the potential fault degree, the early warning mechanism setting of the fault diagnosis rule can utilize predefined rules to trigger early warning implementation, such as threshold rules.
[0097] Furthermore, the embodiment of the present invention sets a visual interactive interface for the ship diesel engine by combining the fault prediction model, the adaptive mechanism and the early warning mechanism, and can provide an intuitive and efficient monitoring and management platform, so that operators can understand the status of the diesel engine in real time and take corresponding preventive measures in time to improve the operating efficiency of the ship diesel engine. The visual interactive interface refers to a user interface that displays the operating status of the diesel engine, fault warning information, maintenance suggestions and other contents in a graphical manner.
[0098] Optionally, in combination with the fault prediction model, the adaptive mechanism and the early warning mechanism, the visualization interactive interface setting of the ship diesel engine can be obtained through a chart library, such as an ECharts chart library.
[0099] It can be seen that the present invention first obtains the ship diesel engine to be monitored and its corresponding output device, analyzes the data propagation path of the output device, identifies the data transmission port of the data propagation path, sets the data sensing node of the data transmission port, and sets the data processing interface of the data sensing node. In combination with the data transmission port, the data sensing node and the data processing interface, the data monitoring device of the ship diesel engine is configured, which can better plan and allocate resources for monitoring, ensure that the monitoring covers all diesel engines and their output devices that need to be paid attention to, help to ensure the integrity and accuracy of the collected data, and thus improve the monitoring quality of the ship diesel engine; further, query the history of the ship diesel engine The historical operating parameters are obtained by analyzing the parameter types of the historical operating parameters, calculating the correlation coefficients between the parameter types, identifying the associated parameter combination of the ship diesel engine based on the parameter types and the correlation coefficients, extracting the key monitoring parameters in the associated parameter combination, performing time series analysis on the key monitoring parameters, and obtaining the time series analysis results. The operation data of the diesel engine in different time periods can be obtained, and the key parameters that have the greatest impact on the operating status of the diesel engine can be identified, thereby reducing the complexity of the monitoring system and focusing on monitoring the most important parameters. By analyzing the trends and patterns of the key monitoring parameters of the ship diesel engine over time, the future behavior of the diesel engine can be predicted, and the problems of the diesel engine can be diagnosed. In addition, By analyzing the change trend of the key monitoring parameter under the time series analysis result, setting the normal threshold of the change trend, and identifying the abnormal parameter of the key monitoring parameter according to the normal threshold, analyzing the fault symptom of the ship diesel engine based on the abnormal parameter, identifying the fault type corresponding to the fault symptom, extracting the fault parameter characteristics of the key monitoring parameter under the fault type, and determining the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics, it is possible to predict the type and severity of the fault that may occur in the future, and issue a warning signal in time to remind the operator to take measures in time to avoid the occurrence of the fault or mitigate the consequences of the fault, thereby reducing Accident risk; further, based on the data monitoring equipment, the real-time operating parameters of the ship diesel engine are collected, the real-time key parameters in the real-time operating parameters are extracted, and the alarm threshold of the real-time key parameters is set. According to the alarm threshold, the real-time fault source of the ship diesel engine is located. In combination with the fault prediction model and the real-time key parameters, the potential fault source of the ship diesel engine is identified. Based on the real-time fault source, the deviation index of the potential fault source is calculated. According to the deviation index, the adaptive mechanism of the fault prediction model is set, which can timely discover and locate the possible fault source, improve the prediction accuracy and adaptability of the model, and enable it to better cope with the changing working conditions and environmental conditions;By identifying the potential fault type of the ship diesel engine and analyzing the potential fault degree of the ship diesel engine, setting the fault diagnosis rules of the ship diesel engine according to the potential fault type and the potential fault degree, and setting the early warning mechanism of the fault diagnosis rules, combining the fault prediction model, the adaptive mechanism and the early warning mechanism, and setting the visual interactive interface of the ship diesel engine, the actual problems of the diesel engine can be accurately diagnosed, misjudgment and missed judgment can be reduced, and the reliability and life of the ship diesel engine can be improved. An intuitive and efficient monitoring and management platform is provided, so that operators can understand the status of the diesel engine in real time, so as to take corresponding preventive measures in time and improve the operating efficiency and health of the ship diesel engine. Therefore, the ship diesel engine monitoring and early warning method based on data processing proposed in the present invention can predict the failure risk of the ship diesel engine in advance, make corresponding adjustments, and improve the safety of ship navigation. ;
[0100] like Figure 2 The figure shows a system functional module diagram of the marine diesel engine monitoring and early warning system based on data processing according to the present invention.
[0101] The marine diesel engine monitoring and early warning system 200 based on data processing of the present invention can be installed in an electronic device. According to the functions to be implemented, the marine diesel engine monitoring and early warning system based on data processing can include a data monitoring module 201, a key parameter extraction module 202, a fault prediction module 203, a fault adaptive module 204, and a result visualization module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0102] In the embodiment of the present invention, the functions of each module / unit are as follows: The data monitoring module 201 is used to obtain the ship diesel engine to be monitored and its corresponding output device, analyze the data propagation path of the output device, identify the data transmission port of the data propagation path, set the data sensing node of the data transmission port, and set the data processing interface of the data sensing node, and configure the data monitoring device of the ship diesel engine in combination with the data transmission port, the data sensing node and the data processing interface; The key parameter extraction module 202 is used to query the historical operating parameters of the ship diesel engine, identify the parameter types of the historical operating parameters, calculate the correlation coefficients between the parameter types, identify the associated parameter combinations of the ship diesel engine based on the parameter types and the correlation coefficients, extract the key monitoring parameters in the associated parameter combinations, perform time series analysis on the key monitoring parameters, and obtain time series analysis results; The fault prediction module 203 is used to analyze the change trend of the key monitoring parameter under the time series analysis result, set a normal threshold value of the change trend, and identify the abnormal parameter of the key monitoring parameter according to the normal threshold value, analyze the fault symptom of the ship diesel engine based on the abnormal parameter, identify the fault type corresponding to the fault symptom, extract the fault parameter characteristics of the key monitoring parameter under the fault type, and determine the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics; A fault adaptive module 204 is used to collect the real-time operating parameters of the ship diesel engine based on the data monitoring device, extract the real-time key parameters in the real-time operating parameters, and set the alarm threshold of the real-time key parameters, locate the real-time fault source of the ship diesel engine according to the alarm threshold, identify the potential fault source of the ship diesel engine in combination with the fault prediction model and the real-time key parameters, calculate the deviation index of the potential fault source based on the real-time fault source, and set the adaptive mechanism of the fault prediction model according to the deviation index; The result visualization module 205 is used to identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine. According to the potential fault type and the potential fault degree, the fault diagnosis rules of the ship diesel engine are set, and the early warning mechanism of the fault diagnosis rules is set. In combination with the fault prediction model, the adaptive mechanism and the early warning mechanism, a visualization interactive interface of the ship diesel engine is set.
[0103] In detail, each module in the marine diesel engine monitoring and early warning system 200 based on data processing in the embodiment of the present invention is used in the same manner as described above. Figure 1 The method for monitoring and early warning of ship diesel engines based on data processing is the same technical means as described in the text and can produce the same technical effects, so it will not be repeated here.
[0104] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0105] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0106] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0107] It should be noted that, in this article, relational terms such as "first" and "second" 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.
[0108] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A marine diesel engine monitoring and early warning method based on data processing, characterized in that: The method comprises: Acquire a ship diesel engine to be monitored and its corresponding output device, analyze the data propagation path of the output device, identify the data transmission port of the data propagation path, set a data sensing node of the data transmission port, and set a data processing interface of the data sensing node, and configure the data monitoring device of the ship diesel engine in combination with the data transmission port, the data sensing node and the data processing interface; querying historical operating parameters of the ship diesel engine, identifying parameter types of the historical operating parameters, calculating correlation coefficients between the parameter types, identifying associated parameter combinations of the ship diesel engine based on the parameter types and the correlation coefficients, extracting key monitoring parameters from the associated parameter combinations, performing time series analysis on the key monitoring parameters, and obtaining time series analysis results; Analyze the change trend of the key monitoring parameter under the time series analysis result, set a normal threshold value of the change trend, and identify the abnormal parameter of the key monitoring parameter according to the normal threshold value, analyze the fault symptom of the ship diesel engine based on the abnormal parameter, identify the fault type corresponding to the fault symptom, extract the fault parameter characteristics of the key monitoring parameter under the fault type, and determine the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics; Based on the data monitoring device, real-time operating parameters of the ship diesel engine are collected, real-time key parameters in the real-time operating parameters are extracted, and alarm thresholds of the real-time key parameters are set; according to the alarm thresholds, the real-time fault source of the ship diesel engine is located; in combination with the fault prediction model and the real-time key parameters, the potential fault source of the ship diesel engine is identified; based on the real-time fault source, the deviation index of the potential fault source is calculated; and according to the deviation index, an adaptive mechanism of the fault prediction model is set; Identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine; set the fault diagnosis rules of the ship diesel engine according to the potential fault type and the potential fault degree; set the early warning mechanism of the fault diagnosis rules; combine the fault prediction model, the adaptive mechanism and the early warning mechanism to set the visual interactive interface of the ship diesel engine.
2. The method according to claim 1, characterized in that Analyzing the data propagation path of the output device, including: identifying output parameters of the output device; Analyzing parameter attributes of the output parameter, and identifying an output mode of the output parameter according to the parameter attributes; Based on the output mode, analyzing the transmission link of the output parameter and determining the communication mode of the transmission link; identifying an output result of the output parameter according to the transmission link and the communication mode; In combination with the output method and the output result, the data propagation path of the output device is analyzed.
3. The method according to claim 1, characterized in that Extracting key monitoring parameters from the associated parameter combination includes: Identifying a combination type in the associated parameter combination; Based on the associated parameter combination, identifying a parameter type of the combination type; The contribution rate of the parameter type in the associated parameter combination is calculated using the following formula: ; in, represents the contribution rate of the ith parameter type in the associated parameter combination, n represents the total number of evaluation indicators of the parameter type, A represents all parameter types, Indicates the evaluation result value of the i-th parameter type in the q-th evaluation among all parameter types. Represents the total value of the evaluation results of all parameter types in the qth evaluation, q represents the evaluation index of the parameter type, and i represents the index of the parameter type; According to the contribution rate, key monitoring parameters in the associated parameter combination are extracted.
4. The method according to claim 1, characterized in that According to the normal threshold, identifying the abnormal parameters of the key monitoring parameters includes: Locating a parameter output device of the key monitoring parameter; Based on the parameter output device, identifying the parameter type of the key monitoring parameter; analyzing the current operating conditions of the parameter output device; Identifying an acceptable variation range of the parameter type according to the normal threshold and the current operating condition; Based on the normal threshold and the acceptable abnormal variation range, setting the abnormal variation standard of the key monitoring parameter; Based on the abnormality standard, the abnormality parameters of the key monitoring parameters are identified.
5. The method according to claim 1, characterized in that Identify the fault type corresponding to the fault symptom, including: Identify the manifestations of the fault symptoms; Extracting equipment operation data corresponding to the fault symptom according to the manifestation form; Identify abnormal components of the equipment operation data, and analyze the impact scope of the fault symptom based on the abnormal components; Analyzing the influencing factors of the abnormal components, and locating the output sources of the abnormal components according to the influencing factors; The fault type corresponding to the fault symptom is identified by combining the manifestation form, the impact scope and the output source.
6. The method according to claim 1, characterized in that Determining a fault prediction model of the marine diesel engine based on the time series analysis result and the fault parameter characteristics includes: Based on the time series analysis result, extracting historical operation data of the ship diesel engine, and extracting historical parameter features of the historical operation data; Identifying the characteristic levels of the historical parameter characteristics and the fault parameter characteristics; identifying relevant features of the historical parameter features according to the feature level and the fault parameter characteristics; Performing dimensionality reduction processing on the relevant features to obtain a target fault feature set; Determining a fault prediction network of the ship diesel engine based on the time series analysis result and the target fault feature set; Based on the historical operation data and the target fault feature set, performing prediction training on the fault prediction network to obtain a prediction result; A fault prediction model of the ship diesel engine is determined according to the fault prediction network and the prediction result.
7. The method according to claim 1, characterized in that According to the alarm threshold, locating the real-time fault source of the ship diesel engine includes: According to the alarm threshold, identifying the alarm type of the ship diesel engine; Query the parameter type corresponding to the alarm type; Analyzing the alarm cause of the ship diesel engine based on the parameter type; The real-time fault source of the ship diesel engine is located according to the parameter type and the alarm cause.
8. The method according to claim 1, identifying a potential fault source of the marine diesel engine, comprising: Inputting the real-time key parameters into the fault prediction model, and extracting parameter features of the real-time key parameters; Identifying a time series variation trend of the parameter characteristics; Based on the time series change trend, identifying the dynamic characteristics of the real-time key parameters; Determining the fault type of the ship diesel engine according to the dynamic characteristics and the time series change trend; According to the failure probability and the failure type, a potential failure source of the ship diesel engine is identified.
9. The method according to claim 1, characterized in that: According to the deviation index, an adaptive mechanism of the fault prediction model is set, including: According to the deviation index, identifying a prediction deviation object of the fault prediction model; Locating an output position of the prediction deviation object and identifying an output type of the output position; Extracting a normal output standard of the output type, and setting a dynamic adjustment range of the fault prediction model according to the normal output standard; Based on the dynamic adjustment range, an adaptive mechanism of the fault prediction model is set.
10. A marine diesel engine monitoring and early warning system based on data processing, characterized in that: The system comprises: A data monitoring module, used to obtain a marine diesel engine to be monitored and its corresponding output device, analyze a data propagation path of the output device, identify a data transmission port of the data propagation path, set a data sensing node of the data transmission port, and set a data processing interface of the data sensing node, and configure a data monitoring device of the marine diesel engine in combination with the data transmission port, the data sensing node and the data processing interface; a key parameter extraction module, used to query the historical operating parameters of the marine diesel engine, identify the parameter types of the historical operating parameters, calculate the correlation coefficients between the parameter types, identify the associated parameter combinations of the marine diesel engine based on the parameter types and the correlation coefficients, extract the key monitoring parameters in the associated parameter combinations, perform time series analysis on the key monitoring parameters, and obtain time series analysis results; a fault prediction module, used for analyzing the change trend of the key monitoring parameter under the time series analysis result, setting a normal threshold value of the change trend, and identifying the abnormal parameter of the key monitoring parameter according to the normal threshold value, analyzing the fault symptom of the ship diesel engine based on the abnormal parameter, identifying the fault type corresponding to the fault symptom, extracting the fault parameter characteristics of the key monitoring parameter under the fault type, and determining the fault prediction model of the ship diesel engine based on the time series analysis result and the fault parameter characteristics; A fault adaptive module, used to collect the real-time operating parameters of the ship diesel engine based on the data monitoring device, extract the real-time key parameters in the real-time operating parameters, and set the alarm threshold of the real-time key parameters, locate the real-time fault source of the ship diesel engine according to the alarm threshold, identify the potential fault source of the ship diesel engine in combination with the fault prediction model and the real-time key parameters, calculate the deviation index of the potential fault source based on the real-time fault source, and set the adaptive mechanism of the fault prediction model according to the deviation index; The result visualization module is used to identify the potential fault type of the ship diesel engine and analyze the potential fault degree of the ship diesel engine. According to the potential fault type and the potential fault degree, the fault diagnosis rules of the ship diesel engine are set, and the early warning mechanism of the fault diagnosis rules is set. In combination with the fault prediction model, the adaptive mechanism and the early warning mechanism, a visualization interactive interface of the ship diesel engine is set.
Citation Information
Patent Citations
Intelligent ship engine room monitoring alarm system based on model
CN108008718A
Data-driven marine diesel engine fault detection method
CN111289256A
Marine engine room diagnosis method based on fault relation analysis
CN117784765A
Cited By
Safety monitoring system for marine LNG / diesel oil dual-fuel engine
CN120487372A
Ship power device fault detection method based on state matching
CN120492940A
Distributed fault prediction system of military ship control unit
CN120508083A
Diesel engine destructive damage monitoring and early warning method based on thermotechnical data driving
CN121207553A
Fault monitoring and alarming method and system for power equipment
CN121350710A
