Ship data exception management analysis method and system based on big data integration

Abstract

The invention relates to the technical field of intelligent monitoring, regulation and control of ship power systems, and particularly discloses a ship data anomaly management analysis method and system based on big data integration, and the method comprises the steps: collecting the exhaust temperature and rotating speed data in real time through installing a temperature sensor and a speed sensor on the surface of an engine; feature vectors are constructed based on an isolated forest algorithm, the abnormal conditions of the exhaust temperature and the rotating speed are accurately recognized, the abnormal state is quantified by calculating an abnormal coefficient, and the risk of misjudgment and missed judgment is remarkably reduced; according to the method, the influence relation model between the exhaust temperature and the rotating speed abnormity is established, the influence degree of the rotating speed abnormity on the exhaust temperature abnormity is evaluated, and real-time regulation and control within the target range are achieved accordingly; in the regulation and control process, the cooperative change of the exhaust temperature and the rotating speed is continuously monitored, regulation and control parameters are optimized, and the stability and safety of the operation state of the engine are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring and control of ship power systems, and in particular to a method and system for managing and analyzing ship data anomalies based on big data integration. Background Art

[0002] With the development of the global shipping industry, ship engines, as the core of the power system, have a direct impact on the economic benefits and navigation safety of ships due to their operational stability and safety. During long-term operation, ship engines are susceptible to factors such as temperature and load due to complex operating conditions and changing environments, leading to performance degradation or abnormal phenomena. In particular, exhaust temperature and speed are important indicators of engine operating status, reflecting key parameters such as combustion efficiency and mechanical wear. Real-time monitoring and abnormal management of these are key to ensuring the efficient operation of ship engines and extending their service life. However, traditional monitoring and management methods often rely on manual experience or simple fixed rules, which are difficult to adapt to the complexity of ship engine operation and the dynamically changing environmental requirements.

[0003] Deficiencies in existing technologies: Traditional anomaly detection methods mostly rely on fixed threshold judgments or simple statistical models. This approach makes it difficult to capture the complex nonlinear relationship between exhaust temperature and speed, and can easily lead to misjudgments and missed detections of anomalies. In addition, after identifying anomalies, existing methods often lack intelligent control methods and cannot effectively coordinate the dynamic relationship between exhaust temperature and speed, resulting in delayed anomaly processing and even secondary failures. At the same time, traditional methods do not pay enough attention to data preprocessing and model optimization, and are easily interfered with by noisy data and missing data, affecting the accuracy and real-time nature of the detection results. Existing technologies are deficient in the accuracy, intelligence, and adaptability of ship engine anomaly detection and control. There is an urgent need for an innovative solution that combines big data analysis and intelligent algorithms to achieve accurate detection and real-time control of engine abnormalities. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for ship data anomaly management and analysis based on big data integration to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The ship data anomaly management and analysis method based on big data integration includes the following steps: S1: A temperature sensor and a speed sensor are installed on the surface of the ship engine to collect exhaust temperature data and speed data of the ship engine in real time, and pre-process the collected exhaust temperature data and speed data; S2: Acquire exhaust temperature data of the engine within a monitoring period in a time series, calculate an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; S3: acquiring engine speed data within a monitoring period in a time series, analyzing the speed data, analyzing the speed fluctuation amplitude and response time, calculating the engine speed abnormality coefficient, and identifying whether the engine speed is abnormal based on the speed abnormality coefficient; S4: Analyze historical exhaust temperature data and speed data to establish an influence relationship model between exhaust temperature and speed abnormality, which is used to evaluate the impact of engine speed abnormality on exhaust temperature abnormality; S5: Based on the analysis results of the impact degree, the engine speed is adjusted in real time to ensure that the exhaust temperature returns to the normal range. The adjustment process continuously monitors the coordinated work of exhaust temperature and speed to ensure stable engine operation.

[0006] As a further solution of the present invention, the calculation of the exhaust temperature anomaly coefficient according to the degree of fluctuation of the exhaust temperature data specifically includes: Obtain exhaust temperature data set within the monitoring period; Calculate the mean, standard deviation, and rate of change of the exhaust temperature data set; The calculation expression of the change rate is: ; in, Represents each temperature data collection point, Indicates the The temperature value of each temperature data collection point, Indicates the The collection point and Temperature change rate of each sampling point; According to the rate of change of the exhaust temperature data set, the mean and standard deviation of the rate of change are calculated; Calculate the local fluctuation value of exhaust temperature, the calculation expression is: ; in, represents the sliding window size, Indicates the The local fluctuation value of each temperature data collection point; The mean value, standard deviation, mean value and standard deviation of the rate of change of the exhaust temperature data set and the local fluctuation value of the exhaust temperature are used to construct a multidimensional feature vector; The isolation forest algorithm is used to train the feature vector to generate multiple isolated trees and then calculate the anomaly score of each data point; Calculate the anomaly score for each data point based on the path length output by the isolation forest model The calculation expression of the abnormality score is: ; Where, Indicates the The abnormality score of each temperature data collection point, Indicates that the isolated tree The average isolated path length, represents the normalization factor; The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is: ; Where, Indicates the total number of exhaust temperature data collection points, Indicates the exhaust temperature abnormality coefficient.

[0007] As a further solution of the present invention, the method of identifying whether the engine speed is abnormal based on the speed abnormality coefficient specifically includes: The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed amplitude fluctuation is analyzed, and the speed amplitude fluctuation coefficient is calculated to evaluate the speed fluctuation degree; The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed response time is analyzed, and the response rate abnormality index is calculated to evaluate the abnormality of the engine speed response; The speed fluctuation degree and the speed response abnormality degree are comprehensively processed, including: normalizing the speed amplitude fluctuation coefficient and the response rate abnormality index, calculating the engine speed abnormality coefficient, comparing the speed abnormality coefficient with a preset threshold, and judging whether the speed abnormality coefficient is greater than or equal to the preset threshold. If so, the engine speed is abnormal; if not, the engine speed is normal.

[0008] As a further solution of the present invention: the process of obtaining the speed amplitude fluctuation coefficient is: Obtain engine speed data and pre-process the speed data; Standardize the processed speed data; Apply discrete wavelet transform to the standardized speed data, decompose the data into detail coefficients and approximation coefficients at multiple scales, use the wavelet basis and decomposition layer number, and obtain the high-frequency components of the speed data at each scale. The calculation expression is: ; Where, is the approximation coefficient, representing the low-frequency part, represents the number of detail coefficients, Indicates the detail coefficients, representing the high-frequency part, A data set representing the high-frequency components of the speed data at each scale; For each detail coefficient, calculate the corresponding amplitude: ; Where, Indicates the The amplitude of the detail coefficient, Indicates the maximum value of detail coefficient, Indicates the minimum value of detail coefficient; The fluctuation amplitudes corresponding to all detail coefficients are weighted averaged to obtain the overall speed amplitude fluctuation coefficient. The calculation expression is: ; in, Indicates the speed amplitude fluctuation coefficient, Indicates the total number of detail coefficients.

[0009] As a further solution of the present invention: the process of obtaining the response rate abnormality index is: By collecting the speed data of the ship engine in real time during the monitoring period, a time series is formed; Perform first-order difference processing on the speed data to obtain a differential data sequence; According to the differential speed data series, the autoregressive order, differential order and sliding average order are selected and the autoregressive integral sliding average model is constructed. The calculation expression is: ; Where, represents the autoregressive order, represents the sliding average order, Indicates the collection time point, Indicates the speed data after differentiation, represents the white noise term, represents the autoregressive coefficient, represents the sliding mean coefficient; The constructed autoregressive integral sliding average model is used to predict the speed at future moments and calculate the time The difference prediction value of , and combine the differential prediction value with the known collected speed data to obtain the speed prediction value. The calculation expression is: ; Where, Indicates the Speed ​​data, Indicates the Speed ​​data of each speed data; Calculate the error between the actual observed speed and the predicted speed. The calculation expression is: ; Where, Indicates the The error between the actual observed speed and the predicted speed at a certain moment All errors are counted and the mean of the errors is calculated and standard deviation ; Calculate the response rate abnormality index. The calculation expression is: ; Where, Indicates the response rate abnormality index, represents the standard deviation of the error, represents the mean of the errors.

[0010] As a further solution of the present invention, historical exhaust temperature data and speed data are analyzed to establish an influence relationship model between exhaust temperature and speed anomalies, specifically including: Based on the data distribution of historical exhaust temperature anomaly coefficients and speed anomaly coefficients, a Bayesian network is constructed, in which a conditional probability relationship exists between exhaust temperature anomaly coefficient nodes and speed anomaly coefficient nodes, and the relationship is used to describe the impact of speed anomaly on exhaust temperature anomaly; Based on historical data, a conditional probability distribution table of the exhaust temperature anomaly coefficient under different speed anomaly coefficient conditions is constructed and the marginal probability distribution of the speed anomaly coefficient is calculated; Calculate the joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient based on the conditional probability formula; The conditional probability formula is: ; Where, Indicates the exhaust temperature abnormality coefficient, Indicates the speed abnormality coefficient, represents the conditional probability distribution, represents the marginal probability distribution of abnormal speed; According to the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated. The calculation expression is: ; Where, It represents the influence relationship coefficient, represents the marginal probability of abnormal exhaust temperature, Indicates the probability of abnormal exhaust temperature under abnormal speed conditions; The influence relationship degree coefficient is used as the output of the influence relationship model to evaluate the influence degree of the abnormal speed on the abnormal exhaust temperature.

[0011] As a further solution of the present invention, the evaluation of the degree of influence of abnormal engine speed on abnormal exhaust temperature specifically includes: Determine whether the influence relationship coefficient is greater than or equal to a preset threshold. If so, the abnormal engine speed has an impact on the abnormal exhaust temperature, which is recorded as an influence signal. If not, the abnormal engine speed has no impact on the abnormal exhaust temperature, which is recorded as a non-influence signal.

[0012] As a further solution of the present invention, the method of ensuring that the exhaust temperature returns to a normal range by regulating the engine speed in real time based on the analysis result of the impact degree specifically includes: Based on the impact signal, the target normal range of the exhaust temperature and the target speed range that needs to be adjusted are determined according to the exhaust temperature abnormality coefficient and the impact relationship degree coefficient; The process of determining the target normal range of the exhaust temperature is as follows: Analyze the exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data; Calculate the target exhaust temperature range using the following expression: ; Where, The standard configuration is the target exhaust temperature range, represents the confidence coefficient, represents the mean value of the exhaust data, represents the standard deviation of the exhaust data; Based on the historical relationship between exhaust temperature and speed, a regression expression of exhaust temperature and speed is constructed: , and the corresponding speed target range is inversely solved according to the target exhaust temperature range. The calculation expression is: ; Where, Indicates the speed target range, Indicates the exhaust temperature, Indicates the rotation speed; Analyze historical speed fluctuation data, calculate the mean and standard deviation of the speed data, and calculate the correction target range. The calculation expression is: ; Where, represents the mean value of the speed data, represents the standard deviation of the speed data, Indicates the adjustment coefficient based on the historical data of speed fluctuations, Indicates the revised target range; According to the real-time monitored speed data and exhaust temperature data, the adjustment amount is calculated. The calculation expression is: ; Where, Indicates the adjustment amount, represents the control coefficient, Indicates real-time exhaust temperature data; Execute speed control to adjust the current engine speed. The calculation expression is: ; Where, Indicates the adjusted engine speed; During the speed control process, the coordinated changes of speed and exhaust temperature are monitored in real time, and the real-time response of the adjusted speed to the exhaust temperature is recorded to ensure that the exhaust temperature is stable within the target range; Optimize the control coefficient based on historical control data and actual adjustment effects.

[0013] The ship data anomaly management and analysis system based on big data integration includes: A data acquisition module, wherein the data acquisition module is used to collect exhaust temperature data and speed data of the ship engine in real time by installing a temperature sensor and a speed sensor on the surface of the ship engine; an exhaust temperature anomaly identification module, which acquires exhaust temperature data of the engine within a monitoring period in a time series, calculates an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; a speed anomaly identification module, which acquires engine speed data within a monitoring period in a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates an engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient; An impact relationship evaluation module, which analyzes historical exhaust temperature data and speed data to establish an impact relationship model between exhaust temperature and speed anomalies, and is used to evaluate the degree of impact of engine speed anomalies on exhaust temperature anomalies; A dynamic adjustment module ensures that the exhaust temperature returns to a normal range by adjusting the engine speed in real time based on the analysis results of the impact degree. The adjustment process continuously monitors the coordinated work of the exhaust temperature and speed to ensure stable engine operation.

[0014] Beneficial effects of the present invention: (1) The present invention collects high-precision exhaust temperature data and real-time speed data by precisely arranging temperature sensors and speed sensors on the surface of the ship engine, and performs multi-layer preprocessing on the collected data using the Kalman filter method, linear interpolation and normalization processing to ensure the integrity and consistency of the time series data. In the anomaly detection process, the isolation forest algorithm is used to take the multi-dimensional feature vector as input, accurately evaluate the anomaly score of each data point through the isolation tree model, and calculate the anomaly coefficient of the exhaust temperature and speed, quantifying the complex anomaly pattern into a numerical index with physical meaning, effectively improving the scientific nature and interpretability of anomaly detection. Compared with traditional monitoring methods that rely on manual experience or simple threshold rule judgment methods, the present invention has achieved optimization in terms of algorithm robustness, dynamic adaptability and real-time performance, and can accurately identify abnormal situations under complex working conditions, reducing the risk of misjudgment and missed judgment, and providing a scientific and reliable decision-making basis for real-time monitoring of engine operating status and subsequent intelligent regulation.

[0015] (2) The present invention not only accurately detects the abnormal state of the ship engine, but also reveals the complex influence relationship between abnormal exhaust temperature and abnormal speed by constructing a Bayesian network model based on historical data, quantifies the causal influence of abnormal speed on abnormal exhaust temperature, and forms a set of scientific abnormal correlation analysis methods. On this basis, according to the target exhaust temperature range and the target speed range, the engine speed is controlled in real time, combined with the regression relationship model of exhaust temperature and speed, to achieve dynamic adjustment of exhaust temperature. During the control process, the present invention continuously monitors the coordinated changes of speed and exhaust temperature, and optimizes the control coefficient through historical control data to ensure the accuracy and adaptability of the control. This closed-loop intelligent control strategy effectively alleviates the impact of abnormal conditions on engine operation, greatly improves the operating stability and safety of the engine, reduces energy consumption and economic losses, thereby comprehensively ensuring the efficient operation and economic benefits of the ship, and demonstrating the practical value and innovative advantages of the present invention under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 It is a flowchart of the specific steps of the ship data anomaly management and analysis method based on big data integration of the present invention; Figure 2 It is a flow chart of the ship data anomaly management and analysis system based on big data integration in the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making any creative efforts shall fall within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention is a ship data anomaly management and analysis method based on big data integration, comprising the following steps: S1: Temperature sensors and speed sensors are installed on the surface of the ship engine to collect real-time exhaust temperature and speed data from the ship engine. The collected exhaust temperature and speed data are pre-processed, including noise removal, missing data filling, and data format standardization to ensure data accuracy and consistency. S2: Acquire exhaust temperature data of the engine within a monitoring period in a time series, calculate an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; S3: acquiring engine speed data within a monitoring period in a time series, analyzing the speed data, analyzing the speed fluctuation amplitude and response time, calculating the engine speed abnormality coefficient, and identifying whether the engine speed is abnormal based on the speed abnormality coefficient; S4: Analyze historical exhaust temperature data and speed data to establish an influence relationship model between exhaust temperature and speed abnormality, which is used to evaluate the impact of engine speed abnormality on exhaust temperature abnormality; S5: Based on the analysis results of the impact degree, the engine speed is adjusted in real time to ensure that the exhaust temperature returns to the normal range. The adjustment process continuously monitors the coordinated work of exhaust temperature and speed to ensure stable engine operation.

[0020] In S1, temperature sensors and speed sensors are installed on the surface of the ship engine to collect the exhaust temperature and speed data of the ship engine in real time. The collected raw data is preprocessed, including removing noise, filling missing data and standardizing the data format to ensure the accuracy and consistency of the data. Specifically, the following steps are performed: Reasonably arrange temperature sensors and speed sensors on the surface of the ship engine to ensure the accuracy and coverage of data collection; The temperature sensor is installed near the engine exhaust port and uses a high-precision thermocouple or infrared temperature sensor to collect exhaust temperature and capture subtle temperature changes in real time; The speed sensor is installed on the engine main shaft or flywheel and uses a magnetoelectric or photoelectric sensor to record the real-time speed of the engine. During the acquisition process, the sensor transmits the collected raw data to the central data processing unit in real time through the integrated data bus, and records the data with a preliminary time stamp to ensure the time series integrity for subsequent analysis.

[0021] In order to improve the validity and consistency of the data, the collected raw data needs to undergo multiple layers of preprocessing. First, the Kalman filter method is used to remove random noise interference in the collected data; Secondly, to address the problem of missing data during the collection process, the linear interpolation method based on adjacent time windows is used to fill in the missing values ​​to ensure the continuity of time series data; Finally, the data from different sensors are standardized, the units and dimensions are unified, and converted into dimensionless data to ensure compatibility and accuracy in subsequent analysis.

[0022] In S2, exhaust temperature data of the engine within a monitoring period is acquired in a time series, an exhaust temperature anomaly coefficient is calculated based on the degree of fluctuation of the exhaust temperature data, and whether the exhaust temperature is abnormal is identified based on the exhaust temperature anomaly coefficient, specifically including: Obtain exhaust temperature data set within the monitoring period; Calculate the mean, standard deviation, and rate of change of the exhaust temperature data set; The calculation expression of the change rate is: ; in, Represents each temperature data collection point, Indicates the The temperature value of each temperature data collection point, Indicates the The collection point and Temperature change rate of each sampling point; According to the rate of change of the exhaust temperature data set, the mean and standard deviation of the rate of change are calculated; Calculate the local fluctuation value of exhaust temperature, the calculation expression is: ; in, represents the sliding window size, Indicates the The local fluctuation value of each temperature data collection point; The mean value, standard deviation, mean value and standard deviation of the rate of change of the exhaust temperature data set and the local fluctuation value of the exhaust temperature are used to construct a multidimensional feature vector; The isolation forest algorithm is used to train the feature vector to generate multiple isolated trees and then calculate the anomaly score of each data point; Calculate the anomaly score for each data point based on the path length output by the isolation forest model The calculation expression of the abnormality score is: ; Where, Indicates the The abnormality score of each temperature data collection point, Indicates that the isolated tree The average isolated path length, represents the normalization factor; The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is: ; Where, Indicates the total number of exhaust temperature data collection points, Indicates the exhaust temperature abnormality coefficient; Comparing the exhaust temperature anomaly coefficient with a preset threshold value; if the exhaust temperature anomaly coefficient is greater than or equal to the preset threshold value, it indicates that the temperature of the corresponding engine is abnormal; if the exhaust temperature anomaly coefficient is less than the preset threshold value, it indicates that the temperature of the corresponding engine is normal; It should be noted that the exhaust temperature coefficient is used to evaluate whether the temperature of the engine exhaust is abnormal, and when the value of the exhaust temperature coefficient is larger, the corresponding exhaust temperature abnormality is higher.

[0023] In S3, the engine speed data within a monitoring period is acquired in a time series, the speed data is analyzed, the speed fluctuation amplitude and response time are analyzed, the engine speed abnormality coefficient is calculated, and whether the engine speed is abnormal is identified based on the speed abnormality coefficient. Specifically, the following steps are performed: The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed amplitude fluctuation is analyzed, and the speed amplitude fluctuation coefficient is calculated to evaluate the speed fluctuation degree; The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed response time is analyzed, and the response rate abnormality index is calculated to evaluate the abnormality of the engine speed response; Comprehensively processing the degree of speed fluctuation and the degree of speed response abnormality, including: normalizing and calculating the speed amplitude fluctuation coefficient and the response rate abnormality index, calculating the engine speed abnormality coefficient, comparing the speed abnormality coefficient with a preset threshold, and determining whether the speed abnormality coefficient is greater than or equal to the preset threshold; if so, the engine speed is abnormal; if not, the engine speed is normal; The process of obtaining the speed amplitude fluctuation coefficient is as follows: Obtain engine speed data and pre-process the speed data; Standardize the processed speed data; Apply discrete wavelet transform to the standardized speed data, decompose the data into detail coefficients and approximation coefficients at multiple scales, use the wavelet basis and decomposition layer number, and obtain the high-frequency components of the speed data at each scale. The calculation expression is: ; Where, is the approximation coefficient, representing the low-frequency part, represents the number of detail coefficients, Indicates the detail coefficients, representing the high-frequency part, A data set representing the high-frequency components of the speed data at each scale; For each detail coefficient, calculate the corresponding amplitude: ; Where, Indicates the The amplitude of the detail coefficient, Indicates the maximum value of detail coefficient, Indicates the minimum value of detail coefficient; The fluctuation amplitudes corresponding to all detail coefficients are weighted averaged to obtain the overall speed amplitude fluctuation coefficient. The calculation expression is: ; in, Indicates the speed amplitude fluctuation coefficient, Indicates the total number of detail coefficients; The process of obtaining the response rate anomaly index is as follows: By collecting the speed data of the ship engine in real time during the monitoring period, a time series is formed; Perform first-order difference processing on the speed data to obtain a differential data sequence; According to the differential speed data series, the autoregressive order, differential order and sliding average order are selected and the autoregressive integral sliding average model is constructed. The calculation expression is: ; Where, represents the autoregressive order, represents the sliding average order, Indicates the collection time point, Indicates the speed data after differentiation, represents the white noise term, represents the autoregressive coefficient, represents the sliding mean coefficient; The constructed autoregressive integral sliding average model is used to predict the speed at future moments and calculate the time The difference prediction value of , and combine the differential prediction value with the known collected speed data to obtain the speed prediction value. The calculation expression is: ; Where, Indicates the Speed ​​data, Indicates the Speed ​​data of each speed data; Calculate the error between the actual observed speed and the predicted speed. The calculation expression is: ; Where, Indicates the The error between the actual observed speed and the predicted speed at a certain moment All errors are counted and the mean of the errors is calculated and standard deviation ; Calculate the response rate abnormality index. The calculation expression is: ; Where, Indicates the response rate abnormality index, represents the standard deviation of the error, represents the mean of the errors; The calculation expression of the speed abnormality coefficient is: ; Where, Indicates the speed abnormality coefficient, and represents the preset scale factor, and and are greater than 0, represents the exhaust temperature coefficient, Indicates the speed abnormality coefficient; It should be noted that the speed abnormality coefficient reflects whether the engine speed is abnormal, and when the value of the speed abnormality coefficient is larger, the corresponding engine speed abnormality is higher.

[0024] In S4, historical exhaust temperature data and speed data are analyzed to establish an influence relationship model between exhaust temperature and speed abnormality. This model is used to evaluate the impact of engine speed abnormality on exhaust temperature abnormality, specifically including: Based on the data distribution of historical exhaust temperature anomaly coefficients and speed anomaly coefficients, a Bayesian network is constructed, in which a conditional probability relationship exists between exhaust temperature anomaly coefficient nodes and speed anomaly coefficient nodes, and the relationship is used to describe the impact of speed anomaly on exhaust temperature anomaly; Based on historical data, a conditional probability distribution table of the exhaust temperature anomaly coefficient under different speed anomaly coefficient conditions is constructed and the marginal probability distribution of the speed anomaly coefficient is calculated; Calculate the joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient based on the conditional probability formula; The conditional probability formula is: ; Where, Indicates the exhaust temperature abnormality coefficient, Indicates the speed abnormality coefficient, represents the conditional probability distribution, represents the marginal probability distribution of abnormal speed; According to the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated. The calculation expression is: ; Where, It represents the influence relationship coefficient, represents the marginal probability of abnormal exhaust temperature, Indicates the probability of abnormal exhaust temperature under abnormal speed conditions; The influence relationship coefficient is used as an output of the influence relationship model to evaluate the influence of the abnormal speed on the abnormal exhaust temperature; Determine whether the influence relationship coefficient is greater than or equal to a preset threshold value. If so, the abnormal engine speed has an impact on the abnormal exhaust temperature, which is recorded as an influence signal. If not, the abnormal engine speed has no impact on the abnormal exhaust temperature, which is recorded as a non-influence signal. It should be noted that the impact signal reflects the impact of abnormal engine speed on exhaust temperature, and the larger the value of the impact relationship coefficient is, the more impact signal will be generated.

[0025] In S5, based on the impact analysis results, the engine speed is adjusted in real time to ensure that the exhaust temperature returns to the normal range. The adjustment process continuously monitors the coordinated work of exhaust temperature and speed to ensure stable engine operation. Specifically, the following steps are performed: Based on the impact signal, the target normal range of the exhaust temperature and the target speed range that needs to be adjusted are determined according to the exhaust temperature abnormality coefficient and the impact relationship degree coefficient; The process of determining the target normal range of the exhaust temperature is as follows: Analyze the exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data; Calculate the target exhaust temperature range using the following expression: ; Where, The standard configuration is the target exhaust temperature range, represents the confidence coefficient, represents the mean value of the exhaust data, represents the standard deviation of the exhaust data; Based on the historical relationship between exhaust temperature and speed, a regression expression of exhaust temperature and speed is constructed: , and the corresponding speed target range is inversely solved according to the target exhaust temperature range. The calculation expression is: ; Where, Indicates the speed target range, Indicates the exhaust temperature, Indicates the rotation speed; Analyze historical speed fluctuation data, calculate the mean and standard deviation of the speed data, and calculate the correction target range. The calculation expression is: ; Where, represents the mean value of the speed data, represents the standard deviation of the speed data, Indicates the adjustment coefficient based on the historical data of speed fluctuations, Indicates the revised target range; According to the real-time monitored speed data and exhaust temperature data, the adjustment amount is calculated. The calculation expression is: ; Where, Indicates the adjustment amount, represents the control coefficient, Indicates real-time exhaust temperature data; Execute speed control to adjust the current engine speed. The calculation expression is: ; Where, Indicates the adjusted engine speed; During the speed control process, the coordinated changes of speed and exhaust temperature are monitored in real time, and the real-time response of the adjusted speed to the exhaust temperature is recorded to ensure that the exhaust temperature is stable within the target range; Optimize the control coefficient based on historical control data and actual adjustment effects.

[0026] See also Figure 2 As shown in the figure, the ship data anomaly management and analysis system based on big data integration includes: A data acquisition module, wherein the data acquisition module is used to collect exhaust temperature data and speed data of the ship engine in real time by installing a temperature sensor and a speed sensor on the surface of the ship engine; an exhaust temperature anomaly identification module, which acquires exhaust temperature data of the engine within a monitoring period in a time series, calculates an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; a speed anomaly identification module, which acquires engine speed data within a monitoring period in a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates an engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient; An impact relationship evaluation module, which analyzes historical exhaust temperature data and speed data to establish an impact relationship model between exhaust temperature and speed anomalies, and is used to evaluate the degree of impact of engine speed anomalies on exhaust temperature anomalies; A dynamic adjustment module ensures that the exhaust temperature returns to a normal range by adjusting the engine speed in real time based on the analysis results of the impact degree. The adjustment process continuously monitors the coordinated work of the exhaust temperature and speed to ensure stable engine operation.

[0027] The present invention works by real-time monitoring and data analysis of marine engine operating parameters, identifying anomalies and implementing targeted adjustments to ensure stable engine operation. The method includes the following steps: First, temperature and speed sensors are installed on the surface of the marine engine to collect real-time exhaust temperature and speed data. The collected data is preprocessed, including noise removal, missing value filling, and data normalization, to ensure data accuracy and consistency. Second, exhaust temperature data is analyzed through time series analysis to calculate the exhaust temperature anomaly coefficient. The isolation forest algorithm is then used to identify exhaust temperature anomalies. Simultaneously, engine speed data is analyzed for amplitude fluctuation and response time, and the speed anomaly coefficient is calculated to determine speed anomalies. Based on this, historical exhaust temperature and speed data are analyzed, and a Bayesian network model is constructed to model the influence relationship between exhaust temperature and speed anomalies, quantifying the impact of speed anomalies on exhaust temperature anomalies. Finally, based on the results of the influence relationship analysis, a target exhaust temperature range is determined and the target speed range is adjusted. Real-time engine speed adjustment is performed to return the exhaust temperature to the normal range. During the adjustment process, the coordinated changes in exhaust temperature and speed are continuously monitored to optimize the adjustment effect. The present invention realizes all-round monitoring, abnormality detection and intelligent regulation of the ship engine operating status, effectively improving the safety and stability of ship operation.

[0028] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0029] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0030] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0031] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0032] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A ship data anomaly management and analysis method based on big data integration is characterized by: The following steps are involved: S1: A temperature sensor and a speed sensor are installed on the surface of the ship engine to collect exhaust temperature data and speed data of the ship engine in real time, and pre-process the collected exhaust temperature data and speed data; S2: Acquire exhaust temperature data of the engine within a monitoring period in a time series, calculate an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; S3: acquiring engine speed data within a monitoring period in a time series, analyzing the speed data, analyzing the speed fluctuation amplitude and response time, calculating the engine speed abnormality coefficient, and identifying whether the engine speed is abnormal based on the speed abnormality coefficient; S4: Analyze historical exhaust temperature data and speed data to establish an influence relationship model between exhaust temperature and speed abnormality, which is used to evaluate the impact of engine speed abnormality on exhaust temperature abnormality; S5: Based on the analysis results of the impact degree, the engine speed is adjusted in real time to ensure that the exhaust temperature returns to the normal range. The adjustment process continuously monitors the coordinated work of exhaust temperature and speed to ensure stable engine operation.

2. The ship data anomaly management and analysis method based on big data integration according to claim 1 is characterized in that: Calculating the exhaust temperature anomaly coefficient according to the degree of fluctuation of the exhaust temperature data specifically includes: Obtain exhaust temperature data set within the monitoring period; Calculate the mean, standard deviation, and rate of change of the exhaust temperature data set; The calculation expression of the change rate is: ； in, Represents each temperature data collection point, Indicates the The temperature value of each temperature data collection point, Indicates the The collection point and Temperature change rate of each sampling point; According to the rate of change of the exhaust temperature data set, the mean and standard deviation of the rate of change are calculated; Calculate the local fluctuation value of exhaust temperature, the calculation expression is: ； in, represents the sliding window size, Indicates the The local fluctuation value of each temperature data collection point; The mean value, standard deviation, mean value and standard deviation of the rate of change of the exhaust temperature data set and the local fluctuation value of the exhaust temperature are used to construct a multidimensional feature vector; The isolation forest algorithm is used to train the feature vector to generate multiple isolated trees and then calculate the anomaly score of each data point; Calculate the anomaly score for each data point based on the path length output by the isolation forest model The calculation expression of the abnormality score is: ； Where, Indicates the The abnormality score of each temperature data collection point, Indicates that the isolated tree The average isolated path length, represents the normalization factor; The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is: ； Where, Indicates the total number of exhaust temperature data collection points, Indicates the exhaust temperature abnormality coefficient.

3. The ship data anomaly management and analysis method based on big data integration according to claim 1 is characterized in that: The step of identifying whether the engine speed is abnormal based on the speed abnormality coefficient specifically includes: The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed amplitude fluctuation is analyzed, and the speed amplitude fluctuation coefficient is calculated to evaluate the speed fluctuation degree; The engine speed data within a monitoring period is acquired in time series, the speed data is analyzed, the speed response time is analyzed, and the response rate abnormality index is calculated to evaluate the abnormality of the engine speed response; The speed fluctuation degree and the speed response abnormality degree are comprehensively processed, including: normalizing the speed amplitude fluctuation coefficient and the response rate abnormality index, calculating the engine speed abnormality coefficient, comparing the speed abnormality coefficient with a preset threshold, and judging whether the speed abnormality coefficient is greater than or equal to the preset threshold. If so, the engine speed is abnormal; if not, the engine speed is normal.

4. The ship data anomaly management and analysis method based on big data integration according to claim 3 is characterized in that: The process of obtaining the speed amplitude fluctuation coefficient is as follows: Obtain engine speed data and pre-process the speed data; Standardize the processed speed data; Apply discrete wavelet transform to the standardized speed data, decompose the data into detail coefficients and approximation coefficients at multiple scales, use the wavelet basis and decomposition layer number, and obtain the high-frequency components of the speed data at each scale. The calculation expression is: ； Where, is the approximation coefficient, representing the low-frequency part, represents the number of detail coefficients, Indicates the detail coefficients, representing the high-frequency part, A data set representing the high-frequency components of the speed data at each scale; For each detail coefficient, calculate the corresponding amplitude: ； Where, Indicates the The amplitude of the detail coefficient, Indicates the maximum value of detail coefficient, Indicates the minimum value of detail coefficient; The fluctuation amplitudes corresponding to all detail coefficients are weighted averaged to obtain the overall speed amplitude fluctuation coefficient. The calculation expression is: ； in, Indicates the speed amplitude fluctuation coefficient, Indicates the total number of detail coefficients.

5. The ship data anomaly management and analysis method based on big data integration according to claim 3 is characterized in that: The process of obtaining the response rate anomaly index is as follows: By collecting the speed data of the ship engine in real time during the monitoring period, a time series is formed; Perform first-order difference processing on the speed data to obtain a differential data sequence; According to the differential speed data sequence, the autoregressive order, differential order and sliding average order are selected and the autoregressive integral sliding average model is constructed. The calculation expression is: ； Where, represents the autoregressive order, represents the sliding average order, Indicates the collection time point, Indicates the speed data after differentiation, represents the white noise term, represents the autoregressive coefficient, represents the sliding mean coefficient; The constructed autoregressive integral sliding average model is used to predict the speed at future moments and calculate the time The difference prediction value of , and combine the differential prediction value with the known collected speed data to obtain the speed prediction value. The calculation expression is: ； Where, Indicates the Speed ​​data, Indicates the Speed ​​data of each speed data; Calculate the error between the actual observed speed and the predicted speed. The calculation expression is: ； Where, Indicates the The error between the actual observed speed and the predicted speed at a certain moment All errors are counted and the mean of the errors is calculated and standard deviation ; Calculate the response rate abnormality index. The calculation expression is: ； Where, Indicates the response rate abnormality index, represents the standard deviation of the error, represents the mean of the errors.

6. The ship data anomaly management and analysis method based on big data integration according to claim 1 is characterized in that: Analyze historical exhaust temperature and speed data to establish an impact relationship model between exhaust temperature and speed anomalies, including: Based on the data distribution of historical exhaust temperature anomaly coefficients and speed anomaly coefficients, a Bayesian network is constructed, in which a conditional probability relationship exists between exhaust temperature anomaly coefficient nodes and speed anomaly coefficient nodes, and the relationship is used to describe the impact of speed anomaly on exhaust temperature anomaly; Based on historical data, a conditional probability distribution table of the exhaust temperature anomaly coefficient under different speed anomaly coefficient conditions is constructed and the marginal probability distribution of the speed anomaly coefficient is calculated; Calculate the joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient based on the conditional probability formula; The conditional probability formula is: ； Where, Indicates the exhaust temperature abnormality coefficient, Indicates the speed abnormality coefficient, represents the conditional probability distribution, represents the marginal probability distribution of abnormal speed; According to the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated. The calculation expression is: ； Where, Indicates the influence relationship coefficient, represents the marginal probability of abnormal exhaust temperature, Indicates the probability of abnormal exhaust temperature under abnormal speed conditions; The influence relationship degree coefficient is used as the output of the influence relationship model to evaluate the influence degree of the abnormal speed on the abnormal exhaust temperature.

7. The ship data anomaly management and analysis method based on big data integration according to claim 1 is characterized in that: The evaluation of the degree of influence of abnormal engine speed on abnormal exhaust temperature specifically includes: Determine whether the influence relationship coefficient is greater than or equal to a preset threshold. If so, the abnormal engine speed has an impact on the abnormal exhaust temperature, which is recorded as an influence signal. If not, the abnormal engine speed has no impact on the abnormal exhaust temperature, which is recorded as a non-influence signal.

8. The ship data anomaly management and analysis method based on big data integration according to claim 1 is characterized in that: According to the analysis results of the impact degree, the engine speed is adjusted in real time to ensure that the exhaust temperature returns to the normal range, specifically including: Based on the impact signal, the target normal range of the exhaust temperature and the target speed range that needs to be adjusted are determined according to the exhaust temperature abnormality coefficient and the impact relationship degree coefficient; The process of determining the target normal range of the exhaust temperature is as follows: Analyze the exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data; Calculate the target exhaust temperature range using the following expression: ； Where, The standard is the target exhaust temperature range, represents the confidence coefficient, represents the mean value of the exhaust data, represents the standard deviation of the exhaust data; Based on the historical relationship between exhaust temperature and speed, a regression expression of exhaust temperature and speed is constructed: , and the corresponding speed target range is inversely solved according to the target exhaust temperature range. The calculation expression is: ； Where, Indicates the speed target range, Indicates the exhaust temperature, Indicates the rotation speed; Analyze historical speed fluctuation data, calculate the mean and standard deviation of the speed data, and calculate the correction target range. The calculation expression is: ； Where, represents the mean value of the speed data, represents the standard deviation of the speed data, Indicates the adjustment coefficient based on the historical data of speed fluctuations, Indicates the revised target range; According to the real-time monitored speed data and exhaust temperature data, the adjustment amount is calculated. The calculation expression is: ； Where, Indicates the adjustment amount, represents the control coefficient, Indicates real-time exhaust temperature data; Execute speed control to adjust the current engine speed. The calculation expression is: ； Where, Indicates the adjusted engine speed; During the speed control process, the coordinated changes of speed and exhaust temperature are monitored in real time, and the real-time response of the adjusted speed to the exhaust temperature is recorded to ensure that the exhaust temperature is stable within the target range; Optimize the control coefficient based on historical control data and actual adjustment effects.

9. The ship data anomaly management and analysis system based on big data integration is characterized by: The ship data anomaly management and analysis method based on big data integration according to any one of claims 1 to 8 comprises: A data acquisition module, wherein the data acquisition module is used to collect exhaust temperature data and speed data of the ship engine in real time by installing a temperature sensor and a speed sensor on the surface of the ship engine; an exhaust temperature anomaly identification module, which acquires exhaust temperature data of the engine within a monitoring period in a time series, calculates an exhaust temperature anomaly coefficient based on the degree of fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient; a speed anomaly identification module, which acquires engine speed data within a monitoring period in a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates an engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient; An impact relationship evaluation module, which analyzes historical exhaust temperature data and speed data to establish an impact relationship model between exhaust temperature and speed anomalies, and is used to evaluate the degree of impact of engine speed anomalies on exhaust temperature anomalies; A dynamic adjustment module ensures that the exhaust temperature returns to a normal range by adjusting the engine speed in real time based on the analysis results of the impact degree. The adjustment process continuously monitors the coordinated work of the exhaust temperature and speed to ensure stable engine operation.

Images