A Method and System for Ship Data Anomaly Management and Analysis Based on Big Data Integration

Abstract

This invention relates to the field of intelligent monitoring and control technology for marine power systems, specifically disclosing a method and system for managing and analyzing ship data anomalies based on big data integration. By installing temperature and speed sensors on the engine surface, exhaust temperature and speed data are collected in real time. Feature vectors are constructed based on the isolated forest algorithm to accurately identify anomalies in exhaust temperature and speed, and anomaly states are quantified by calculating anomaly coefficients, significantly reducing the risk of misjudgment and missed judgment. This invention establishes a model of the influence relationship between exhaust temperature and speed anomalies, assesses the degree of influence of speed anomalies on exhaust temperature anomalies, and achieves real-time control within the target range accordingly. During the control process, the coordinated changes in exhaust temperature and speed are continuously monitored, and control parameters are optimized to ensure the stability and safety of engine operation.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring and control technology for ship propulsion systems, specifically to a method and system for ship data anomaly management and analysis based on big data integration. Background Technology

[0002] With the development of the global shipping industry, marine engines, as the core of the power system, directly impact the economic benefits and navigational safety of ships due to their operational stability and safety. During long-term operation, marine engines are susceptible to performance degradation or malfunctions due to complex operating conditions and variable environments caused by factors such as temperature and load. In particular, exhaust temperature and engine speed, as important indicators of engine operating status, reflect key parameters such as combustion efficiency and mechanical wear. Real-time monitoring and anomaly management of these parameters are crucial for ensuring efficient operation and extending the service life of marine engines. However, traditional monitoring and management methods often rely on manual experience or simple, fixed rules, which are ill-suited to the complexity of marine engine operation and the dynamically changing environmental demands.

[0003] Shortcomings of existing technology:

[0004] Traditional anomaly detection methods often rely on fixed threshold judgments or simple statistical models. These approaches struggle to capture the complex nonlinear relationship between exhaust temperature and engine speed, easily leading to misjudgments and missed detections. Furthermore, existing methods often lack intelligent control mechanisms after anomaly identification, failing to effectively coordinate the dynamic relationship between exhaust temperature and engine speed, resulting in delayed anomaly handling or even secondary failures. Simultaneously, traditional methods do not adequately emphasize data preprocessing and model optimization, making them susceptible to interference from noisy and missing data, affecting the accuracy and real-time performance of detection results. Current technologies fall short in terms of accuracy, intelligence, and adaptability in marine engine anomaly detection and control, urgently requiring an innovative solution combining big data analytics and intelligent algorithms to achieve precise detection and real-time control of engine anomalies. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for managing and analyzing ship data anomalies based on big data integration, so as to solve the problems mentioned above.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] The ship data anomaly management and analysis method based on big data integration includes the following steps:

[0008] S1: By installing temperature and speed sensors on the surface of the ship engine, the exhaust temperature and speed data of the ship engine are collected in real time, and the collected exhaust temperature and speed data are preprocessed.

[0009] S2: Obtain the engine exhaust temperature data within a monitoring period according to the time series, calculate the exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient.

[0010] S3: Obtain engine speed data within a monitoring period according to the time series, analyze the speed data, analyze the speed fluctuation and response time, calculate the engine speed anomaly coefficient, and identify whether the engine speed is abnormal based on the speed anomaly coefficient;

[0011] S4: Analyze historical exhaust temperature and speed data to establish a model of the relationship between exhaust temperature and speed anomalies, which is used to assess the degree of influence of engine speed anomalies on exhaust temperature anomalies.

[0012] S5: Based on the analysis results of the degree of impact, 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 operation of exhaust temperature and speed to ensure stable engine operation.

[0013] As a further aspect of the present invention: the calculation of the exhaust temperature anomaly coefficient based on the fluctuation of exhaust temperature data specifically includes:

[0014] Obtain the exhaust temperature dataset within the monitoring period;

[0015] Calculate the mean, standard deviation, and rate of change of the exhaust temperature dataset;

[0016] The expression for calculating the rate of change is:

[0017] ;

[0018] in, This represents each temperature data collection point. Indicates the first Temperature values ​​at each temperature data collection point. Indicates the first The first collection point and the first Temperature change rate at each sampling point;

[0019] Calculate the mean and standard deviation of the rate of change based on the rate of change of the exhaust temperature dataset;

[0020] The local fluctuation value of the exhaust temperature is calculated using the following expression:

[0021] ;

[0022] in, Indicates the size of the sliding window. Indicates the first Local fluctuation values ​​at each temperature data collection point;

[0023] A multidimensional feature vector is constructed from the mean, standard deviation, mean and standard deviation of the rate of change, and local fluctuations of the exhaust temperature dataset.

[0024] The isolated forest algorithm is used to train the feature vectors, generate multiple isolated trees, and then calculate the anomaly score for each data point.

[0025] Calculate the anomaly score for each data point based on the path length output by the Isolation Forest model.

[0026] The calculation expression for the anomaly score is as follows:

[0027] ;

[0028] In the formula, Indicates the first Anomaly rating for each temperature data collection point Indicates the general in an isolated tree Average path length when isolated Indicates the normalization factor;

[0029] The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is as follows:

[0030] ;

[0031] In the formula, This indicates the total number of exhaust temperature data collection points. This represents the exhaust temperature anomaly coefficient.

[0032] As a further aspect of the present invention: the method of identifying whether the engine speed is abnormal based on the speed anomaly coefficient specifically includes:

[0033] Engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to determine the fluctuation range of the speed and to calculate the speed fluctuation coefficient to assess the degree of speed fluctuation.

[0034] The engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to analyze the speed response time and calculate the response rate anomaly index to assess the degree of anomaly in the engine speed response.

[0035] The fluctuation degree of engine speed and the abnormal degree of engine speed response are processed in a comprehensive manner, including: normalizing the engine speed amplitude fluctuation coefficient and the response rate abnormality index, calculating the engine speed abnormality coefficient, comparing the engine speed abnormality coefficient with a preset threshold, and determining whether the engine speed abnormality coefficient is greater than or equal to the preset threshold. If it is, the engine speed is abnormal; otherwise, the engine speed is normal.

[0036] As a further aspect of the present invention: the process for obtaining the rotational speed fluctuation coefficient is as follows:

[0037] Acquire engine speed data and preprocess the speed data;

[0038] The processed rotation speed data is then standardized.

[0039] Discrete wavelet transform is applied to the standardized rotational speed data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Using wavelet basis and decomposition level, the high-frequency components of the rotational speed data at each scale are obtained. The calculation expression is as follows:

[0040] ;

[0041] In the formula, The approximation coefficient represents the low-frequency component. Indicates the number of detail coefficients. Indicates the first These detail coefficients represent the high-frequency components. A dataset representing the high-frequency components of rotational speed data at each scale;

[0042] For each detail coefficient, calculate the corresponding amplitude:

[0043] ;

[0044] In the formula, Indicates the first The magnitude of each detail coefficient, This represents the maximum value of the detail coefficient. This represents the minimum value of the detail coefficient;

[0045] The overall speed fluctuation coefficient is obtained by weighted averaging the fluctuation amplitudes corresponding to all detail coefficients. The calculation expression is as follows:

[0046] ;

[0047] in, Indicates the coefficient of rotational speed fluctuation. This represents the total number of detail coefficients.

[0048] As a further aspect of the present invention: the process for obtaining the response rate anomaly index is as follows:

[0049] By collecting real-time speed data of ship engines during the monitoring period, a time series is formed;

[0050] The rotational speed data is subjected to first-order difference processing to obtain a difference data sequence;

[0051] Based on the differentiald rotational speed data sequence, the autoregressive order, differencing order, and moving average order are selected, and an autoregressive integral moving average model is constructed. The calculation expression is as follows:

[0052] ;

[0053] In the formula, Indicates the order of autoregression. Indicates the order of the moving average. Indicates the time point of data collection. This represents the speed data after differential processing. Represents the white noise term. Represents the autoregressive coefficient. Indicates the moving average coefficient;

[0054] The constructed autoregressive integral moving average model is used to predict the rotational speed at future times, and the rotational speed at time is calculated. Differential prediction values The differential prediction value is then combined with the known collected rotational speed data to obtain the rotational speed prediction value, calculated as follows:

[0055] ;

[0056] In the formula, Indicates the first One rotational speed data, Indicates the first Speed ​​data for each speed;

[0057] The error between the actual observed rotational speed and the predicted rotational speed is calculated using the following expression:

[0058] ;

[0059] In the formula, Indicates the first The error between the actual observed rotational speed and the predicted rotational speed at a given moment

[0060] All errors are statistically analyzed, and the mean of the errors is calculated. and standard deviation ;

[0061] The response rate anomaly index is calculated using the following expression:

[0062] ;

[0063] In the formula, Indicates the anomaly index of response rate. The standard deviation represents the error. This represents the mean of the error.

[0064] As a further aspect of this invention: analyzing historical exhaust temperature data and engine speed data to establish a model of the influence relationship between abnormal exhaust temperature and engine speed, specifically including:

[0065] Based on the data distribution of historical exhaust temperature anomaly coefficient and speed anomaly coefficient, a Bayesian network is constructed, in which there is a conditional probability relationship between the exhaust temperature anomaly coefficient node and the speed anomaly coefficient node, and the relationship is used to describe the influence of speed anomaly on exhaust temperature anomaly.

[0066] 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.

[0067] The joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient is calculated based on the conditional probability formula.

[0068] The conditional probability formula is:

[0069] ;

[0070] In the formula, Indicates the exhaust temperature anomaly coefficient. Indicates the speed anomaly coefficient. Represents the conditional probability distribution. This represents the marginal probability distribution of abnormal rotational speed.

[0071] Based on the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated, and the calculation expression is as follows:

[0072] ;

[0073] In the formula, Indicates the degree of influence coefficient. This represents the marginal probability of an abnormal exhaust temperature. This indicates the probability of abnormal exhaust temperature under abnormal speed conditions;

[0074] The influence relationship coefficient is used as the output of the influence relationship model to evaluate the degree of influence of abnormal speed on abnormal exhaust temperature.

[0075] As a further aspect of the present invention: the assessment of the impact of abnormal engine speed on abnormal exhaust temperature specifically includes:

[0076] Determine whether the influence coefficient is greater than or equal to a preset threshold. If it is, the abnormal engine speed has an impact on the abnormal exhaust temperature, and this is recorded as an influence signal. If not, the abnormal engine speed does not have an impact on the abnormal exhaust temperature, and this is recorded as a non-influence signal.

[0077] As a further aspect of the present invention: the step of ensuring the exhaust temperature returns to the normal range by real-time adjustment of engine speed based on the analysis results of the degree of influence specifically includes:

[0078] Based on the influence signals, the target normal range of exhaust temperature and the target range of engine speed that need to be adjusted are determined according to the exhaust temperature anomaly coefficient and the influence relationship degree coefficient.

[0079] The process for determining the target normal range of the exhaust temperature is as follows:

[0080] Analyze exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data;

[0081] The target exhaust temperature range is calculated using the following formula:

[0082] ;

[0083] In the formula, The standard configuration is the target exhaust temperature range. Represents the confidence coefficient. This represents the mean of exhaust data. This represents the standard deviation of exhaust data;

[0084] Based on the historical relationship between exhaust temperature and engine speed, a regression expression for exhaust temperature and engine speed is constructed: And based on the target exhaust temperature range, the corresponding target speed range is solved inversely, and the calculation expression is:

[0085] ;

[0086] In the formula, Indicates the target speed range. Indicates exhaust temperature. Indicates rotational speed;

[0087] 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 as follows:

[0088] ;

[0089] In the formula, This represents the mean of the rotational speed data. The standard deviation of the rotational speed data This represents the adjustment coefficient based on historical speed fluctuation data. Indicates the scope of the target adjustment;

[0090] Based on the real-time monitored engine speed and exhaust temperature data, the adjustment amount is calculated using the following expression:

[0091] ;

[0092] In the formula, Indicates the adjustment amount. Indicates the control coefficient. This indicates real-time exhaust temperature data;

[0093] To perform speed control and adjust the current engine speed, the calculation expression is:

[0094] ;

[0095] In the formula, This indicates the adjusted engine speed;

[0096] During the speed control process, the coordinated changes of speed and exhaust temperature are monitored in real time, and the real-time response of speed to exhaust temperature after adjustment is recorded to ensure that the exhaust temperature remains stable within the target range.

[0097] The control coefficients are optimized based on historical control data and actual adjustment effects.

[0098] A comprehensive ship data anomaly management and analysis system based on big data includes:

[0099] The data acquisition module, which uses temperature and speed sensors mounted on the surface of the ship engine, is used to collect exhaust temperature and speed data of the ship engine in real time.

[0100] An exhaust temperature anomaly identification module acquires engine exhaust temperature data within a monitoring period according to a time series, calculates an exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient.

[0101] The engine speed anomaly identification module acquires engine speed data within a monitoring period according to a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates the engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient.

[0102] The impact relationship assessment module analyzes historical exhaust temperature data and engine speed data to establish an impact relationship model between exhaust temperature and engine speed anomalies, which is used to assess the degree of impact of engine speed anomalies on exhaust temperature anomalies.

[0103] The dynamic adjustment module, based on the analysis results of the degree of influence, adjusts the engine speed in real time to ensure that the exhaust temperature returns to the normal range, and continuously monitors the coordinated operation of exhaust temperature and speed to ensure stable engine operation.

[0104] The beneficial effects of this invention are:

[0105] (1) This invention precisely arranges temperature and speed sensors on the surface of the ship's engine to collect high-precision exhaust temperature and real-time speed data, respectively. The collected data undergoes multi-layer preprocessing using Kalman filtering, linear interpolation, and standardization to ensure the integrity and consistency of the time-series data. During anomaly detection, the isolated forest algorithm is used, employing multi-dimensional feature vectors as input. The isolated tree model accurately evaluates the anomaly score of each data point and calculates the anomaly coefficients for exhaust temperature and speed, quantifying complex anomaly patterns into physically meaningful numerical indicators, effectively improving the scientific rigor and interpretability of anomaly detection. Compared to traditional monitoring methods relying on human experience or simple threshold rules, this invention optimizes algorithm robustness, dynamic adaptability, and real-time performance. It can accurately identify anomalies under complex operating conditions, reducing the risk of misjudgment and missed judgment, and providing a scientific and reliable decision-making basis for real-time monitoring and subsequent intelligent control of engine operating status.

[0106] (2) This invention not only accurately detects abnormal states of ship engines, but also reveals the complex relationship between abnormal exhaust temperature and abnormal engine speed by constructing a Bayesian network model based on historical data. It quantifies the causal impact of abnormal engine speed on abnormal exhaust temperature, forming a scientific method for abnormal correlation analysis. Based on this, according to the target exhaust temperature range and target engine speed range, the engine speed is dynamically adjusted in real time, combined with a regression model of exhaust temperature and engine speed. During the adjustment process, this invention continuously monitors the coordinated changes in engine speed and exhaust temperature, and optimizes the adjustment coefficient using historical adjustment data to ensure the accuracy and adaptability of the adjustment. This closed-loop intelligent control strategy effectively mitigates the impact of abnormal states on engine operation, significantly improves engine stability and safety, reduces energy consumption and economic losses, and thus comprehensively ensures the efficient operation and economic benefits of the ship, demonstrating the practical value and innovative advantages of this invention under complex operating conditions. Attached Figure Description

[0107] The invention will now be further described with reference to the accompanying drawings.

[0108] Figure 1 This is a flowchart illustrating the specific steps of the ship data anomaly management and analysis method based on big data integration according to the present invention.

[0109] Figure 2 This is a flowchart of the ship data anomaly management and analysis system based on big data integration in this invention. Detailed Implementation

[0110] 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.

[0111] Please see Figure 1 As shown, this invention is a ship data anomaly management and analysis method based on big data integration, including the following steps:

[0112] S1: By installing temperature and speed sensors on the surface of the ship's engine, the exhaust temperature and speed data of the ship's engine are collected in real time. The collected exhaust temperature and speed data are preprocessed, including noise removal, missing data filling and data format standardization, to ensure the accuracy and consistency of the data.

[0113] S2: Obtain the engine exhaust temperature data within a monitoring period according to the time series, calculate the exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient.

[0114] S3: Obtain engine speed data within a monitoring period according to the time series, analyze the speed data, analyze the speed fluctuation and response time, calculate the engine speed anomaly coefficient, and identify whether the engine speed is abnormal based on the speed anomaly coefficient;

[0115] S4: Analyze historical exhaust temperature and speed data to establish a model of the relationship between exhaust temperature and speed anomalies, which is used to assess the degree of influence of engine speed anomalies on exhaust temperature anomalies.

[0116] S5: Based on the analysis results of the degree of impact, 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 operation of exhaust temperature and speed to ensure stable engine operation.

[0117] In S1, temperature and speed sensors are installed on the surface of the ship's engine to collect real-time exhaust temperature and speed data. The collected raw data undergoes preprocessing, including noise removal, missing data filling, and data format standardization, to ensure accuracy and consistency. Specifically, this includes:

[0118] Temperature and speed sensors are strategically placed on the surface of the ship's engine to ensure the accuracy and coverage of data collection.

[0119] The temperature sensor is installed near the engine exhaust port and uses a high-precision thermocouple or infrared temperature sensor to collect the exhaust temperature and capture minute temperature changes in real time.

[0120] The speed sensor is installed on the engine main shaft or flywheel, and uses a magnetoelectric or photoelectric sensor to record the real-time rotation speed of the engine.

[0121] During the data acquisition process, the sensor transmits the raw data to the central data processing unit in real time via an integrated data bus, and simultaneously records the data with a preliminary timestamp to ensure the integrity of the time series for subsequent analysis.

[0122] 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 from the collected data;

[0123] Secondly, to address the issue of missing data during the data collection process, a linear interpolation method based on adjacent time windows is used to fill in the missing values, ensuring the continuity of the time series data.

[0124] Finally, the data from different sensors are standardized, with unified units and dimensions, and converted into a dimensionless data format to ensure compatibility and accuracy in subsequent analysis.

[0125] In S2, exhaust temperature data of the engine within a monitoring period is acquired according to a time series. Based on the fluctuation of the exhaust temperature data, an exhaust temperature anomaly coefficient is calculated. The anomaly coefficient is used to identify whether the exhaust temperature is abnormal, specifically including:

[0126] Obtain the exhaust temperature dataset within the monitoring period;

[0127] Calculate the mean, standard deviation, and rate of change of the exhaust temperature dataset;

[0128] The expression for calculating the rate of change is:

[0129] ;

[0130] in, This represents each temperature data collection point. Indicates the first Temperature values ​​at each temperature data collection point. Indicates the first The first collection point and the first Temperature change rate at each sampling point;

[0131] Calculate the mean and standard deviation of the rate of change based on the rate of change of the exhaust temperature dataset;

[0132] The local fluctuation value of the exhaust temperature is calculated using the following expression:

[0133] ;

[0134] in, Indicates the size of the sliding window. Indicates the first Local fluctuation values ​​at each temperature data collection point;

[0135] A multidimensional feature vector is constructed from the mean, standard deviation, mean and standard deviation of the rate of change, and local fluctuations of the exhaust temperature dataset.

[0136] The isolated forest algorithm is used to train the feature vectors, generate multiple isolated trees, and then calculate the anomaly score for each data point.

[0137] Calculate the anomaly score for each data point based on the path length output by the Isolation Forest model.

[0138] The calculation expression for the anomaly score is as follows:

[0139] ;

[0140] In the formula, Indicates the first Anomaly rating for each temperature data collection point Indicates the general in an isolated tree Average path length when isolated Indicates the normalization factor;

[0141] The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is as follows:

[0142] ;

[0143] In the formula, This indicates the total number of exhaust temperature data collection points. Indicates the exhaust temperature anomaly coefficient;

[0144] The exhaust temperature abnormality coefficient is compared with the preset threshold. If the exhaust temperature abnormality coefficient is greater than or equal to the preset threshold, it indicates that the temperature of the corresponding engine is abnormal. If the exhaust temperature abnormality coefficient is less than the preset threshold, it indicates that the temperature of the corresponding engine is normal.

[0145] It should be noted that the exhaust temperature coefficient is used to assess whether the temperature of the engine exhaust is abnormal, and the larger the value of the exhaust temperature coefficient, the higher the degree of exhaust temperature abnormality.

[0146] In S3, engine speed data for a monitoring period is acquired according to a time series. The speed data is analyzed to assess fluctuations in speed amplitude and response time, and an engine speed anomaly coefficient is calculated. Based on this coefficient, the system identifies whether the engine speed is abnormal. Specifically, this includes:

[0147] Engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to determine the fluctuation range of the speed and to calculate the speed fluctuation coefficient to assess the degree of speed fluctuation.

[0148] The engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to analyze the speed response time and calculate the response rate anomaly index to assess the degree of anomaly in the engine speed response.

[0149] The fluctuation degree of speed and the abnormal degree of speed response are processed in a comprehensive manner, 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 determining whether the speed abnormality coefficient is greater than or equal to the preset threshold. If it is, the engine speed is abnormal; otherwise, the engine speed is normal.

[0150] The process for obtaining the rotational speed fluctuation coefficient is as follows:

[0151] Acquire engine speed data and preprocess the speed data;

[0152] The processed rotation speed data is then standardized.

[0153] Discrete wavelet transform is applied to the standardized rotational speed data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Using wavelet basis and decomposition level, the high-frequency components of the rotational speed data at each scale are obtained. The calculation expression is as follows:

[0154] ;

[0155] In the formula, The approximation coefficient represents the low-frequency component. Indicates the number of detail coefficients. Indicates the first These detail coefficients represent the high-frequency components. A dataset representing the high-frequency components of rotational speed data at each scale;

[0156] For each detail coefficient, calculate the corresponding amplitude:

[0157] ;

[0158] In the formula, Indicates the first The magnitude of each detail coefficient, This represents the maximum value of the detail coefficient. This represents the minimum value of the detail coefficient;

[0159] The overall speed fluctuation coefficient is obtained by weighted averaging the fluctuation amplitudes corresponding to all detail coefficients. The calculation expression is as follows:

[0160] ;

[0161] in, Indicates the coefficient of rotational speed fluctuation. Indicates the total number of detail coefficients;

[0162] The process for obtaining the response rate anomaly index is as follows:

[0163] By collecting real-time engine speed data during the monitoring period, a time series is generated;

[0164] The rotational speed data is subjected to first-order difference processing to obtain a difference data sequence;

[0165] Based on the differentiald rotational speed data sequence, the autoregressive order, differencing order, and moving average order are selected, and an autoregressive integral moving average model is constructed. The calculation expression is as follows:

[0166] ;

[0167] In the formula, Indicates the order of autoregression. Indicates the order of the moving average. Indicates the time point of data collection. This represents the speed data after differential processing. Represents the white noise term. Represents the autoregressive coefficient. Indicates the moving average coefficient;

[0168] The constructed autoregressive integral moving average model is used to predict the rotational speed at future times, and the rotational speed at time is calculated. Differential prediction values The differential prediction value is then combined with the known collected rotational speed data to obtain the rotational speed prediction value, calculated as follows:

[0169] ;

[0170] In the formula, Indicates the first One rotational speed data, Indicates the first Speed ​​data for each speed;

[0171] The error between the actual observed rotational speed and the predicted rotational speed is calculated using the following expression:

[0172] ;

[0173] In the formula, Indicates the first The error between the actual observed rotational speed and the predicted rotational speed at a given moment

[0174] All errors are statistically analyzed, and the mean of the errors is calculated. and standard deviation ;

[0175] The response rate anomaly index is calculated using the following expression:

[0176] ;

[0177] In the formula, Indicates the anomaly index of response rate. The standard deviation represents the error. This represents the mean of the error;

[0178] The formula for calculating the speed anomaly coefficient is as follows:

[0179] ;

[0180] In the formula, Indicates the speed anomaly coefficient. and This indicates a preset scaling factor, and and All are greater than 0. Indicates the exhaust temperature coefficient. Indicates the speed anomaly coefficient;

[0181] It should be noted that the speed abnormality coefficient reflects whether the engine speed is abnormal, and the larger the value of the speed abnormality coefficient, the higher the degree of engine speed abnormality.

[0182] In S4, historical exhaust temperature and engine speed data are analyzed to establish a model of the relationship between exhaust temperature and engine speed anomalies. This model is used to assess the impact of engine speed anomalies on exhaust temperature anomalies, specifically including:

[0183] Based on the data distribution of historical exhaust temperature anomaly coefficient and speed anomaly coefficient, a Bayesian network is constructed, in which there is a conditional probability relationship between the exhaust temperature anomaly coefficient node and the speed anomaly coefficient node, and the relationship is used to describe the influence of speed anomaly on exhaust temperature anomaly.

[0184] 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.

[0185] The joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient is calculated based on the conditional probability formula.

[0186] The conditional probability formula is:

[0187] ;

[0188] In the formula, Indicates the exhaust temperature anomaly coefficient. Indicates the speed anomaly coefficient. Represents the conditional probability distribution. This represents the marginal probability distribution of abnormal rotational speed.

[0189] Based on the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated, and the calculation expression is as follows:

[0190] ;

[0191] In the formula, Indicates the degree of influence coefficient. This represents the marginal probability of an abnormal exhaust temperature. This indicates the probability of abnormal exhaust temperature under abnormal speed conditions;

[0192] The influence relationship coefficient is used as the output of the influence relationship model to evaluate the degree of influence of abnormal speed on abnormal exhaust temperature.

[0193] Determine whether the influence coefficient is greater than or equal to a preset threshold. If it is, the abnormal engine speed has an impact on the abnormal exhaust temperature, and this is recorded as an influence signal. If not, the abnormal engine speed does not have an impact on the abnormal exhaust temperature, and this is recorded as a non-influence signal.

[0194] It should be noted that the influence signal reflects the impact of abnormal engine speed on exhaust temperature, and the larger the value of the influence coefficient, the more influence signal will be generated.

[0195] In S5, based on the analysis of the degree of impact, 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 operation of exhaust temperature and engine speed to ensure stable engine operation. Specifically, this includes:

[0196] Based on the influence signals, the target normal range of exhaust temperature and the target range of engine speed that need to be adjusted are determined according to the exhaust temperature anomaly coefficient and the influence relationship degree coefficient.

[0197] The process for determining the target normal range of the exhaust temperature is as follows:

[0198] Analyze exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data;

[0199] The target exhaust temperature range is calculated using the following formula:

[0200] ;

[0201] In the formula, The standard configuration is the target exhaust temperature range. Represents the confidence coefficient. This represents the mean of exhaust data. This represents the standard deviation of exhaust data;

[0202] Based on the historical relationship between exhaust temperature and engine speed, a regression expression for exhaust temperature and engine speed is constructed: And based on the target exhaust temperature range, the corresponding target speed range is solved inversely, and the calculation expression is:

[0203] ;

[0204] In the formula, Indicates the target speed range. Indicates exhaust temperature. Indicates rotational speed;

[0205] 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 as follows:

[0206] ;

[0207] In the formula, This represents the mean of the rotational speed data. The standard deviation of the rotational speed data This represents the adjustment coefficient based on historical speed fluctuation data. Indicates the scope of the target adjustment;

[0208] Based on the real-time monitored engine speed and exhaust temperature data, the adjustment amount is calculated using the following expression:

[0209] ;

[0210] In the formula, Indicates the adjustment amount. Indicates the control coefficient. This indicates real-time exhaust temperature data;

[0211] To perform speed control and adjust the current engine speed, the calculation expression is:

[0212] ;

[0213] In the formula, This indicates the adjusted engine speed;

[0214] During the speed control process, the coordinated changes of speed and exhaust temperature are monitored in real time, and the real-time response of speed to exhaust temperature after adjustment is recorded to ensure that the exhaust temperature remains stable within the target range.

[0215] The control coefficients are optimized based on historical control data and actual adjustment effects.

[0216] Please see Figure 2 As shown, the ship data anomaly management and analysis system based on big data integration includes:

[0217] The data acquisition module, which uses temperature and speed sensors mounted on the surface of the ship engine, is used to collect exhaust temperature and speed data of the ship engine in real time.

[0218] An exhaust temperature anomaly identification module acquires engine exhaust temperature data within a monitoring period according to a time series, calculates an exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient.

[0219] The engine speed anomaly identification module acquires engine speed data within a monitoring period according to a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates the engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient.

[0220] The impact relationship assessment module analyzes historical exhaust temperature data and engine speed data to establish an impact relationship model between exhaust temperature and engine speed anomalies, which is used to assess the degree of impact of engine speed anomalies on exhaust temperature anomalies.

[0221] The dynamic adjustment module, based on the analysis results of the degree of influence, adjusts the engine speed in real time to ensure that the exhaust temperature returns to the normal range, and continuously monitors the coordinated operation of exhaust temperature and speed to ensure stable engine operation.

[0222] The working principle of this invention is as follows: By real-time monitoring and data analysis of the operating parameters of a ship's engine, anomalies are identified and targeted adjustments are made to ensure the stable operation of the engine. The method includes the following steps: First, temperature and speed sensors are installed on the surface of the ship's engine to collect exhaust temperature and speed data in real time. The collected data is preprocessed, including noise removal, missing value imputation, and data standardization to ensure data accuracy and consistency. Second, exhaust temperature data is analyzed through time series analysis to calculate the exhaust temperature anomaly coefficient. The isolated forest algorithm is used to identify whether the exhaust temperature is abnormal. Simultaneously, engine speed data is analyzed for amplitude fluctuations and response time to calculate the speed anomaly coefficient, thereby determining the speed anomaly. Based on this, historical exhaust temperature and speed data are analyzed, and a Bayesian network is used to construct an influence relationship model between exhaust temperature and speed anomalies, quantifying the degree of influence of speed anomalies on exhaust temperature anomalies. Finally, based on the influence relationship analysis results, a target exhaust temperature range and a target speed adjustment range are determined. By real-time adjustment of engine speed, the exhaust temperature is brought back to the normal range. During the adjustment process, the coordinated changes in exhaust temperature and speed are continuously monitored to optimize the adjustment effect. This invention enables comprehensive monitoring, anomaly detection, and intelligent control of the operating status of ship engines, effectively improving the safety and stability of ship operations.

[0223] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0224] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. 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. 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 a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0225] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0226] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 this application.

[0227] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for managing and analyzing ship data anomalies based on big data integration, characterized in that: Includes the following steps: S1: By installing temperature and speed sensors on the surface of the ship engine, the exhaust temperature and speed data of the ship engine are collected in real time, and the collected exhaust temperature and speed data are preprocessed. S2: Obtain the engine exhaust temperature data within a monitoring period according to the time series, calculate the exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identify whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient. S3: Obtain engine speed data within a monitoring period according to the time series, analyze the speed data, analyze the speed fluctuation and response time, calculate the engine speed anomaly coefficient, and identify whether the engine speed is abnormal based on the speed anomaly coefficient; S4: Analyze historical exhaust temperature and speed data to establish a model of the relationship between exhaust temperature and speed anomalies, which is used to assess the degree of influence of engine speed anomalies on exhaust temperature anomalies. S5: Based on the analysis results of the degree of impact, 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 operation of exhaust temperature and speed to ensure stable engine operation. The calculation of the exhaust temperature anomaly coefficient based on the fluctuation of exhaust temperature data specifically includes: Obtain the exhaust temperature dataset within the monitoring period; Calculate the mean, standard deviation, and rate of change of the exhaust temperature dataset; The expression for calculating the rate of change is: ； in, This represents each temperature data collection point. Indicates the first Temperature values ​​at each temperature data collection point. Indicates the first The first collection point and the first Temperature change rate at each sampling point; Calculate the mean and standard deviation of the rate of change based on the rate of change of the exhaust temperature dataset; The local fluctuation value of the exhaust temperature is calculated using the following expression: ； in, Indicates the size of the sliding window. Indicates the first Local fluctuation values ​​at each temperature data collection point; A multidimensional feature vector is constructed from the mean, standard deviation, mean and standard deviation of the rate of change, and local fluctuations of the exhaust temperature dataset. The isolated forest algorithm is used to train the feature vectors, generate multiple isolated trees, and then calculate the anomaly score for 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 for the anomaly score is as follows: ； In the formula, Indicates the first Anomaly rating for each temperature data collection point Indicates the general in an isolated tree Average path length when isolated Indicates the normalization factor; The exhaust temperature anomaly coefficient is obtained by averaging the anomaly scores of all monitoring data points. The calculation expression is as follows: ； In the formula, This indicates the total number of exhaust temperature data collection points. Indicates the exhaust temperature anomaly coefficient; The method of identifying whether the engine speed is abnormal based on the speed anomaly coefficient specifically includes: Engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to determine the fluctuation range of the speed and to calculate the speed fluctuation coefficient to assess the degree of speed fluctuation. The engine speed data within a monitoring period is obtained according to the time series. The speed data is analyzed to analyze the speed response time and calculate the response rate anomaly index to assess the degree of anomaly in the engine speed response. The fluctuation degree of engine speed and the abnormal degree of engine speed response are processed in a comprehensive manner, including: normalizing the engine speed amplitude fluctuation coefficient and the response rate abnormality index, calculating the engine speed abnormality coefficient, comparing the engine speed abnormality coefficient with a preset threshold, and determining whether the engine speed abnormality coefficient is greater than or equal to the preset threshold. If it is, the engine speed is abnormal; otherwise, the engine speed is normal.

2. The ship data anomaly management and analysis method based on big data integration according to claim 1, characterized in that, The process for obtaining the rotational speed fluctuation coefficient is as follows: Acquire engine speed data and preprocess the speed data; The processed rotation speed data is then standardized. Discrete wavelet transform is applied to the standardized rotational speed data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Using wavelet basis and decomposition level, the high-frequency components of the rotational speed data at each scale are obtained. The calculation expression is as follows: ； In the formula, The approximation coefficient represents the low-frequency component. Indicates the number of detail coefficients. Indicates the first These detail coefficients represent the high-frequency components. A dataset representing the high-frequency components of rotational speed data at each scale; For each detail coefficient, calculate the corresponding amplitude: ； In the formula, Indicates the first The magnitude of each detail coefficient, This represents the maximum value of the detail coefficient. This represents the minimum value of the detail coefficient; The overall speed fluctuation coefficient is obtained by weighted averaging the fluctuation amplitudes corresponding to all detail coefficients. The calculation expression is as follows: ； in, Indicates the coefficient of rotational speed fluctuation. This represents the total number of detail coefficients.

3. The ship data anomaly management and analysis method based on big data integration according to claim 1, characterized in that, The process for obtaining the response rate anomaly index is as follows: By collecting real-time speed data of ship engines during the monitoring period, a time series is formed; The rotational speed data is subjected to first-order difference processing to obtain a difference data sequence; Based on the differentiald rotational speed data sequence, the autoregressive order, differencing order, and moving average order are selected, and an autoregressive integral moving average model is constructed. The calculation expression is as follows: ； In the formula, Indicates the order of autoregression. Indicates the order of the moving average. Indicates the time point of data collection. This represents the speed data after differential processing. Represents the white noise term. Represents the autoregressive coefficient. Indicates the moving average coefficient; The constructed autoregressive integral moving average model is used to predict the rotational speed at future times, and the rotational speed at time is calculated. Differential prediction values The differential prediction value is then combined with the known collected rotational speed data to obtain the rotational speed prediction value, calculated as follows: ； In the formula, Indicates the first One rotational speed data, Indicates the first Speed ​​data for each speed; The error between the actual observed rotational speed and the predicted rotational speed is calculated using the following expression: ； In the formula, Indicates the first The error between the actual observed rotational speed and the predicted rotational speed at a given moment All errors are statistically analyzed, and the mean of the errors is calculated. and standard deviation ; The response rate anomaly index is calculated using the following expression: ； In the formula, Indicates the anomaly index of response rate. The standard deviation represents the error. This represents the mean of the error.

4. The ship data anomaly management and analysis method based on big data integration according to claim 1, characterized in that, By analyzing historical exhaust temperature and engine speed data, a model was established to demonstrate the relationship between abnormal exhaust temperature and engine speed. This model specifically includes: Based on the data distribution of historical exhaust temperature anomaly coefficient and speed anomaly coefficient, a Bayesian network is constructed, in which there is a conditional probability relationship between the exhaust temperature anomaly coefficient node and the speed anomaly coefficient node, and the relationship is used to describe the influence 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. The joint probability distribution of the exhaust temperature anomaly coefficient and the speed anomaly coefficient is calculated based on the conditional probability formula. The conditional probability formula is: ； In the formula, Indicates the exhaust temperature anomaly coefficient. Indicates the speed anomaly coefficient. Represents the conditional probability distribution. This represents the marginal probability distribution of abnormal rotational speed. Based on the conditional probability distribution and marginal probability distribution, the influence coefficient of abnormal speed on abnormal exhaust temperature is calculated, and the calculation expression is as follows: ； In the formula, Indicates the degree of influence coefficient. This represents the marginal probability of an abnormal exhaust temperature. This indicates the probability of abnormal exhaust temperature under abnormal speed conditions; The influence relationship coefficient is used as the output of the influence relationship model to evaluate the degree of influence of abnormal speed on abnormal exhaust temperature.

5. The ship data anomaly management and analysis method based on big data integration according to claim 1, characterized in that, The assessment of the impact of abnormal engine speed on abnormal exhaust temperature specifically includes: Determine whether the influence coefficient is greater than or equal to a preset threshold. If it is, the abnormal engine speed has an impact on the abnormal exhaust temperature, and this is recorded as an influence signal. If not, the abnormal engine speed does not have an impact on the abnormal exhaust temperature, and this is recorded as a non-influence signal.

6. The ship data anomaly management and analysis method based on big data integration according to claim 1, characterized in that, Based on the analysis results of the degree of impact, ensuring that the exhaust temperature returns to the normal range by adjusting the engine speed in real time specifically includes: Based on the influence signals, the target normal range of exhaust temperature and the target range of engine speed that need to be adjusted are determined according to the exhaust temperature anomaly coefficient and the influence relationship degree coefficient. The process for determining the target normal range of the exhaust temperature is as follows: Analyze exhaust temperature data under historical normal operating conditions and calculate the mean and standard deviation of the exhaust temperature data; The target exhaust temperature range is calculated using the following formula: ； In the formula, The standard configuration is the target exhaust temperature range. Represents the confidence coefficient. This represents the mean of exhaust data. This represents the standard deviation of exhaust data; Based on the historical relationship between exhaust temperature and engine speed, a regression expression for exhaust temperature and engine speed is constructed: And based on the target exhaust temperature range, the corresponding target speed range is solved inversely, and the calculation expression is: ； In the formula, Indicates the target speed range. Indicates exhaust temperature. Indicates rotational 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 as follows: ； In the formula, This represents the mean of the rotational speed data. The standard deviation of the rotational speed data This represents the adjustment coefficient based on historical speed fluctuation data. Indicates the scope of the target adjustment; Based on the real-time monitored engine speed and exhaust temperature data, the adjustment amount is calculated using the following expression: ； In the formula, Indicates the adjustment amount. Indicates the control coefficient. This indicates real-time exhaust temperature data; To perform speed control and adjust the current engine speed, the calculation expression is: ； In the formula, This 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 speed to exhaust temperature after adjustment is recorded to ensure that the exhaust temperature remains stable within the target range. The control coefficients are optimized based on historical control data and actual adjustment effects.

7. A ship data anomaly management and analysis system based on big data integration, characterized in that: The method for ship data anomaly management and analysis based on big data integration as described in any one of claims 1-6 includes: The data acquisition module, which uses temperature and speed sensors mounted on the surface of the ship engine, is used to collect exhaust temperature and speed data of the ship engine in real time. An exhaust temperature anomaly identification module acquires engine exhaust temperature data within a monitoring period according to a time series, calculates an exhaust temperature anomaly coefficient based on the fluctuation of the exhaust temperature data, and identifies whether the exhaust temperature is abnormal based on the exhaust temperature anomaly coefficient. The engine speed anomaly identification module acquires engine speed data within a monitoring period according to a time series, analyzes the speed data, analyzes the speed fluctuation amplitude and response time, calculates the engine speed anomaly coefficient, and identifies whether the engine speed is abnormal based on the speed anomaly coefficient. The impact relationship assessment module analyzes historical exhaust temperature data and engine speed data to establish an impact relationship model between exhaust temperature and engine speed anomalies, which is used to assess the degree of impact of engine speed anomalies on exhaust temperature anomalies. The dynamic adjustment module, based on the analysis results of the degree of influence, adjusts the engine speed in real time to ensure that the exhaust temperature returns to the normal range, and continuously monitors the coordinated operation of exhaust temperature and speed to ensure stable engine operation.

Images