A method and system for extracting characteristic values of ship main engine operating conditions

Abstract

The present invention provides a method and system for extracting characteristic values of the operating conditions of a ship's main engine. The method includes a data collection and judgment step, a correlation calculation step, a working condition division step and a characteristic value extraction step. Based on correlation analysis, a specific calculation method is adopted to calculate the characteristic parameter with the highest correlation with the main engine power, the data range of the characteristic parameter is determined based on the confidence interval, and the working condition is divided for the data within the data range based on the Gaussian mixture model clustering algorithm. This method can effectively improve the main engine working condition division capability and more finely divide the main engine working condition under normal operation of the ship.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for extracting characteristic values of operating conditions of a ship's main engine. Background Art

[0002] The daily operating costs of ships are extremely high, and effective operating time determines the profitability of shipowners. A ship's main engine is the core power plant, and it is inevitable that it will experience some failures during use. These failures will seriously affect the normal operation of the ship, affecting not only the normal operation of the equipment but also causing accidents and even endangering personal safety in serious cases.

[0003] The operating status of a ship's main engine is a crucial indicator of its navigational status. Current research on main engines, both domestically and internationally, primarily focuses on fault analysis and prediction. However, limited research has focused on identifying different operating conditions and conducting fault analysis accordingly. This limited research still suffers from issues such as an inability to precisely categorize main engine operating conditions under normal ship operation, slow classification, and inadequate consideration.

[0004] The identification of the operating status of the ship's main engine is the basis of fault analysis. The changes in the main engine's operating conditions will be affected by temperature and machine aging. For example, the operating conditions of a ship during its initial operation are different from those of a ship that has been in operation for many years. Therefore, dividing the reasonable operating conditions of the ship's main engine based on actual ship data can lay the foundation for determining the ship's pollutant emissions, estimating fuel consumption, evaluating the main engine's performance, and diagnosing and predicting faults of the main engine's key equipment, providing a reference basis for ship equipment management and maintenance.

[0005] The operation of the main engine is a coupled process. The main equipment will affect each other, causing changes in the operating conditions. However, it is difficult for actual ships to fully output the parameters required by the main engine operation physical model. Therefore, according to the existing methods, this operating condition division is somewhat difficult. Summary of the Invention

[0006] To address the existing problems of insufficiently refined classification and low efficiency in the process of main engine operating condition classification and feature extraction, the present invention provides a method for extracting characteristic values of ship main engine operating conditions. Based on correlation analysis, a specific calculation method is used to calculate the characteristic parameters with the highest correlation with main engine power. The data range of the characteristic parameters is determined based on the confidence interval, and the data within the data range is classified into operating conditions based on a Gaussian mixture model. This method can effectively improve the main engine operating condition classification capability and more finely classify the main engine operating conditions under normal ship operation. The present invention also relates to a system for extracting characteristic values of ship main engine operating conditions.

[0007] The technical solutions of the present invention are as follows:

[0008] A method for extracting characteristic values of ship main engine operating conditions, characterized by comprising the following steps:

[0009] Data collection and judgment steps: obtaining ship data, and filtering the main engine speed and water speed in the ship data according to preset filtering conditions, and judging the ship in a stable operating state based on the main engine speed and water speed that meet the preset filtering conditions;

[0010] Correlation calculation steps: When the ship is in a stable operating state, multiple characteristic parameters are selected from the ship data, and the correlation between each characteristic parameter and the main engine power in the ship data is calculated respectively, and the characteristic parameter with the greatest correlation with the main engine power is extracted as the relevant characteristic parameter;

[0011] Operating condition division step: establishing a confidence interval based on relevant characteristic parameters, dividing the confidence interval according to a preset confidence level, determining the confidence interval range of the relevant characteristic parameters, and using a Gaussian mixture model clustering algorithm to divide the data within the confidence interval into operating conditions to divide multiple host operating conditions;

[0012] Feature value extraction step: extract the feature values of each host operating condition respectively to analyze the specific situation of each host operating condition.

[0013] Preferably, in the data collection and judgment step, the preset screening conditions are specifically set according to the main engine speed at a certain moment, the water speed at a certain moment, the main engine maximum speed and the design speed;

[0014] When the ratio of the main engine speed at a certain moment to the maximum main engine speed is greater than the preset speed threshold, and the ratio of the waterspeed to the design speed at a certain moment is greater than the preset speed threshold, if the difference percentages calculated between the main engine speed at a certain moment, the main engine speed at the next moment, and the main engine speed at the next moment are less than or equal to the preset threshold, then it is determined that the main engine speed and the waterspeed at a certain moment are the main engine speed and the waterspeed that meet the preset screening conditions.

[0015] Preferably, in the correlation calculation step, the characteristic parameters include any combination of the ship's water speed, main engine speed, average draft, actual wind speed encountered by the ship, speed over ground, main engine scavenge box average temperature, main engine cylinder exhaust outlet temperature, main engine cylinder liner cooling water outlet temperature and main engine cylinder piston lubricating oil outlet temperature.

[0016] Preferably, in the feature value extraction step, the feature value includes an average value of relevant feature parameters, a standard deviation of relevant feature parameters, a power average value, and a power standard deviation.

[0017] Preferably, in the working condition division step, the preset confidence level is 75% of the relevant characteristic parameters.

[0018] A system for extracting characteristic values of operating conditions of ship main engines is characterized by comprising a data acquisition and judgment module, a correlation calculation module, an operating condition division module and a characteristic value extraction module connected in sequence.

[0019] Data acquisition and judgment module: acquires ship data, and filters the main engine speed and water speed in the ship data according to preset screening conditions, and judges the ship in a stable operating state based on the main engine speed and water speed that meet the preset screening conditions;

[0020] Correlation calculation module: When the ship is in a stable operating state, multiple characteristic parameters are selected from the ship data, and the correlation between each characteristic parameter and the main engine power in the ship data is calculated respectively. The characteristic parameter with the greatest correlation with the main engine power is extracted as the relevant characteristic parameter;

[0021] Operating condition classification module: establishes confidence intervals based on relevant characteristic parameters, divides the confidence intervals according to preset confidence levels, determines the confidence interval ranges of relevant characteristic parameters, and uses the Gaussian mixture model clustering algorithm to classify the data within the confidence intervals into multiple host operating conditions;

[0022] Eigenvalue extraction module: extracts the eigenvalues of each host operating condition respectively to analyze the specific situation of each host operating condition.

[0023] Preferably, in the data collection and judgment module, the preset screening conditions are specifically set according to the main engine speed at a certain moment, the water speed at a certain moment, the main engine maximum speed and the design speed;

[0024] When the ratio of the main engine speed at a certain moment to the maximum main engine speed is greater than the preset speed threshold, and the ratio of the waterspeed to the design speed at a certain moment is greater than the preset speed threshold, if the difference percentages calculated between the main engine speed at a certain moment, the main engine speed at the next moment, and the main engine speed at the next moment are less than or equal to the preset threshold, then it is determined that the main engine speed and the waterspeed at a certain moment are the main engine speed and the waterspeed that meet the preset screening conditions.

[0025] Preferably, the characteristic parameters include any combination of the ship's water speed, main engine speed, average draft, actual wind speed encountered by the ship, ground speed, main engine scavenge box average temperature, main engine cylinder exhaust outlet temperature, main engine cylinder liner cooling water outlet temperature and main engine cylinder piston lubricating oil outlet temperature.

[0026] Preferably, the characteristic values include an average value of relevant characteristic parameters, a standard deviation of relevant characteristic parameters, a power average value, and a power standard deviation.

[0027] Preferably, the preset confidence level is 75% of the relevant characteristic parameters.

[0028] The beneficial effects of the present invention are:

[0029] The present invention provides a method for extracting characteristic values of ship main engine operating conditions. This method is essentially based on correlation analysis, confidence level, and Gaussian mixture model cluster analysis. By using specific screening conditions to identify ships in a stable operating state and employing a specific calculation method to determine the characteristic parameters with the highest correlation coefficient with the ship main engine power, the method can rapidly determine the characteristic parameters with a high correlation with the main engine. Furthermore, based on the confidence interval and Gaussian mixture model clustering algorithm, the method can rapidly screen the main engine's operating interval data, identify complex discrete points that interfere with the main engine operating condition classification, rapidly classify the main engine operating conditions, and calculate the characteristic values of each condition. This method effectively improves the ability to classify main engine operating conditions, enabling a more refined classification of the main engine operating conditions under normal ship operation.

[0030] The present invention also relates to a system for extracting characteristic values of ship main engine operating conditions, which corresponds to the above-mentioned method for extracting characteristic values of ship main engine operating conditions, and can be understood as a system for implementing the above-mentioned method for extracting characteristic values of ship main engine operating conditions, comprising a data acquisition and judgment module, a correlation calculation module, a working condition division module and a characteristic value extraction module connected in sequence, wherein each module works in coordination with each other, and judges a ship in a stable operating state by adopting specific screening conditions, calculates characteristic parameters with the largest correlation coefficient with the ship main engine power based on correlation analysis by adopting a specific calculation method, determines the data range of the characteristic parameters based on the confidence interval, and divides the data within the data range into working conditions based on the Gaussian mixture model clustering algorithm, which can effectively improve the main engine working condition division capability and more finely divide the main engine working conditions under normal operation of the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the method for extracting characteristic values of ship main engine operating conditions of the present invention.

[0032] Figure 2 This is a preferred flow chart of the method for extracting characteristic values of ship main engine operating conditions of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be described below with reference to the accompanying drawings.

[0034] The present invention relates to a method for extracting characteristic values of ship main engine operating conditions, the flow chart of which is as follows: Figure 1 As shown, the following steps are included in sequence:

[0035] The data collection and judgment step obtains ship data, and filters the main engine speed and water speed in the ship data according to preset filtering conditions, and judges the ship in a stable operating state based on the main engine speed and water speed that meet the preset filtering conditions;

[0036] Specifically, if Figure 2 The preferred flow chart shown in FIG. 1 is based on the preset screening conditions according to the host speed Rpm at a certain moment (i.e., moment i). i , the water speed Vs at a certain moment (i.e., moment i) i 、Maximum speed of host machine Ppm max and design speed V design Make settings;

[0037] The engine speed Rpm at time i i , and the maximum speed of the host Rpm max The ratio of is greater than the preset speed threshold, and the water speed Vs at time i i and design speed V design When the ratio is greater than the preset speed threshold, for example, the preset speed threshold is 0.5 (it can also be preset to other values), the preset speed threshold is 0.5 (it can also be preset to other values), that is, Rpm i >0.5*Rpm max , and Vs i >0.5*V design hour,

[0038] If the difference percentages between the engine speed at a certain moment, the engine speed at the next moment, and the engine speed at the next moment are less than or equal to a preset threshold, for example, the preset threshold is 0.05 (it can also be preset to other values), that is, Rpm i -Rpm i+1 | / Rpm i ≤0.05, and |Rpm i -Rpm i+2 | / Rpm i ≤0.05, and |Rpm i+2 -Rpm i+1 | / Rpm i+1 When ≤0.05, the main engine speed and water speed at a certain moment (i.e., moment i) are determined to be the main engine speed and water speed that meet the preset screening conditions.

[0039] Correlation calculation steps: When the ship is in a stable operating state, multiple characteristic parameters are selected from the ship data, and the correlation between each characteristic parameter and the main engine power in the ship data is calculated respectively, and the characteristic parameter with the greatest correlation with the main engine power is extracted as the relevant characteristic parameter;

[0040] The correlation between each characteristic parameter and the host power y is calculated according to the correlation coefficient r calculation formula, which is as follows:

[0041]

[0042] In the above formula, n is the total number of ship data, x is any one of the multiple characteristic parameters, and y is the main engine power.

[0043] Preferably, the characteristic parameters include the ship's water speed V s , main engine speed RPM, average draft, actual wind speed V encountered by the ship w , Ground Speed V g , Average temperature of main engine scavenging box T scav , Main engine cylinder exhaust outlet temperature T ge , Main engine cylinder liner cooling water outlet temperature T cfw And the main engine cylinder piston oil outlet temperature T pco Any combination of real ship data points.

[0044] Assume that, according to the correlation calculation, it is determined that a certain characteristic parameter A (for example, the RPM of the main engine) and the main engine power have the highest correlation.

[0045] Working condition division step: This step introduces a confidence interval to conduct a secondary screening of the actual ship data, determine the confidence level (preferably 75%, but can also be set to other values), thereby eliminating discrete points that affect the working condition division and determining the data range of the relevant characteristic parameters. A confidence interval is established based on the relevant characteristic parameters, and the confidence interval is divided according to a preset confidence level (preferably 75%). The discrete points that affect the working condition division are eliminated, and the confidence interval range [LL, HH] of the relevant characteristic parameter A is determined, that is, [LL, HH] is the range interval of the characteristic parameter A of the main engine under normal operation; and the Gaussian mixture model clustering algorithm is used to divide the data within the confidence interval range [LL, HH] into multiple (m) main engine working conditions, that is, the range [LL, HH] of the relevant characteristic parameter A is divided into m main engine working conditions. Among them, the input parameters of the Gaussian mixture model clustering algorithm are the characteristic parameter A determined above and the main engine power.

[0046] The Gaussian mixture model (GMM) clustering algorithm assumes that all data are generated from a mixture of a finite number of Gaussian distributions with unknown parameters. This is a probability model based on maximum likelihood estimation. The Gaussian mixture model can be viewed as a combination of M single Gaussian probability density functions, each with a corresponding mean and covariance, to incorporate information about the data covariance structure and potential Gaussian centers.

[0047] Its expression is as follows:

[0048]

[0049] In the above formula, p(x) is the probability density function of M Gaussians, N(x|μ k ,∑ k ) is the Gaussian distribution density function of the kth sub-model; μ k is the sample mean of the kth sub-model, ∑ k is the covariance of the kth sub-model; π k is the weight of the kth Gaussian distribution and satisfies the constraints of formula (3).

[0050]

[0051] Solve formula (2) and find the probability of each data point in the M models, which is the weight. The distribution range of the M models is determined based on the weights of all data points.

[0052] Feature value extraction step: Extract the feature values of each of the m main engine operating conditions. This involves extracting the average value, standard deviation, average power, and standard deviation of the relevant feature parameters under each main engine operating condition to analyze the specific operating conditions of each main engine. For example, extract the average value, standard deviation, average power, and standard deviation of feature parameter A under five operating conditions.

[0053] The present invention also relates to a system for extracting characteristic values of operating conditions of ship main engines. The system corresponds to the above-mentioned method for extracting characteristic values of operating conditions of ship main engines and can be understood as a system for implementing the above-mentioned method. The system includes a data acquisition and judgment module, a correlation calculation module, an operating condition division module and a characteristic value extraction module connected in sequence. Specifically,

[0054] The data acquisition and judgment module obtains ship data and filters the main engine speed and water speed in the ship data according to preset screening conditions, and judges the ship in a stable operating state based on the main engine speed and water speed that meet the preset screening conditions;

[0055] The correlation calculation module selects multiple characteristic parameters from the ship data when the ship is in a stable operating state, calculates the correlation between each characteristic parameter and the main engine power in the ship data, and extracts the characteristic parameter with the greatest correlation with the main engine power as the relevant characteristic parameter;

[0056] An operating condition classification module establishes a confidence interval based on relevant characteristic parameters, divides the confidence interval according to a preset confidence level, determines the confidence interval range of the relevant characteristic parameters, and uses a Gaussian mixture model clustering algorithm to classify the data within the confidence interval into multiple host operating conditions;

[0057] The feature value extraction module extracts the feature values of each host operating condition to analyze the specific situation of each host operating condition.

[0058] Preferably, in the data collection and judgment module, the preset screening conditions are specifically set according to the main engine speed at a certain moment, the water speed at a certain moment, the main engine maximum speed and the design speed;

[0059] When the ratio of the main engine speed at a certain moment to the maximum main engine speed is greater than the preset speed threshold, and the ratio of the waterspeed to the design speed at a certain moment is greater than the preset speed threshold, if the difference percentages calculated between the main engine speed at a certain moment, the main engine speed at the next moment, and the main engine speed at the next moment are less than or equal to the preset threshold, then it is determined that the main engine speed and the waterspeed at a certain moment are the main engine speed and the waterspeed that meet the preset screening conditions.

[0060] Preferably, the characteristic parameters include any combination of the ship's water speed, main engine speed, average draft, actual wind speed encountered by the ship, ground speed, main engine scavenge box average temperature, main engine cylinder exhaust outlet temperature, main engine cylinder liner cooling water outlet temperature and main engine cylinder piston lubricating oil outlet temperature.

[0061] Preferably, the characteristic values include an average value of relevant characteristic parameters, a standard deviation of relevant characteristic parameters, a power average value, and a power standard deviation.

[0062] Preferably, the preset confidence level is 75% of the relevant characteristic parameters.

[0063] The present invention provides an objective and scientific method and system for extracting characteristic values of ship main engine operating conditions. By adopting specific screening conditions to judge a ship in a stable operating state, and adopting a specific calculation method to calculate the characteristic parameters with the largest correlation coefficient with the ship main engine power, the characteristic parameters with a high correlation with the main engine can be quickly determined. At the same time, based on the confidence interval and Gaussian mixture model clustering algorithm, the main operating range data of the ship main engine can be quickly screened, the main engine operating conditions can be quickly divided, and the characteristic values of each operating condition can be calculated, which effectively improves the main engine operating condition division capability and can more finely divide the main engine operating conditions under normal operation of the ship.

[0064] It should be noted that the specific embodiments described above can enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although this specification has described the present invention in detail with reference to the drawings and embodiments, those skilled in the art should understand that the present invention can still be modified or replaced with equivalents. In short, all technical solutions and improvements that do not depart from the spirit and scope of the present invention should be included in the scope of protection of the patent for the present invention.

Claims

1. A method for extracting characteristic values of ship main engine operating conditions, characterized in that: The following steps are involved: Data collection and judgment steps: obtaining ship data, and filtering the main engine speed and water speed in the ship data according to preset filtering conditions, and judging the ship in a stable operating state based on the main engine speed and water speed that meet the preset filtering conditions; Correlation calculation steps: When the ship is in a stable operating state, multiple characteristic parameters are selected from the ship data, and the correlation between each characteristic parameter and the main engine power in the ship data is calculated respectively, and the characteristic parameter with the greatest correlation with the main engine power is extracted as the relevant characteristic parameter; The operating condition classification step includes establishing a confidence interval based on the relevant characteristic parameters, dividing the confidence interval according to a preset confidence level of 75%, eliminating discrete points that affect the operating condition classification, determining the confidence interval range of the relevant characteristic parameters of the main engine under normal operation, and using a Gaussian mixture model clustering algorithm to classify the data within the confidence interval into multiple main engine operating conditions; the input parameters of the Gaussian mixture model clustering algorithm are the relevant characteristic parameters and the main engine power; Feature value extraction step: extract the feature values of each host operating condition respectively to analyze the specific situation of each host operating condition.

2. The method for extracting characteristic values of ship main engine operating conditions according to claim 1, characterized in that: In the data collection and judgment step, the preset screening conditions are specifically set according to the main engine speed at a certain moment, the water speed at a certain moment, the main engine maximum speed and the design speed; When the ratio of the main engine speed at a certain moment to the maximum main engine speed is greater than the preset speed threshold, and the ratio of the waterspeed to the design speed at a certain moment is greater than the preset speed threshold, if the difference percentages calculated between the main engine speed at a certain moment, the main engine speed at the next moment, and the main engine speed at the next moment are less than or equal to the preset threshold, then it is determined that the main engine speed and the waterspeed at a certain moment are the main engine speed and the waterspeed that meet the preset screening conditions.

3. The method for extracting characteristic values of ship main engine operating conditions according to claim 1, characterized in that: In the correlation calculation step, the characteristic parameters include any combination of the ship's water speed, main engine speed, average draft, actual wind speed encountered by the ship, ground speed, main engine scavenge box average temperature, main engine cylinder exhaust outlet temperature, main engine cylinder liner cooling water outlet temperature and main engine cylinder piston lubricating oil outlet temperature.

4. The method for extracting characteristic values of ship main engine operating conditions according to claim 1, characterized in that: In the feature value extraction step, the feature values include the average value of relevant feature parameters, the standard deviation of relevant feature parameters, the power average value and the power standard deviation.

5. A system for extracting characteristic values of ship main engine operating conditions, characterized in that: It includes a data acquisition and judgment module, a correlation calculation module, a working condition division module and a characteristic value extraction module connected in sequence. Data acquisition and judgment module: acquires ship data, and filters the main engine speed and water speed in the ship data according to preset screening conditions, and judges the ship in a stable operating state based on the main engine speed and water speed that meet the preset screening conditions; Correlation calculation module: When the ship is in a stable operating state, multiple characteristic parameters are selected from the ship data, and the correlation between each characteristic parameter and the main engine power in the ship data is calculated respectively. The characteristic parameter with the greatest correlation with the main engine power is extracted as the relevant characteristic parameter; Operating condition classification module: Confidence intervals are established based on relevant characteristic parameters, and the confidence intervals are divided according to a preset confidence level of 75%. Discrete points that affect the operating condition classification are eliminated, and the confidence interval range of the relevant characteristic parameters of the main engine under normal operation is determined. The data within the confidence interval is then classified into multiple main engine operating conditions using a Gaussian mixture model clustering algorithm. The input parameters of the Gaussian mixture model clustering algorithm are the relevant characteristic parameters and the main engine power. Eigenvalue extraction module: extracts the eigenvalues of each host operating condition respectively to analyze the specific situation of each host operating condition.

6. The system for extracting characteristic values of ship main engine operating conditions according to claim 5, characterized in that: In the data collection and judgment module, the preset screening conditions are specifically set according to the main engine speed at a certain moment, the water speed at a certain moment, the main engine maximum speed and the design speed; When the ratio of the main engine speed at a certain moment to the maximum main engine speed is greater than the preset speed threshold, and the ratio of the waterspeed to the design speed at a certain moment is greater than the preset speed threshold, if the difference percentages calculated between the main engine speed at a certain moment, the main engine speed at the next moment, and the main engine speed at the next moment are less than or equal to the preset threshold, then it is determined that the main engine speed and the waterspeed at a certain moment are the main engine speed and the waterspeed that meet the preset screening conditions.

7. The system for extracting characteristic values of ship main engine operating conditions according to claim 5, characterized in that: The characteristic parameters include any combination of the ship's water speed, main engine speed, average draft, actual wind speed encountered by the ship, ground speed, main engine scavenge box average temperature, main engine cylinder exhaust outlet temperature, main engine cylinder liner cooling water outlet temperature and main engine cylinder piston lubricating oil outlet temperature.

8. The system for extracting characteristic values of ship main engine operating conditions according to claim 5, characterized in that: The characteristic values include an average value of relevant characteristic parameters, a standard deviation of relevant characteristic parameters, a power average value, and a power standard deviation.

Images