Method for predicting fuel consumption of ocean-going vessels based on big data

Abstract

The present invention provides an ocean - going ship fuel consumption prediction method based on big data, belonging to the field of data prediction; it solves the problem of complex data prediction; specifically as follows: Step S1: Obtain ship data and climate data, and obtain fuel consumption information; Step S2: Process the ship data and climate data, combine the fuel consumption information, calculate the correlation coefficient, analyze and judge the correlation coefficient to obtain influencing parameters; Step S3: According to the influencing parameters, obtain the acting force of the influencing parameters on the ship, integrate the acting forces to obtain the propulsion force, and perform regression analysis based on the propulsion force and the fuel consumption information to construct a fuel consumption prediction model; Step S4: Predict the fuel consumption of the ship according to the fuel consumption prediction model, perform real - time analysis on the fuel consumption of the ship, and give an early warning when the fuel consumption is abnormal; The present invention predicts the fuel consumption of ocean - going ships, provides data reference for ocean - going ships, and ensures the safe operation of ocean - going ships.

Description

Technical Field

[0001] The fuel consumption prediction method for ocean - going ships based on big data of the present invention relates to the field of data prediction. Background Art

[0002] The existing fuel consumption prediction methods for ocean - going ships have the following deficiencies:

[0003] Incomplete data: The data generated during the navigation of ocean - going ships is huge and complex, including various factors such as navigation speed, position, climate, load, etc.; the data of existing inventions is often incomplete, posing challenges to fuel consumption prediction;

[0004] Insufficient data pre - processing: Existing inventions often have insufficient pre - processing of data, affecting the accuracy and stability of subsequent prediction models;

[0005] Excessive model simplification: Existing fuel consumption prediction models are often based on some simplified assumptions and formulas, such as speed - power models, thrust - power models. Although these models can reflect the relationship between fuel consumption and certain factors to a certain extent, they often ignore the influence of other important factors, such as the specific design of the ship and the change of climate conditions. Summary of the Invention

[0006] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a fuel consumption prediction method for ocean - going ships based on big data, aiming to solve the problem of complex data prediction.

[0007] To achieve the above - mentioned purpose, the present invention is realized through the following technical solutions: A fuel consumption prediction method for ocean - going ships based on big data, the prediction method includes:

[0008] Step S1: Obtain ship data, climate data, and obtain fuel consumption information;

[0009] Step S2: According to the ship data and climate data, obtain ship parameters and climate parameters, process the ship parameters and climate parameters, extract the outliers in the ship parameters and climate parameters, combine the fuel consumption information, calculate the correlation coefficients of the ship parameters and climate parameters, analyze and judge the correlation coefficients, and obtain the influencing parameters;

[0010] Step S3: Obtain the acting force of the influencing parameters on the ship, conduct a force analysis on the acting force received by the ship, obtain the total acting force, and conduct a regression analysis according to the total acting force and the fuel consumption information to construct a fuel consumption prediction model;

[0011] Step S4: According to the fuel consumption prediction model, conduct navigation prediction and real - time prediction on the fuel consumption of the ship, and give an alarm for abnormal fuel consumption generated during the navigation process.

[0012] Furthermore, the specific steps of step S2 are as follows:

[0013] Step S21: Process the ship data and climate data to obtain ship parameters and climate parameters, perform numerical analysis on the ship parameters and climate parameters to obtain the distribution status of the ship parameters and climate parameters, and extract outliers from the ship parameters and climate parameters according to the distribution status;

[0014] Step S22: Calculate the means of the ship parameters and climate parameters based on the processed data, and combine with the fuel consumption information to calculate the correlation coefficients of the ship parameters, climate parameters and fuel consumption;

[0015] Step S23: Analyze and judge the correlation coefficients, and extract the ship parameters and climate parameters with large correlation coefficients to obtain the influencing parameters.

[0016] Further, the specific steps of step S21 are as follows:

[0017] Step S211: Obtain the ship parameter type y, obtain the data of x ships according to the ship data to get the ship parameters cb(i, cy), 0 < cy ≤ y, where cy refers to the specific ship parameter type; obtain the climate type z that the ship is subject to, and obtain the climate influence on x ships according to the climate data to get the climate parameters qh(i, qz), 0 < qz ≤ z, where qz refers to the specific ship parameter type, and i refers to the i-th ship;

[0018] Step S212: Perform numerical analysis on the ship parameters cb(i, cy) and the climate parameters qh(i, qz), and judge whether the parameters conform to the normal distribution according to the analysis results;

[0019] Step S213: Extract outliers according to the judgment results;

[0020] If the parameters conform to the normal distribution, extract outliers according to the 3σ principle;

[0021] If the parameters do not conform to the normal distribution, extract outliers according to the Isolation Forest method.

[0022] Further, the specific steps of step S212 are as follows:

[0023] Step S2121: Calculate the mean of the ship parameters to obtain the ship parameter mean μ(cy);

[0024]

[0025] Step S2122: Calculate the standard deviation of the ship parameters based on the ship parameters and combined with the ship parameter mean to obtain the ship parameter standard deviation σ(cy):

[0026]

[0027] Step S2123: Obtain the kurtosis FD(cy) and skewness PD(cy) of the ship parameters by calculating the kurtosis and skewness of the ship parameters based on the mean value μ(cy) and standard deviation σ(cy) of the ship parameters:

[0028]

[0029] Step S2124: Analyze and judge the ship parameters according to the kurtosis FD(cy) and skewness PD(cy) of the ship parameters:

[0030] If -2 ≤ FD(cy) ≤ 2 and -0.5 ≤ PD(cy) ≤ 0.5, the ship parameters conform to the normal distribution;

[0031] If FD(cy) > 2 or FD(cy) < -2 or PD(cy) > 0.5 or PD(cy) < -0.5, the ship parameters do not conform to the normal distribution.

[0032] Furthermore, the step S212 also includes:

[0033] Step S2125: Calculate the mean value of the climate parameters to obtain the mean value μ(qz) of the climate parameters;

[0034] Step S2126: Calculate the standard deviation of the climate parameters according to the climate parameters and in combination with the mean value of the climate parameters to obtain the standard deviation σ(qz) of the climate parameters;

[0035] Step S2127: Obtain the kurtosis FD(qz) and skewness PD(qz) of the climate parameters by calculating the kurtosis and skewness of the climate parameters based on the mean value μ(qz) and standard deviation σ(qz) of the climate parameters;

[0036] Judge the data distribution of the climate parameters by calculating the kurtosis and skewness of the climate parameters, and extract the parameters that conform to the normal distribution according to the data of kurtosis and skewness;

[0037] Step S2128: Analyze and judge the climate parameters according to the kurtosis FD(qz) and skewness PD(qz) of the climate parameters:

[0038] If -2 ≤ FD(qz) ≤ 2 and -0.5 ≤ PD(qz) ≤ 0.5, the climate parameters conform to the normal distribution;

[0039] If FD(qz) > 2 or FD(qz) < -2 or PD(qz) > 0.5 or PD(qz) < -0.5, the climate parameters do not conform to the normal distribution.

[0040] Further, the specific steps of step S22 are as follows:

[0041] Step S221: According to the fuel consumption information, obtain the fuel consumption YH(i, cy, qz) of the ship, and calculate the average fuel consumption of the ship when the climate is different and the average fuel consumption when the ship data is different respectively, to obtain the average ship fuel consumption CJZ and the average climate fuel consumption QJZ;

[0042] The calculation process of the average ship fuel consumption CJZ is as follows:

[0043]

[0044] YH(i, cy, qz) refers to the fuel consumption of the i-th ship, under the cy-th ship parameter, and under the influence of the qz-th climate. x refers to the number of ships, and z refers to the type of climate;

[0045] The calculation process of the average climate fuel consumption QJZ is as follows:

[0046]

[0047] Among them, y refers to the type of ship parameters;

[0048] Step S222: Obtain the ship parameter cb(i, cy) and the climate parameter qh(i, qz), and calculate the average ship parameter J(cy) and the average climate parameter J(qz);

[0049]

[0050] Step S223: According to the ship parameter cb(i, cy), the average ship parameter J(cy), the fuel consumption YH(i, cy, qz) of the ship, and the average ship fuel consumption CJZ, calculate the correlation between the ship parameter and the ship fuel consumption, to obtain the correlation coefficient XG(cy);

[0051]

[0052] Step S224: According to the climate parameter qh(i, qz), the average climate parameter J(qz), the fuel consumption YH(i, cy, qz) of the ship, and the average climate fuel consumption CJZ, calculate the correlation between the climate parameter and the ship fuel consumption, to obtain the correlation coefficient XG(qz);

[0053]

[0054] Further, the subsequent steps of step S23 are as follows:

[0055] Step S231: Obtain the correlation coefficient threshold t, where 0 < t ≤ 1. Obtain the correlation coefficient XG(cy) between the ship parameters and the ship fuel consumption. Combine the correlation coefficient threshold t to judge and analyze XG(cy):

[0056] If |XG(cy)| ≥ t, then this ship parameter belongs to the influencing parameter, and extract this ship parameter;

[0057] If |XG(cy)| < t, then this ship parameter does not belong to the influencing parameter;

[0058] Step S232: Obtain the correlation coefficient XG(qz) between the climate parameters and the ship fuel consumption. Combine the correlation coefficient threshold t to judge and analyze XG(qz):

[0059] If |XG(qz)| ≥ t, then this climate parameter belongs to the influencing parameter, and extract this climate parameter;

[0060] If |XG(qz)| < t, then this climate parameter does not belong to the influencing parameter.

[0061] Furthermore, the specific steps of step S3 are as follows:

[0062] Step S31: Obtain the acting forces F(i, cy) and F(i, qz) of the influencing parameters on the ship; obtain the angles θ cy 、θ qz , obtain the friction coefficient xs of the hull; integrate the acting forces to obtain the total acting force zF i ;

[0063] zF i = F(i, cy) cosθ cy + xs × F(i, cy) sinθ cy + F(i, qz) cosθ qz + xs × F(i, qz) sinθ qz ;

[0064] Step S32: According to the fuel consumption information, obtain the fuel consumption xh i , combine the total acting force to construct a data set of the total acting force zF i and the fuel consumption xh i . Process the data set by least squares to obtain the first parameter k and the second parameter v of the fuel consumption prediction model;

[0065] According to the first parameter k and the second parameter v, construct the fuel consumption prediction model to obtain the fuel consumption prediction model. The fuel consumption prediction model is as follows:

[0066] xh = k × zF + v

[0067] xh is the fuel consumption variable of the fuel consumption prediction model, and zF is the total force variable of the fuel consumption prediction model.

[0068] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0069] Improve the data range: The present invention obtains hull data through sensors and recording devices, obtains climate data through meteorological bureaus, ocean observation stations or professional meteorological service agencies, and analyzes and judges the hull data and climate data;

[0070] Strengthen data preprocessing: The present invention respectively judges various types of data through numerical analysis, and extracts outliers according to the judgment results using the 3σ principle or the isolation forest method;

[0071] Optimize model parameters: The present invention obtains the correlation values between ship parameters and fuel consumption through ship parameters, the mean value of ship parameters, the fuel consumption of the ship, and the mean value of ship fuel consumption, and obtains the correlation values between climate parameters and fuel consumption through climate parameters, the mean value of climate parameters, the fuel consumption of the ship, and the mean value of ship fuel consumption. According to the magnitudes of the correlation values, the main parameters of fuel consumption are selected and irrelevant parameters are excluded;

[0072] Improve the model construction method: The present invention obtains the forces exerted by various ship parameters and climate parameters during the operation of the ship, analyzes the forces, obtains the forces affecting fuel consumption, and constructs a model based on the correlation between the forces and fuel consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] By reading the following detailed description of the non-restrictive embodiments with reference to the accompanying drawings, other features, objects, and advantages of the present invention will become more apparent:

[0074] Figure 1 It is a schematic diagram of the method of the present invention;

[0075] Figure 2 It is a schematic diagram of the main data processing of the present invention;

[0076] Figure 3 It is a schematic diagram of the regression analysis of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0077] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0078] Embodiment 1

[0079] Please refer to Figure 1 , the ocean-going ship fuel consumption prediction method based on big data includes:

[0080] Step S1: Obtain ship data, climate data, and fuel consumption information.

[0081] Step S11: Obtain ship data according to sensors and recording devices. These data include but are not limited to the ship type, tonnage, draft, speed, and heading of the ship.

[0082] Step S12: Obtain the latest climate data from meteorological bureaus, ocean observation stations, or professional meteorological service agencies; these climate data include wind speed, wind direction, wave height, sea current direction and speed, air temperature, and humidity.

[0083] Step S13: Obtain fuel consumption information, including the fuel consumption records of the ship during past voyages, the fuel consumption performance under different types of navigation tasks, and the detailed data of the engine's working efficiency and fuel consumption rate.

[0084] Step S2: Process the ship data and climate data. According to the processed data, combined with the fuel consumption information, calculate the correlation coefficient, analyze and judge the correlation coefficient, and obtain the influencing parameters.

[0085] Step S21: Process the ship data and climate data, obtain ship parameters and climate parameters, conduct numerical analysis on the ship parameters and climate parameters, obtain the distribution status of the ship parameters and climate parameters, and extract the outliers in the ship parameters and climate parameters according to the distribution status to eliminate the influence of outliers on the data.

[0086] The specific steps for extracting outliers are as follows:

[0087] Step S211: Obtain the ship parameter type y. According to the ship data, obtain the data of x ships to get the ship parameters cb(i, cy), where 0 < cy ≤ y. Here, cy refers to the specific ship parameter type, such as ship weight, ship size, ship material, ship age, and ship speed; obtain the climate type z that the ship is subject to. According to the climate data, obtain the climate impacts on x ships to get the climate parameters qh(i, qz), where 0 < qz ≤ z. Here, qz refers to the specific ship parameter type, such as wind force, seawater flow rate, and temperature.

[0088] Step S212: Conduct numerical analysis on the ship parameters cb(i, cy) and the climate parameters qh(i, qz), and judge whether the parameters conform to the normal distribution according to the analysis results.

[0089] Step S2121: Calculate the mean value of the ship parameters to obtain the ship parameter mean μ(cy).

[0090]

[0091] Step S2122: Calculate the standard deviation of the ship parameters based on the ship parameters and in combination with the mean value of the ship parameters, to obtain the standard deviation of the ship parameters σ(cy):

[0092]

[0093] Step S2123: Calculate the kurtosis and skewness of the ship parameters based on the mean value of the ship parameters μ(cy) and the standard deviation of the ship parameters σ(cy), in combination with the ship parameters, to obtain the kurtosis of the ship parameters FD(cy) and the skewness of the ship parameters PD(cy):

[0094]

[0095] In the process of calculating the kurtosis FD of the ship parameters in this application document, by subtracting 3 from the value, the values of kurtosis and skewness approach 0. By calculating the kurtosis and skewness of the ship parameters, the data distribution of the ship parameters is judged, and the parameters that conform to the normal distribution are extracted through the data of kurtosis and skewness. This method has high reliability and strong simplicity;

[0096] Step S2124: Analyze and judge the ship parameters based on the kurtosis FD(cy) and skewness PD(cy) of the ship parameters:

[0097] If -2 ≤ FD(cy) ≤ 2 and -0.5 ≤ PD(cy) ≤ 0.5, then the ship parameters conform to the normal distribution;

[0098] If FD(cy) > 2 or FD(cy) < -2 or PD(cy) > 0.5 or PD(cy) < -0.5, then the ship parameters do not conform to the normal distribution;

[0099] Step S2125: Calculate the mean value of the climate parameters to obtain the mean value of the climate parameters μ(qz);

[0100]

[0101] Step S2126: Calculate the standard deviation of the climate parameters based on the climate parameters and in combination with the mean value of the climate parameters, to obtain the standard deviation of the climate parameters σ(qz):

[0102]

[0103] Step S2127: Calculate the kurtosis and skewness of the climate parameters based on the mean value of the climate parameters μ(qz) and the standard deviation of the climate parameters σ(qz), in combination with the climate parameters, to obtain the kurtosis of the climate parameters FD(qz) and the skewness of the climate parameters PD(qz):

[0104]

[0105] By calculating the kurtosis and skewness of climate parameters, the data distribution of climate parameters is judged, and the parameters that conform to the normal distribution are extracted based on the kurtosis and skewness data. This method has high reliability and strong simplicity.

[0106] Step S2128: Analyze and judge the climate parameters according to the climate parameter kurtosis FD(qz) and the climate parameter skewness PD(qz):

[0107] If -2 ≤ FD(qz) ≤ 2 and -0.5 ≤ PD(qz) ≤ 0.5, then the climate parameters conform to the normal distribution;

[0108] If FD(qz) > 2 or FD(qz) < -2 or PD(qz) > 0.5 or PD(qz) < -0.5, then the climate parameters do not conform to the normal distribution.

[0109] Step S213: Extract outliers according to the judgment result;

[0110] If the parameters conform to the normal distribution, extract outliers according to the 3σ principle;

[0111] For example, for ship parameters, obtain the ship parameter mean μ(cy) and the ship parameter standard deviation σ(cy), and compare the ship parameters:

[0112] If μ(cy) - 3σ(cy) ≤ cb(i, cy) ≤ μ(cy) + 3σ(cy), then cb(i, cy) belongs to the normal value;

[0113] If μ(cy) - 3σ(cy) > cb(i, cy) or cb(i, cy) < μ(cy) + 3σ(cy), then cb(i, cy) is an outlier;

[0114] If the parameters do not conform to the normal distribution, extract outliers according to the Isolation Forest method.

[0115] It should be noted that: Isolation Forest (abbreviated as iForest) is an unsupervised anomaly detection algorithm based on tree structure. Its core idea is that outlier data points are fewer in number and have a large difference from normal data, so they are more likely to be quickly isolated by random partitioning.

[0116] Step S22: Calculate the means of the ship parameters and climate parameters based on the processed data, and combine the fuel consumption information to calculate the correlation coefficients of the ship parameters, climate parameters and fuel consumption;

[0117] Step S221: Obtain the fuel consumption YH(i, cy, qz) of the ship according to the fuel consumption information. Calculate the average fuel consumption of the ship when the climate is different and the average fuel consumption when the ship data is different respectively, and obtain the average ship fuel consumption CJZ and the average climate fuel consumption QJZ.

[0118] The calculation process of the average ship fuel consumption CJZ is as follows:

[0119]

[0120] It should be noted that: YH(i, cy, qz) refers to the fuel consumption of the i-th ship under the cy-th ship parameter and under the influence of the qz-th climate.

[0121] Accumulate the fuel consumption of x ships under z climates according to the calculation formula of the average ship fuel consumption CJZ, divide by the product of the number of ships and the number of climate types, calculate the average fuel consumption under the same ship parameters, and perform an overall calculation on the influence data of the ship to simplify the calculation steps.

[0122] The calculation process of the average climate fuel consumption QJZ is as follows:

[0123]

[0124] Accumulate the fuel consumption of x ships under y ship parameters according to the calculation formula of the average ship fuel consumption CJZ, divide by the product of the number of ships and the number of ship parameter types, calculate the average fuel consumption under the same climate, and perform an overall calculation on the influence data of the ship to simplify the calculation steps.

[0125] Step S222: Obtain the ship parameter cb(i, cy) and the climate parameter qh(i, qz). Calculate the average value of the ship parameters to obtain the average ship parameter J(cy), and calculate the average value of the climate parameters to obtain the average climate parameter J(qz).

[0126]

[0127] Step S223: According to the ship parameter cb(i, cy), the average ship parameter J(cy), the fuel consumption YH(i, cy, qz) of the ship, and the average ship fuel consumption CJZ, calculate the correlation between the ship parameter and the ship fuel consumption to obtain the correlation coefficient XG(cy).

[0128]

[0129] Step S224: According to the climate parameter qh(i, qz), the average climate parameter J(qz), the fuel consumption YH(i, cy, qz) of the ship, and the average climate fuel consumption CJZ, calculate the correlation between the climate parameter and the ship fuel consumption to obtain the correlation coefficient XG(qz).

[0130]

[0131] By calculating the correlation coefficient, the correlation relationship between the parameters and the fuel consumption is obtained. The value range of the correlation coefficient is [-1, 1]. If the correlation coefficient is greater than 0, it indicates a positive correlation between the parameters and the fuel consumption; if the correlation coefficient is less than 0, it indicates a negative correlation between the parameters and the fuel consumption; if the correlation coefficient is equal to 0, it indicates no correlation between the parameters and the fuel consumption. The larger the absolute value of the correlation coefficient, the higher the correlation between the parameters and the fuel consumption. The greater the influence of the parameters on the fuel consumption, the data can be divided by the correlation coefficient, and specific numerical ranges of the correlation coefficient can be selected according to specific requirements.

[0132] Step S23: Analyze and judge the correlation coefficient, extract the ship parameters and climate parameters with large correlation coefficients to obtain the influencing parameters;

[0133] Step S231: According to actual needs, obtain the correlation coefficient threshold t, obtain the correlation coefficient XG(cy) between the ship parameters and the ship fuel consumption, and conduct judgment and analysis on XG(cy) in combination with the correlation coefficient threshold t:

[0134] If |XG(cy)| ≥ t, then this ship parameter belongs to the influencing parameter, and this ship parameter is extracted;

[0135] If |XG(cy)| < t, then this ship parameter does not belong to the influencing parameter;

[0136] It should be noted that: the value range of the correlation coefficient is [-1, 1], and by selecting the correlation coefficient through t, the value range of t is [0, 1]. The larger t is, the fewer the number of selected parameters, and the greater the correlation between the selected parameters and the fuel consumption; the smaller t is, the more the number of selected parameters, and the smaller the correlation between the selected parameters and the fuel consumption. When specifically selecting, the value is limited according to the number of the obtained ship parameters and climate parameters.

[0137] Step S232: Obtain the correlation coefficient XG(qz) between the climate parameters and the ship fuel consumption, and conduct judgment and analysis on XG(qz) in combination with the correlation coefficient threshold t:

[0138] If |XG(qz)| ≥ t, then this climate parameter belongs to the influencing parameter, and this climate parameter is extracted;

[0139] If |XG(qz)| < t, then this climate parameter does not belong to the influencing parameter;

[0140] Step S3: According to the influencing parameters, obtain the acting forces of the influencing parameters on the ship, integrate the acting forces to obtain the total acting force, and conduct regression analysis based on the total acting force combined with the fuel consumption information to construct a fuel consumption prediction model.

[0141] Step S31: Refer to Figure 2 to obtain the forces F(i, cy) and F(i, qz) exerted on the ship by the influencing parameters; obtain the angles θ cy , θ qz of the forces with the ship's traveling direction, and obtain the friction coefficient xs of the hull; integrate the forces to obtain the total force zF i ;

[0142] zF i = F(i, cy)cosθ cy + xs×F(i, cy)sinθ cy + F(i, qz)cosθ qz + xs×F(i, qz)sinθ qz ;

[0143] It should be noted that: the forces exerted on the ship by the influencing parameters are decomposed by angles so that they are mainly forces in the horizontal and vertical directions. The forces in the vertical direction are converted through the friction with the water surface and unified into forces in the horizontal direction.

[0144] Through this formula, various external factors during ship navigation are standardized. All factors are uniformly calculated according to the action of forces and decomposed according to the direction and angle of the forces. The total force affected by all factors is obtained, and combined with the fuel consumption information of the ship, the relationship between the fuel consumption change of the ship and the total action is reflected, which is convenient for model construction.

[0145] For the first ship, for example, it is mainly affected by the load. According to its load, F(i, cy) = 10 9 is obtained. During navigation, it is mainly affected by a 45° headwind with a wind force of six levels, so F(i, qz) = 10 6 is obtained. The friction coefficient xs = 0.02 is obtained. Then the total force is:

[0146]

[0147] Step S32: Refer to Figure 3 ; according to the fuel consumption information, obtain the fuel consumption xh i of the ship, and combine it with the total force to construct a data set of the total force zF i and the fuel consumption xh i ; process the data set through least squares to obtain the relevant parameters of the fuel consumption prediction model;

[0148] The specific process is as follows:

[0149] Step S321: Obtain the data set. According to the total force zF i and the fuel consumption xh iPerform calculations to obtain the first parameter k of the fuel consumption prediction model;

[0150] The specific calculation process of the first parameter k is as follows:

[0151]

[0152] It should be noted that: zF i refers to the total force received by the i-th ship, xh i refers to the fuel consumption generated by the i-th ship;

[0153] Step S322: According to the total force zF i and the fuel consumption xh i , combined with the first parameter k, calculate to obtain the second parameter v of the fuel consumption prediction model;

[0154] The specific calculation process of the second parameter v is as follows:

[0155]

[0156] Step S323: Obtain the first parameter k and the second parameter v, and construct the fuel consumption prediction model. The fuel consumption prediction model is as follows:

[0157] xh = k × zF + v;

[0158] Step S4: Perform voyage prediction and real-time prediction on the fuel consumption of the ship according to the fuel consumption prediction model, prepare the fuel volume of the ship according to the prediction result, and give an alarm for abnormal fuel consumption generated during the voyage;

[0159] Step S41: Before the ship is ready to set sail, obtain the voyage route through the navigation system; according to the weather forecast data provided by the meteorological bureau, including wind speed, wind direction, wave height and possible severe weather warnings, as well as the sea conditions information of the relevant sea areas released by the maritime bureau, obtain the climate conditions, and use the mechanical model to estimate the natural forces received by the hull to obtain the total force zF1 received by the hull during navigation; combined with the fuel consumption prediction model, substitute the total force zF1 into the model for calculation to obtain the fuel consumption xh1 required for navigation; prepare sufficient fuel volume for the ship according to xh1 to prevent affecting the voyage plan or safety due to insufficient fuel.

[0160] Step S42: When the ship is in a navigation state, monitor the fuel consumption in real time; continuously monitor and record various forces actually exerted on the hull during navigation through high-precision sensors and measuring instruments, including wind force, water flow impact force, and bumps caused by waves, to obtain the force zF2 received during navigation. Combine it with the fuel consumption prediction model to obtain the predicted fuel consumption xh2, and obtain the actual fuel consumption xhs of the ship at the current moment. Compare the difference between the predicted fuel consumption and the actual fuel consumption. If xhs > xh2, trigger the fuel consumption warning mechanism, and the crew needs to inspect the hull and troubleshoot the reasons for abnormal fuel consumption.

[0161] The above formulas are all calculated by taking the numerical values without dimensions. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by technicians in this field according to the actual situation. For example, there are weight coefficients and proportionality coefficients, and the sizes of their settings are for quantifying each parameter to obtain a specific numerical value for subsequent comparison. Regarding the sizes of the weight coefficients and proportionality coefficients, as long as they do not affect the proportional relationship between the parameters and the quantified numerical values, it is fine.

[0162] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any technician familiar with this technical field can still modify the technical solutions described in the foregoing embodiments or easily think of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for predicting the fuel consumption of ocean - going ships based on big data, characterized in that, The prediction method includes: Step S1: Obtain ship data and climate data, and obtain fuel consumption information; Step S2: According to the ship data and climate data, obtain ship parameters and climate parameters, process the ship parameters and climate parameters, extract the outliers in the ship parameters and climate parameters, combine the fuel consumption information, calculate the correlation coefficient of the ship parameters and climate parameters, analyze and judge the correlation coefficient, and obtain the influencing parameters; Step S3: Obtain the force exerted on the ship by the influencing parameters, conduct a force analysis on the forces exerted on the ship, obtain the total force, and conduct a regression analysis based on the total force and the fuel consumption information to construct a fuel consumption prediction model; Step S4: Conduct navigation prediction and real-time prediction on the fuel consumption of the ship according to the fuel consumption prediction model, and give an alarm for abnormal fuel consumption generated during navigation; The specific steps of step S2 are as follows: Step S21: Process the ship data and climate data to obtain ship parameters and climate parameters, conduct numerical analysis on the ship parameters and climate parameters to obtain the distribution of the ship parameters and climate parameters, and extract the outliers in the ship parameters and climate parameters according to the distribution; Step S22: Calculate the mean values of the ship parameters and climate parameters according to the processed data, and combine the fuel consumption information to calculate the correlation coefficients of the ship parameters, climate parameters and fuel consumption; Step S23: Analyze and judge the correlation coefficients, extract the ship parameters and climate parameters with large correlation coefficients, and obtain the influencing parameters; The specific steps of step S22 are as follows: Step S221: According to the fuel consumption information, obtain the fuel consumption YH(i, cy, qz) of the ship, calculate the average fuel consumption of the ship when the climate is different and the average fuel consumption when the ship data is different respectively, and obtain the average ship fuel consumption CJZ and the average climate fuel consumption QJZ; The calculation process of the average ship fuel consumption CJZ is as follows: YH(i, cy, qz) refers to the fuel consumption of the i-th ship under the cy-th ship parameter and under the influence of the qz-th climate. x refers to the number of ships, and z refers to the type of climate parameters; The calculation process of the average climate fuel consumption QJZ is as follows: Among them, y refers to the type of ship parameters; Step S222: Obtain the ship parameter cb(i, cy) and the climate parameter qh(i, qz), and calculate the average value J(cy) of the ship parameter and the average value J(qz) of the climate parameter; Step S223: Calculate the correlation between the ship parameter and the ship fuel consumption according to the ship parameter cb(i, cy), the average value J(cy) of the ship parameter, the fuel consumption YH(i, cy, qz) of the ship, and the average ship fuel consumption CJZ, and obtain the correlation coefficient XG(cy); Step S224: Calculate the correlation between the climate parameter and the ship fuel consumption according to the climate parameter qh(i, qz), the average value J(qz) of the climate parameter, the fuel consumption YH(i, cy, qz) of the ship, and the average climate fuel consumption QJZ, and obtain the correlation coefficient XG(qz); The specific steps of step S3 are as follows: Step S31: Obtain the forces F(i, cy) and F(i, qz) exerted by the influencing parameters on the ship; obtain the angles θ and θ between the forces and the ship's traveling direction; obtain the friction coefficient xs of the hull; integrate the forces to obtain the total force zF cy and θ qz , obtain the friction coefficient xs of the hull; integrate the forces to obtain the total force zF i ; zF i = F(i, cy) cosθ cy + xs × F(i, cy) sinθ cy + F(i, qz) cosθ qz + xs × F(i, qz) sinθ qz ; Step S32: Obtain the fuel consumption xh of the ship according to the fuel consumption information i , and combine the total force to construct the total force zF i and the fuel consumption xh i data set, and process the data set by the least squares method to obtain the first parameter k and the second parameter v of the fuel consumption prediction model; Construct a fuel consumption prediction model according to the first parameter k and the second parameter v to obtain the fuel consumption prediction model. The fuel consumption prediction model is as follows: xh = k × zF + v xh is the fuel consumption variable of the fuel consumption prediction model, and zF is the total force variable of the fuel consumption prediction model.

2. The method for predicting the fuel consumption of ocean-going ships based on big data according to claim 1, wherein, The specific steps of step S21 are as follows: Step S211: Obtain the type y of ship parameter types, obtain the data of x ships according to the ship data, and obtain the ship parameters cb(i, cy), where 0 < cy ≤ y, and cy refers to the specific ship parameter type; obtain the type z of climate parameter types suffered by the ship, obtain the climate impacts on x ships according to the climate data, and obtain the climate parameters qh(i, qz), where 0 < qz ≤ z, qz refers to the specific climate parameter type, and i refers to the i-th ship. Step S212: Conduct numerical analysis on the ship parameters cb(i, cy) and the climate parameters qh(i, qz), and judge whether the parameters conform to the normal distribution according to the analysis results. Step S213: Extract outliers according to the judgment results. If the parameters conform to the normal distribution, extract outliers according to the 3σ principle. If the parameters do not conform to the normal distribution, extract outliers according to the isolation forest method.

3. The method for predicting the fuel consumption of ocean-going ships based on big data according to claim 2, characterized in that, The specific steps of step S212 are as follows: Step S2121: Calculate the mean of the ship parameters to obtain the ship parameter mean μ(cy). Step S2122: Calculate the standard deviation of the ship parameters in combination with the ship parameter mean according to the ship parameters to obtain the ship parameter standard deviation σ(cy): Step S2123: Calculate the kurtosis and skewness of the ship parameters in combination with the ship parameters according to the ship parameter mean μ(cy) and the ship parameter standard deviation σ(cy) to obtain the ship parameter kurtosis FD(cy) and the ship parameter skewness PD(cy): Step S2124: Analyze and judge the ship parameters according to the ship parameter kurtosis FD(cy) and the ship parameter skewness PD(cy): If -2 ≤ FD(cy) ≤ 2 and -0.5 ≤ PD(cy) ≤ 0.5, then the ship parameters conform to the normal distribution. If FD(cy) > 2 or FD(cy) < -2 or PD(cy) > 0.5 or PD(cy) < -0.5, then the ship parameters do not conform to the normal distribution.

4. The method for predicting fuel consumption of ocean-going ships based on big data according to claim 3, characterized in that Step S212 also includes: Step S2125: Calculate the mean of the climate parameters to obtain the climate parameter mean μ(qz). Step S2126: Calculate the standard deviation of the climate parameters in combination with the climate parameter mean according to the climate parameters to obtain the climate parameter standard deviation σ(qz). Step S2127: Calculate the kurtosis and skewness of the climate parameters in combination with the climate parameters according to the climate parameter mean μ(qz) and the climate parameter standard deviation σ(qz) to obtain the climate parameter kurtosis FD(qz) and the climate parameter skewness PD(qz); Judge the data distribution of the climate parameters by calculating the kurtosis and skewness of the climate parameters, and extract the parameters that conform to the normal distribution through the data of kurtosis and skewness. Step S2128: Analyze and judge the climate parameters according to the climate parameter kurtosis FD(qz) and the climate parameter skewness PD(qz): If -2 ≤ FD(qz) ≤ 2 and -0.5 ≤ PD(qz) ≤ 0.5, then the climate parameters conform to the normal distribution. If FD(qz) > 2 or FD(qz) < -2 or PD(qz) > 0.5 or PD(qz) < -0.5, then the climate parameters do not conform to the normal distribution.

5. The method for predicting fuel consumption of ocean-going ships based on big data according to claim 1, wherein The subsequent steps of step S23 are as follows: Step S231: Obtain a correlation coefficient threshold t, where 0 < t ≤ 1. Obtain the correlation coefficient XG(cy) between the ship parameters and the ship fuel consumption, and make a judgment and analysis of XG(cy) in combination with the correlation coefficient threshold t: If |XG(cy)| ≥ t, then the ship parameter belongs to the influencing parameter, and extract the ship parameter; If |XG(cy)| < t, then the ship parameter does not belong to the influencing parameter; Step S232: Obtain the correlation coefficient XG(qz) between the climate parameters and the ship fuel consumption, and make a judgment and analysis of XG(qz) in combination with the correlation coefficient threshold t: If |XG(qz)| ≥ t, then the climate parameter belongs to the influencing parameter, and extract the climate parameter; If |XG(qz)| < t, then the climate parameter does not belong to the influencing parameter.

Images