Marine main engine oil consumption modeling method and system based on noon report data

Abstract

The invention relates to a ship main engine oil consumption modeling method and system based on noon report data, and the modeling method comprises a noon report data collection and screening step, a noon report data classification step, a ship type classification step, a partial load condition fitting modeling step and a unified fitting and draught correction modeling step. Modeling operand and modeling complexity are greatly reduced, meanwhile, multi-level classification of weather (wind level and wave level) and ship types under different dimensions is carried out, a plurality of ship main engine oil models are constructed by adopting a partial load condition fitting method, a unified fitting method and a draught correction method respectively, ship slip rate is adopted as an intermediate variable, and a ship main engine oil model is constructed. According to the method, the relation between the navigational speed and the ship slip rate and the relation between the oil consumption and the ship slip rate are fitted respectively, the fitting flexibility and the formula complexity are improved, the fitting effect is better, the multiple built ship main engine oil models are accurate and efficient, cost reduction, efficiency improvement and safe and reliable performance improvement of enterprises are facilitated, and environmental protection and compliance management can be promoted.

Description

Technical Field

[0001] The invention relates to the technical field of ship navigation energy efficiency management, and in particular to a ship main engine fuel consumption modeling method and system based on midday report data. Background Art

[0002] The fuel consumption of ship main engines accounts for an important proportion of shipping costs. Through the fuel consumption model, shipowners and shipping companies can accurately predict and control the fuel consumption of ships under different operating conditions. This can help them optimize the speed, route and voyage planning of ships, thereby reducing operating costs. The fuel consumption model can also improve the operational efficiency and safety of ships. The fuel consumption model can be used as an indicator to evaluate the status of ship main engines and related systems. By analyzing fuel consumption data, problems that affect fuel efficiency, such as equipment failure, poor operation or hull structure design, can be identified and solved. In addition, many countries and regions have strict regulations and standards on ship emissions. The fuel consumption model can help shipowners and shipping companies monitor and manage the emission levels of ships, ensure that ships operate under regulatory requirements, and help implement energy-saving and emission reduction policies and technologies. Therefore, building a ship main engine fuel consumption model not only helps companies reduce costs and improve efficiency, but also promotes environmental protection and compliance management, and is an important support for the sustainable development of the shipping industry.

[0003] There are several commonly used ship main engine fuel consumption modeling methods:

[0004] 1. Use model test or numerical calculation method to establish ship main engine fuel consumption model, but the method is complicated and requires a lot of ship parameters, ship type data or test data;

[0005] 2. Using machine learning methods based on real ship monitoring data to establish a ship main engine fuel consumption model, but sensor monitoring data is required, and the model has poor interpretability and generalization ability, and may output results that violate physical laws (for example, lower speed leads to higher fuel consumption);

[0006] 3. The ship's main engine fuel consumption model is established by directly fitting the speed and fuel consumption of the ship's midday report data, but the fitting effect is not good, and it is usually difficult to consider the influence of weather and load conditions.

[0007] Therefore, a new engine fuel consumption modeling scheme with simple modeling, strong generalization ability and good fitting effect is urgently needed. Summary of the invention

[0008] The present invention aims at the existing ship main engine fuel consumption modeling methods, which have complex modeling, large data volume, poor interpretability, poor generalization ability, and poor fitting effect. A ship main engine fuel consumption modeling method based on midday report data is proposed, which greatly reduces the modeling calculation amount and modeling complexity, and simultaneously performs multi-level classification under different dimensions of weather (wind level and wave level) and ship type, respectively adopts two methods of load condition fitting and unified fitting plus draft correction to establish several models, adopts ship slip rate as an intermediate variable, and respectively fits the relationship between speed, fuel consumption and slip rate, which increases the flexibility of fitting and the complexity of formula, and has better fitting effect. The constructed several ship main engine fuel consumption models are accurate and efficient. The present invention also relates to a ship main engine fuel consumption modeling system based on midday report data.

[0009] The technical solution of the present invention is as follows:

[0010] A method for modeling fuel consumption of a ship main engine based on midday report data, characterized in that it comprises the following steps:

[0011] Midday report data collection and screening step: collecting the sailing time, average speed over ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern from the daily midday report data, and analyzing the collected midday report data through the preset screening conditions;

[0012] The midday report data classification step is to classify the midday report data that meets the screening conditions into good weather data and bad weather data according to the level intervals of wind level and wave level;

[0013] The ship type classification step is divided into two different steps for modeling according to the different ship types. For ships with fixed load conditions, the modeling step of loading condition fitting is entered; for ships with variable load conditions, the modeling step of unified fitting plus draft correction is entered;

[0014] The modeling steps of the load condition fitting are as follows: the good weather data and the bad weather data are divided into two load conditions, full load and ballast, according to the selected average draft of the bow and stern according to the preset load condition conditions, and then the two load conditions of the good weather data and the two load conditions of the bad weather data are modeled respectively, and the modeling steps are: according to the selected average main engine speed and average ground speed, the theoretical speed and the ship slip rate are calculated, and then the relationship between the theoretical speed and the main engine fuel consumption is fitted by the least squares method, and the relationship between the theoretical speed and the ship slip rate is fitted by the least squares method, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then the corresponding relationship between the average ground speed and the main engine fuel consumption is obtained, which is the ship main engine fuel consumption model, and finally four ship main engine fuel consumption models are constructed for the full load condition of good weather data, the ballast condition of good weather data, the full load condition of bad weather data and the ballast condition of bad weather data;

[0015] The modeling steps of unified fitting plus draft correction are used. Good weather data and bad weather data are modeled separately according to the screened average draft of bow and stern. The modeling steps are: according to the screened average main engine speed and average ground speed, the theoretical speed and ship slip rate are calculated, and then the relationship between the theoretical speed and the main engine fuel consumption is fitted by the least squares method, and the relationship between the theoretical speed and the ship slip rate is fitted by the least squares method, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then the corresponding relationship between the average ground speed and the main engine fuel consumption is obtained, which is the ship main engine fuel consumption model, and the analysis is constructed. Two ship main engine fuel consumption models for good weather data and bad weather data are respectively formulated; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

[0016] Preferably, in the noon report data collection and screening step, the preset screening conditions are: 23 hours <= sailing time <= 25 hours; 7kn <= average speed over ground <= design speed of the ship; 0 < actual fuel consumption of the main engine <= fuel consumption corresponding to the rated power of the main engine * 1.5; 0 < average main engine speed <= rated speed of the main engine.

[0017] Preferably, in the noon report data classification step, the noon report data that meets the screening conditions is classified as good weather data when the wind level is less than or equal to level 5 and the wave level is less than or equal to level 3, otherwise it is classified as bad weather data.

[0018] Preferably, in the load condition fitting modeling step and the unified fitting plus draft correction modeling step, the theoretical speed and the ship slip rate are calculated according to the screened average main engine speed and average ground speed, and the specific calculation formula is:

[0019]

[0020] Among them, V t is the theoretical speed, Slip is the slip rate of the ship, N s is the average main engine speed, Pitch is the ship propeller pitch, V g is the average ground speed.

[0021] Preferably, in the load condition fitting modeling step and the unified fitting plus draft correction modeling step, the least squares method is used to fit the relationship between the theoretical speed and the main engine fuel consumption, and the fitting function form adopts a power function or a cubic polynomial without a constant term; the least squares method is used to fit the relationship between the theoretical speed and the ship slip rate, and the fitting function form adopts a linear function or a quadratic function.

[0022] Preferably, in the unified fitting plus draft correction modeling step, a quadratic function is used to fit the relationship between the bow and stern average draft and the ratio to obtain a draft correction coefficient.

[0023] A ship main engine fuel consumption modeling system based on midday report data, characterized in that it comprises a midday report data collection and screening module, a midday report data classification module, a ship type classification module, a load condition fitting modeling module and a unified fitting plus draft correction modeling module, wherein the midday report data collection and screening module, the midday report data classification module and the ship type classification module are connected in sequence, and the ship type classification module is respectively connected to the load condition fitting modeling module and the unified fitting plus draft correction modeling module;

[0024] The midday report data collection and screening module collects the sailing time, average speed over ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern in the daily midday report data, and analyzes the collected midday report data according to the preset screening conditions;

[0025] The midday report data classification module classifies the midday report data that meets the screening conditions into good weather data and bad weather data according to the level intervals of wind level and wave level;

[0026] The ship type classification module is divided into two different steps of modeling according to different ship types. For a ship type with a fixed load condition, it enters the load condition fitting modeling module; for a ship type with a variable load condition, it enters the unified fitting plus draft correction modeling module;

[0027] The load condition fitting modeling module divides the good weather data and the bad weather data into two load conditions, full load and ballast, according to the screened average draft of the bow and stern according to the preset load condition conditions, and then models the two load conditions of the good weather data and the two load conditions of the bad weather data respectively, and the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and the ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and finally construct four ship main engine fuel consumption models for the full load condition of good weather data, the ballast condition of good weather data, the full load condition of bad weather data and the ballast condition of bad weather data respectively;

[0028] The unified fitting plus draft correction modeling module models the good weather data and the bad weather data respectively according to the screened average draft of the bow and stern, and the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and the ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and construct Two ship main engine fuel consumption models for good weather data and bad weather data are respectively constructed; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

[0029] Preferably, in the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the theoretical speed and the ship slip rate are calculated according to the screened average main engine speed and average ground speed, and the specific calculation formula is:

[0030]

[0031] Among them, V t is the theoretical speed of the ship, Slip is the slip rate, N s is the average main engine speed, Pitch is the ship propeller pitch, V g is the actual speed of the ship.

[0032] Preferably, in the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the least squares method is used to fit the relationship between the theoretical speed and the main engine fuel consumption, and the fitting function form adopts a power function or a cubic polynomial without a constant term; the least squares method is used to fit the relationship between the theoretical speed and the ship slip rate, and the fitting function form adopts a linear function or a quadratic function.

[0033] Preferably, in the unified fitting plus draft correction modeling module, a quadratic function is used to fit the relationship between the bow and stern average draft and the ratio to obtain a draft correction coefficient.

[0034] The technical effects of the present invention are as follows:

[0035] The present invention relates to a method for modeling fuel consumption of ship main engine based on midday report data, which collects and screens midday report data, removes abnormal data, selects normal data of all-day navigation for analysis, and then classifies the midday report data, considering the weather impact, and classifies it into good weather data and bad weather data according to the level interval of wind level and wave level, and models the good weather data and bad weather data separately to realize the calculation of fuel consumption in good weather and bad weather separately. At the same time, the ship types are classified, and according to the operating characteristics of different ship types, two methods of load condition fitting and unified fitting plus draft correction are used to establish models. For ship types with fixed load conditions, load condition fitting modeling is carried out; for ship types with variable load conditions, unified fitting plus draft correction modeling is carried out. For the modeling step of loading condition fitting, the good weather data and bad weather data are divided into two loading conditions, full load and ballast, according to the selected bow and stern average draft according to the preset loading conditions, and then the two loading conditions of good weather data and the two loading conditions of bad weather data are modeled separately to obtain four models; for unified fitting plus draft correction modeling, it is not necessary to divide it into two loading conditions, full load and ballast, but all data are fitted together. Of course, good and bad weather still need to be distinguished, so there should be two models. Whether it is loading condition fitting or unified fitting, the ship slip rate and theoretical speed are used as intermediate variables during fitting, and the relationship between theoretical speed and main engine fuel consumption, theoretical speed and ship slip rate (where slip rate is related to actual speed) is fitted respectively, which can improve the fitting effect. At the same time, according to the actual data situation, different fitting function forms can be combined, which is more adaptable. The model finally established realizes the calculation of main engine fuel consumption at different speeds under the conditions of different weather (good / bad) and different drafts (or loading conditions). The ship main engine fuel consumption modeling method involved in the present invention only needs to combine the ship midday report data with a small amount of ship fixed parameters for analysis. By adopting a method that conforms to physical laws to carry out modeling, the model has good interpretability and will not produce results that violate physical laws. More importantly, the ship slip rate is used as an intermediate variable to fit the relationship between speed, fuel consumption and slip rate respectively, which increases the flexibility of fitting and the complexity of the formula, and the fitting effect is better. That is to say, compared with the single formula fitting, the model complexity of the two-part fitting of the present invention is higher, and a more complex functional relationship can be described, thereby improving the fitting effect; and multi-level classification under different dimensions is integrated, the influence of weather is considered, and different methods are adopted for different ship types to consider the influence of load conditions, so as to construct an accurate and efficient ship main engine fuel consumption model, which has the advantages of simple modeling, good interpretability, strong generalization ability, good fitting effect, etc., so that ship owners and shipping companies can accurately predict and control the fuel consumption of ships under different operating conditions, which can not only reduce operating costs, but also improve the operating efficiency and safety of ships. It can be widely promoted as an optimization scheme and has certain engineering application prospects.

[0036] The present invention also relates to a ship main engine fuel consumption modeling system based on midday report data, which corresponds to the above-mentioned ship main engine fuel consumption modeling method based on midday report data, and can be understood as a system for realizing the ship main engine fuel consumption modeling method based on midday report data of the present invention, including a midday report data collection and screening module, a midday report data classification module, a ship type classification module, a load condition fitting modeling module and a unified fitting plus draft correction modeling module. Each module works in coordination, and there is no need to collect massive parameters. It is based on daily midday report data, which is convenient and practical, greatly reducing the amount of modeling calculations and the complexity of modeling. At the same time, multi-level classification is performed under different dimensions of weather (wind level and wave level) and ship type, and models are established by using load condition fitting and unified fitting plus draft correction methods to construct several corresponding ship main engine oil models under good / bad weather data and different load conditions. The ship slip rate is used as an intermediate variable to fit the relationship between speed, fuel consumption and ship slip rate, respectively, which increases the flexibility of fitting and the complexity of the formula, and the fitting effect is better. The constructed several ship main engine oil models are accurate and efficient, which helps enterprises reduce costs, improve efficiency and safety and reliability, and can promote environmental protection and compliance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The present invention is a flow chart of a method for modeling fuel consumption of a ship main engine based on midday report data.

[0038] Figure 2 It is a working principle diagram of the ship main engine fuel consumption modeling method based on midday report data of the present invention. DETAILED DESCRIPTION

[0039] The present invention will be described below in conjunction with the accompanying drawings.

[0040] The present invention relates to a ship main engine fuel consumption modeling method based on midday report data, which uses the daily midday report data of the ship to establish a ship speed fuel consumption model to achieve the calculation of the ship main engine fuel consumption at a specific speed. Figure 1 The flowchart shown and Figure 2 The working principle diagram (or detailed flow chart) shown in the figure includes the following steps:

[0041] 1. Midday report data collection and screening steps: collect the sailing time, average speed over ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern in the daily midday report data, and analyze the collected midday report data through the preset screening conditions.

[0042] Specifically, the sailing time T of the daily noon report is used to filter the data of the whole day's sailing for analysis (the influence of time zone needs to be considered, and the sailing time may be greater than 24 hours). At the same time, in order to remove abnormal data, the daily average ground speed Vg (also known as the actual speed of the ship), the actual fuel consumption of the main engine FC i, screen the average main engine speed Ns, and filter out the noon report data that meet the preset screening conditions. Further, the preset screening conditions are as follows:

[0043] 1) 23 hours <= T <= 25 hours;

[0044] 2) 7 kn <= Vg <= ship design speed;

[0045] 3) 0 < FC i <= fuel consumption corresponding to the rated power of the main engine * 1.5;

[0046] 4) 0 < Ns <= rated speed of the main engine.

[0047] II. Noon report data classification step, classify the noon report data that meet the screening conditions into good weather data and bad weather data according to the grade intervals where the wind grade and wave grade are located.

[0048] Further, classify the noon report data that meet the screening conditions into good weather data when the wind grade is less than or equal to 5 and the wave grade is less than or equal to 3, otherwise classify it as bad weather data. Subsequently, build models for the two groups of good and bad weather data respectively.

[0049] III. Ship type classification step, classify the ship type, and according to the different ship types, divide it into two different steps for modeling. For ship types with relatively fixed loading conditions such as bulk carriers and oil tankers, enter the sub-loading condition (fully loaded, ballast) fitting modeling step; for ship types with variable loading conditions such as container ships, enter the unified fitting plus draft correction modeling step.

[0050] IV. Sub-loading condition fitting modeling step, according to the screened bow and stern average drafts, divide the good weather data and bad weather data into two loading conditions of fully loaded and ballast according to the preset loading conditions, and then model the two loading conditions of good weather data and the two loading conditions of bad weather data respectively. The modeling steps are all: according to the screened average main engine speed and average speed over the ground, calculate the theoretical speed and the ship's slip ratio, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and use the least squares method to fit the relationship between the theoretical speed and the ship's slip ratio to obtain the corresponding relationship between the average speed over the ground and the theoretical speed, and then obtain the corresponding relationship between the average speed over the ground and the main engine fuel consumption, which is the ship's main engine fuel consumption model. Finally, construct four ship's main engine fuel consumption models respectively for the fully loaded condition of good weather data, the ballast condition of good weather data, the fully loaded condition of bad weather data, and the ballast condition of bad weather data.

[0051] Specifically, the data (good weather data and bad weather data) are divided into full load and ballast load conditions according to the average draft of the bow and stern. The preset screening range of the full load condition is that the full load draft fluctuates by 0.2m, and the ballast load condition is that the ballast draft fluctuates by 0.2m. The two load conditions are modeled separately (that is, the two load conditions of the good weather data and the two load conditions of the bad weather data are modeled separately). The steps are as follows (considering good / bad weather and two load conditions, there are four models in total, and the modeling steps are consistent):

[0052] 1) Based on the average host speed N s , Actual speed of the ship (i.e. average speed over the ground) V g , calculate the theoretical ship speed V t And slip rate Slip:

[0053]

[0054]

[0055] Where Pitch is the pitch of the ship's propeller.

[0056] 2) Fitting theoretical speed V t The relationship between the fuel consumption of the main engine FC can be in the form of a power function or a cubic polynomial without a constant term, and the fitting method can be the least squares method. Take the cubic polynomial without a constant term as an example:

[0057]

[0058] Where a1, b1, and c1 are fitting coefficients.

[0059] 3) Fitting theoretical speed V t The relationship between the ship slip rate Slip and the ship slip rate can be expressed in the form of a linear function or a quadratic function, and the fitting method can be the least squares method. Take the quadratic function as an example:

[0060]

[0061] Where a2, b2, and c2 are fitting coefficients.

[0062] 4) According to equations (2) and (4), the actual speed of the ship V can be obtained: g and theoretical speed V t The corresponding relationship is:

[0063]

[0064] 5) According to equations (5) and (3), the actual speed of the ship V can be obtained: g The corresponding relationship with the main engine fuel consumption FC is recorded as:

[0065] FC=f(Vg ) (6)

[0066] This is the main engine fuel consumption model. When the main engine fuel consumption model is actually used, the curve interpolation can be performed according to formula (5) and input V g Get V t , then V t Substituting into (3) we obtain FC.

[0067] This step uses the ship slip rate and the corresponding relationship of the fitting as the intermediate variable and intermediate process, and finally constructs four ship main engine fuel consumption models for full load condition of good weather data, ballast load condition of good weather data, full load condition of bad weather data and ballast load condition of bad weather data. When constructing the four ship main engine fuel consumption models for fitting, their fitting coefficients are different.

[0068] 5. Unified fitting plus draft correction modeling steps, modeling good weather data and bad weather data respectively according to the screened average draft of bow and stern, the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and construct Two ship main engine fuel consumption models for good weather data and bad weather data are respectively constructed; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

[0069] Specifically, the modeling steps of the unified fitting plus draft correction method are the same as steps 1) to 5) in the above-mentioned load condition fitting modeling steps, but it does not need to be divided into two load conditions, full load and ballast. Instead, all data are fitted together to obtain the actual ship speed V g Corresponding relationship with the main engine fuel consumption FC FC = f (V g )(Good weather and bad weather still need to be distinguished, so there should be two models).

[0070] Then use FC = f (V g ) Calculate the main engine fuel consumption corresponding to the actual speed of the ship every day (get the calculated value of the main engine fuel consumption), and then calculate the ratio K of the actual fuel consumption of the ship's main engine to the calculated value of the main engine fuel consumption f , using quadratic function to fit daily ship draft Tm (Average draft of bow and stern) and K f The relationship is:

[0071]

[0072] Among them, a3, b3, and c3 are fitting coefficients.

[0073] K f As the draft correction factor, the final main engine fuel consumption model is:

[0074] FC=f(V g )*K f (8)

[0075] When constructing two ship main engine fuel consumption models for good weather data and bad weather data for fitting, the respective fitting coefficients are different, and the draft correction coefficients obtained are also different. The two ship main engine fuel consumption models for good weather data and bad weather data obtained by formula 6 are FC=f(V g ) are multiplied by their corresponding draft correction coefficient K f Two final ship main engine fuel consumption models for good weather data and bad weather data are obtained respectively.

[0076] The present invention also relates to a ship main engine fuel consumption modeling system based on midday report data, which corresponds to the above-mentioned ship main engine fuel consumption modeling method based on midday report data, and can be understood as a system for implementing the ship main engine fuel consumption modeling method based on midday report data of the present invention, including a midday report data collection and screening module, a midday report data classification module, a ship type classification module, a sub-load condition fitting modeling module and a unified fitting plus draft correction modeling module, the midday report data collection and screening module, the midday report data classification module and the ship type classification module are connected in sequence, the ship type classification module is respectively connected to the sub-load condition fitting modeling module and the unified fitting plus draft correction modeling module, the system workflow diagram refers to Figure 2 shown.

[0077] Among them, the noon report data collection and screening module collects the sailing time, average speed over the ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern in the daily noon report data, and analyzes the collected noon report data through preset screening conditions; the noon report data classification module classifies the noon report data that meets the screening conditions into good weather data and bad weather data according to the level interval of the wind level and wave level; the ship type classification module is divided into two different steps (data flow) modeling according to different ship types, that is, Figure 2 As shown, the data flow is divided into two paths. For ships with fixed loading conditions, the data flow enters the loading condition fitting modeling module; for ships with variable loading conditions, the data flow enters the unified fitting plus draft correction modeling module.

[0078] The load condition fitting modeling module divides the good weather data and the bad weather data into two load conditions, full load and ballast, according to the screened average draft of the bow and stern according to the preset load condition conditions, and then models the two load conditions of the good weather data and the two load conditions of the bad weather data respectively, and the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and the ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and finally construct four ship main engine fuel consumption models for the full load condition of good weather data, the ballast condition of good weather data, the full load condition of bad weather data and the ballast condition of bad weather data respectively;

[0079] The unified fitting plus draft correction modeling module models the good weather data and the bad weather data respectively according to the screened average draft of the bow and stern, and the modeling steps are: according to the screened average main engine speed and average ground speed, the theoretical speed and the ship slip rate are calculated, and then the relationship between the theoretical speed and the main engine fuel consumption is fitted by the least squares method, and the relationship between the theoretical speed and the ship slip rate is fitted by the least squares method, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then the corresponding relationship between the average ground speed and the main engine fuel consumption is obtained, which is the ship main engine fuel consumption model, and a Two ship main engine fuel consumption models for good weather data and bad weather data are respectively constructed; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

[0080] Furthermore, in the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the theoretical speed and the ship slip rate are calculated according to the screened average main engine speed and average ground speed. The specific calculation formula is:

[0081]

[0082] Among them, V t is the theoretical speed of the ship, Slip is the slip rate, N s is the average main engine speed, Pitch is the ship propeller pitch, V g is the actual speed of the ship.

[0083] Furthermore, in the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the least squares method is used to fit the relationship between the theoretical speed and the main engine fuel consumption, and the fitting function form adopts a power function or a cubic polynomial without a constant term; the least squares method is used to fit the relationship between the theoretical speed and the ship slip rate, and the fitting function form adopts a linear function or a quadratic function.

[0084] Furthermore, in the unified fitting plus draft correction modeling module, a quadratic function is used to fit the relationship between the bow and stern average draft and the ratio to obtain a draft correction coefficient.

[0085] The ship main engine fuel consumption modeling method and system involved in the present invention only need daily noon report data (navigation time, average speed over ground, actual fuel consumption of main engine, average main engine speed, wind level, wave level and bow and stern average draft) combined with a small amount of ship fixed parameters (such as ship design speed, main engine rated power, main engine rated speed, ship type, ship propeller pitch) for analysis. By adopting a method that conforms to physical laws to carry out modeling, the model has good interpretability and will not produce results that violate physical laws. More importantly, the ship slip rate is used as an intermediate variable to fit the relationship between speed, fuel consumption and slip rate respectively, which increases the flexibility of fitting and the complexity of formulas, and has better fitting effect. In addition, multi-level classification under different dimensions is integrated to consider the influence of weather. At the same time, different methods are used for different ship types to consider the influence of load conditions, so as to construct an accurate and efficient ship main engine fuel consumption model, which has the advantages of simple modeling, good interpretability, strong generalization ability, good fitting effect, etc.

[0086] It should be noted that the above-described specific implementations can enable those skilled in the art to more fully understand the invention, but do not limit the invention in any way. Therefore, although this specification has described the invention in detail with reference to the drawings and embodiments, those skilled in the art should understand that the invention can still be modified or replaced by equivalents. In short, all technical solutions and improvements that do not deviate from the spirit and scope of the invention should be included in the protection scope of the patent for the invention.

Claims

1. A ship main engine fuel consumption modeling method based on midday report data, characterized in that: The steps include: Midday report data collection and screening step: collecting the sailing time, average speed over ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern from the daily midday report data, and analyzing the collected midday report data through the preset screening conditions; The midday report data classification step is to classify the midday report data that meets the screening conditions into good weather data and bad weather data according to the level intervals of wind level and wave level; The ship type classification step is divided into two different steps for modeling according to the different ship types. For ships with fixed load conditions, the modeling step of loading condition fitting is entered; for ships with variable load conditions, the modeling step of unified fitting plus draft correction is entered; The modeling steps of the load condition fitting are as follows: the good weather data and the bad weather data are divided into two load conditions, full load and ballast, according to the selected average draft of the bow and stern according to the preset load condition conditions, and then the two load conditions of the good weather data and the two load conditions of the bad weather data are modeled respectively, and the modeling steps are: according to the selected average main engine speed and average ground speed, the theoretical speed and the ship slip rate are calculated, and then the relationship between the theoretical speed and the main engine fuel consumption is fitted by the least squares method, and the relationship between the theoretical speed and the ship slip rate is fitted by the least squares method, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then the corresponding relationship between the average ground speed and the main engine fuel consumption is obtained, which is the ship main engine fuel consumption model, and finally four ship main engine fuel consumption models are constructed for the full load condition of good weather data, the ballast condition of good weather data, the full load condition of bad weather data and the ballast condition of bad weather data; The modeling steps of unified fitting plus draft correction are used. Good weather data and bad weather data are modeled separately according to the screened average draft of bow and stern. The modeling steps are: according to the screened average main engine speed and average ground speed, the theoretical speed and ship slip rate are calculated, and then the relationship between the theoretical speed and the main engine fuel consumption is fitted by the least squares method, and the relationship between the theoretical speed and the ship slip rate is fitted by the least squares method, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then the corresponding relationship between the average ground speed and the main engine fuel consumption is obtained, which is the ship main engine fuel consumption model, and the analysis is constructed. Two ship main engine fuel consumption models for good weather data and bad weather data are respectively formulated; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

2. The ship main engine fuel consumption modeling method based on midday report data according to claim 1 is characterized in that: In the noon report data collection and screening step, the preset screening conditions are: 23 hours <= sailing time <= 25 hours; 7kn <= average ground speed <= ship design speed; 0 < actual fuel consumption of the main engine <= fuel consumption corresponding to the rated power of the main engine * 1.5; 0 < average main engine speed <= rated speed of the main engine.

3. The ship main engine fuel consumption modeling method based on midday report data according to claim 1 is characterized in that: In the noon report data classification step, the noon report data that meets the screening conditions is classified as good weather data when the wind level is less than or equal to level 5 and the wave level is less than or equal to level 3, otherwise it is classified as bad weather data.

4. The ship main engine fuel consumption modeling method based on midday report data according to any one of claims 1 to 3 is characterized in that: In the load condition fitting modeling step and the unified fitting plus draft correction modeling step, the theoretical speed and the ship slip rate are calculated according to the average main engine speed and the average ground speed selected. The specific calculation formula is: Among them, V t is the theoretical speed, Slip is the slip rate of the ship, N s is the average main engine speed, Pitch is the ship propeller pitch, V g is the average ground speed.

5. The ship main engine fuel consumption modeling method based on midday report data according to claim 4 is characterized in that: In the load condition fitting modeling step and the unified fitting plus draft correction modeling step, the least squares method is used to fit the relationship between the theoretical speed and the main engine fuel consumption, and the fitting function form adopts a power function or a cubic polynomial without a constant term; the least squares method is used to fit the relationship between the theoretical speed and the ship slip rate, and the fitting function form adopts a linear function or a quadratic function.

6. The ship main engine fuel consumption modeling method based on midday report data according to claim 5 is characterized in that: In the unified fitting plus draft correction modeling step, a quadratic function is used to fit the relationship between the bow and stern average draft and the ratio to obtain a draft correction coefficient.

7. A ship main engine fuel consumption modeling system based on midday report data, characterized in that: It includes a midday report data collection and screening module, a midday report data classification module, a ship type classification module, a load condition fitting modeling module and a unified fitting plus draft correction modeling module, wherein the midday report data collection and screening module, the midday report data classification module and the ship type classification module are connected in sequence, and the ship type classification module is respectively connected to the load condition fitting modeling module and the unified fitting plus draft correction modeling module; The midday report data collection and screening module collects the sailing time, average speed over ground, actual fuel consumption of the main engine, average main engine speed, wind level, wave level and average draft of the bow and stern in the daily midday report data, and analyzes the collected midday report data according to the preset screening conditions; The midday report data classification module classifies the midday report data that meets the screening conditions into good weather data and bad weather data according to the level intervals of wind level and wave level; The ship type classification module is divided into two different steps of modeling according to different ship types. For a ship type with a fixed load condition, it enters the load condition fitting modeling module; for a ship type with a variable load condition, it enters the unified fitting plus draft correction modeling module; The load condition fitting modeling module divides the good weather data and the bad weather data into two load conditions, full load and ballast, according to the screened average draft of the bow and stern according to the preset load condition conditions, and then models the two load conditions of the good weather data and the two load conditions of the bad weather data respectively, and the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and the ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and finally construct four ship main engine fuel consumption models for the full load condition of good weather data, the ballast condition of good weather data, the full load condition of bad weather data and the ballast condition of bad weather data respectively; The unified fitting plus draft correction modeling module models the good weather data and the bad weather data respectively according to the screened average draft of the bow and stern, and the modeling steps are: according to the screened average main engine speed and average ground speed, calculate the theoretical speed and the ship slip rate, and then use the least squares method to fit the relationship between the theoretical speed and the main engine fuel consumption and the relationship between the theoretical speed and the ship slip rate, so as to obtain the corresponding relationship between the average ground speed and the theoretical speed, and then obtain the corresponding relationship between the average ground speed and the main engine fuel consumption, which is the ship main engine fuel consumption model, and construct Two ship main engine fuel consumption models for good weather data and bad weather data are respectively constructed; then, the main engine fuel consumption calculated value corresponding to the daily average speed over ground is calculated by using the constructed main engine fuel consumption models of each ship, and then the ratio of the collected and screened main engine actual fuel consumption to the main engine fuel consumption calculated value is calculated, and the relationship between the bow and stern average draft and the ratio is fitted to obtain the draft correction coefficient, and the two ship main engine fuel consumption models for good weather data and bad weather data are multiplied by their corresponding draft correction coefficients to obtain the two final ship main engine fuel consumption models for good weather data and bad weather data.

8. The ship main engine fuel consumption modeling system based on midday report data according to claim 7 is characterized in that: In the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the theoretical speed and the ship slip rate are calculated according to the average main engine speed and the average ground speed selected. The specific calculation formula is: Among them, V t is the theoretical speed of the ship, Slip is the slip rate, N s is the average main engine speed, Pitch is the ship propeller pitch, V g is the actual speed of the ship.

9. The ship main engine fuel consumption modeling system based on midday report data according to claim 8 is characterized in that: In the load condition fitting modeling module and the unified fitting plus draft correction modeling module, the least squares method is used to fit the relationship between the theoretical speed and the main engine fuel consumption, and the fitting function form adopts a power function or a cubic polynomial without a constant term; the least squares method is used to fit the relationship between the theoretical speed and the ship slip rate, and the fitting function form adopts a linear function or a quadratic function.

10. The ship main engine fuel consumption modeling system based on midday report data according to claim 9 is characterized in that: In the unified fitting plus draft correction modeling module, a quadratic function is used to fit the relationship between the bow and stern average draft and the ratio to obtain a draft correction coefficient.

Images