CN115577215B

CN115577215B - Real-time power estimation method, system, electronic device, storage medium and chip

Info

Publication number: CN115577215B
Application number: CN202211564955.0A
Authority: CN
Inventors: 梁韩旭; 张左悦
Original assignee: Elane Inc
Current assignee: Elane Inc
Priority date: 2022-12-07
Filing date: 2022-12-07
Publication date: 2023-03-24
Anticipated expiration: 2042-12-07
Also published as: CN115577215A

Abstract

The invention provides a real-time power estimation method, a real-time power estimation system, electronic equipment, a storage medium and a chip, and relates to the field of ship transportation, wherein the estimation method comprises the following steps: acquiring message information of an automatic ship identification system; determining the ship type; determining the length of the ship; determining the width of the ship; determining the maximum power of the ship; determining the maximum navigational speed of the ship; according to the type, the length, the width and the historical speed of the ship, and by combining an experience dictionary table, obtaining the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method; and obtaining a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the specific value, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship.

Description

Real-time power estimation method, system, electronic device, storage medium and chip

Technical Field

The invention relates to the field of ship transportation, in particular to a ship real-time power estimation method, a ship real-time power estimation system, electronic equipment, a computer readable storage medium and a chip.

Background

In the related art, the way of acquiring the real-time power of the ship is that the traditional sensor acquires the data of the single-ship engine room instrument, and the way cannot realize the dynamic estimation of the real-time power of the ship with the magnitude of millions.

Disclosure of Invention

In order to solve or improve the technical problem that the dynamic estimation of the real-time power of a ship with a large magnitude order cannot be realized, the invention aims to provide a ship real-time power estimation method.

Another object of the present invention is to provide a real-time power estimation system for a ship.

Another object of the present invention is to provide an electronic device.

It is another object of the present invention to provide a computer-readable storage medium.

Another object of the present invention is to provide a chip.

In order to achieve the above object, a first aspect of the present invention provides a method for estimating real-time power of a ship, including: acquiring ship automatic identification system message information sent by a ship, wherein the ship automatic identification system message information comprises a water mobile communication service identification code, a ship length, a ship width and a real-time navigational speed; acquiring a ship type through a water mobile communication service identification code, judging whether the ship type is effective, if so, determining the ship type, and if not, taking average values, standard deviations, kurtosis and skewness as characteristics of historical attachment frequency, navigation time, real-time navigation speed, on-berth time, equal-berth time and attachment rates of different berth attributes of the ship, and simulating and calculating the ship type through a first mathematical model; judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, determining the ship length, otherwise, simulating and calculating the ship length by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics; judging whether the ship width is effective or not by a long-wide scatter matrix region method, if so, determining the ship width, otherwise, simulating and calculating the ship width by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics; acquiring the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, and if not, simulating and calculating the maximum power through a decision tree model by taking the ship length, the ship width and the ship type as characteristics; acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective or not, if so, determining the maximum navigational speed, and otherwise, determining the maximum navigational speed according to the historical speed distribution of the ship; according to the ship type, the ship length, the ship width and the historical ship speed, and by combining an experience dictionary table, obtaining the ratio of the ship pitch to the ship pitch diameter through a Lagrange interpolation method; and obtaining a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the specific value, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship.

According to the technical scheme of the ship real-time power estimation method provided by the invention, the ship real-time power estimation method can be used for dynamically estimating the real-time power of a ship with a large magnitude order, provides theoretical support for future ship design and construction, reasonably optimizes the configuration of a ship main engine, and can avoid the waste phenomenon of 'large horse pulls a trolley' caused by mismatching of the main engine power and the actual operation condition to a great extent. In addition, the acquired real-time power can be used as basic data, and the oil consumption data can be obtained by multiplying the oil consumption coefficient and the duration, or the atmospheric emission data can be obtained by multiplying the atmospheric emission coefficient and the duration. The ship real-time power estimation method is used for remotely carrying out simulation monitoring on the ship real-time power by means of AIS (automatic identification system) space-time data. The ship real-time power estimation method firstly prejudges the data effectiveness and then fills up missing data by using a machine learning method, so that the logic rationality of calculation is improved.

The ship real-time power estimation method is used for estimating the real-time power of a ship with a large magnitude order, and comprises the following specific steps:

the method comprises the steps of firstly, acquiring message information of an automatic ship identification system sent by a ship, wherein the message information of the automatic ship identification system comprises a water mobile communication service identification code, a ship length, a ship width and a real-time speed. And the message information of the automatic ship identification system is AIS message information. An Automatic Identification System (AIS) for ships is composed of a base station or satellite facility and AIS equipment. GPS signals are accessed through the shipborne AIS equipment, and radio signals are sent to the outside through the AIS equipment and are used for navigation collision avoidance. The shore-based and satellite equipment can store and transmit the signals, and is the technical basis of the current shipping position big data. The identification code of the water mobile communication service is MMSI information. The type (ship type) of the ship, the maximum power of the ship, the maximum navigational speed of the ship and other data can be acquired through the overwater mobile communication service identification code;

and secondly, acquiring the ship type through the identification code of the water mobile communication service, judging whether the ship type is effective, if so, determining the ship type, and if not, taking the historical attachment frequency, the navigation time, the real-time navigation speed, the on-berth time, the equal-berth time and the attachment rates of different berth attributes of the ship as the characteristics, and simulating and calculating the ship type through a first mathematical model. After the type (ship type) of the ship is acquired through the marine mobile communication service identification code, the acquired information of the ship type needs to be judged to judge whether the ship type is valid or not. If the acquired information of the ship type is effective, determining the ship type; if the acquired ship model information is invalid (such as the situations of filling by mistake, missing information and the like), the ship model needs to be simulated and calculated through the first mathematical model. Optionally, the first mathematical model is an Ada-boost model. Optionally, the first mathematical model adopts an iterative algorithm, and the core idea is to train different classifiers (weak classifiers) for the same training set, and then assemble these weak classifiers to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, the kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve. In the step, the effectiveness of the data is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and thirdly, judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, determining the ship length, otherwise, simulating and calculating the ship length by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point where the captain is located is within the matrix area, the captain is valid; and if the point where the ship length is located is not in the matrix area, the ship length is invalid, and the ship length is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and fourthly, judging whether the ship width is effective or not by a long-wide scatter matrix area method, if so, determining the ship width, and if not, simulating and calculating the ship width by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point at which the beam is located is within the matrix area, the beam is valid; if the point where the ship width is located is not in the matrix area, the ship width is invalid, and the ship width is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and fifthly, acquiring the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, otherwise, simulating and calculating the maximum power by using a decision tree model with the characteristics of the ship length, the ship width and the ship type as characteristics. After the maximum power of the ship is obtained through the overwater mobile communication service identification code, the information or data of the obtained maximum power needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum power is effective (the value of the maximum power is in a reasonable range), determining the maximum power; if the obtained information of the maximum power is invalid (such as mis-filling, missing information or out of a reasonable range), the ship model needs to be simulated and calculated through the decision tree model. The decision tree model adopts a decision tree analysis method. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points outside the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and sixthly, acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective or not, if so, determining the maximum navigational speed, and otherwise, determining the maximum navigational speed according to the historical speed distribution of the ship. After the maximum navigational speed of the ship is acquired through the overwater mobile communication service identification code, the acquired information or data of the maximum navigational speed needs to be judged to judge whether the maximum power is effective or not. If the obtained information of the maximum navigational speed is effective (the numerical value of the maximum navigational speed is in a reasonable range), determining the maximum navigational speed; and if the acquired information of the maximum navigational speed is invalid (such as misfilling, information omission or out of a reasonable range), determining the maximum navigational speed according to the historical speed distribution of the ship. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and seventhly, acquiring the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed and by combining an experience dictionary table. The experience dictionary table is formed by feedback of questionnaires from a plurality of shipyards, shipowners, maritime offices, etc., which are manually visited in the field. The lagrange interpolation is a polynomial interpolation that gives a polynomial function that exactly passes through several known points on a two-dimensional plane. Polynomials of degree not exceeding n that satisfy the interpolation condition are present and unique;

and eighthly, acquiring a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the specific value, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship. Optionally, the second mathematical model is a BPSP model (Basic Principles of Ship Propulsion). The core of the BPSP model is to calculate or estimate the real-time power of the vessel. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the propeller speeds of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the vessel type configuration. Optionally, the data of the ratio of the ship pitch to the ship diameter is a numerical value obtained by the study of the visit, and the numerical value is different according to the ship type or the tonnage.

In the technical scheme defined by the invention, the ship real-time power estimation method can dynamically estimate the real-time power of a ship with a large magnitude order, provides theoretical support for future ship design and construction, reasonably optimizes the configuration of a ship main engine, and can avoid the waste phenomenon of 'large horse-drawn trolleys' caused by mismatching of the main engine power and the actual operation condition to a great extent. In addition, the acquired real-time power can be used as basic data, and the oil consumption data can be obtained by multiplying the oil consumption coefficient and the duration, or the atmospheric emission data can be obtained by multiplying the atmospheric emission coefficient and the duration. The ship real-time power estimation method is used for remotely carrying out simulation monitoring on the ship real-time power by means of AIS (automatic identification system) space-time data. The ship real-time power estimation method firstly prejudges the data effectiveness and then fills up missing data by using a machine learning method, so that the logic rationality of calculation is improved.

In addition, the technical scheme provided by the invention can also have the following additional technical characteristics:

in the above technical solution, the message information of the automatic ship identification system further includes a ship position longitude and a ship position latitude, and after the message information of the automatic ship identification system sent by a ship is acquired, the message information of the automatic ship identification system includes a marine mobile communication service identification code, a ship length, a ship width and a real-time speed, the method for estimating the real-time power of the ship further includes: determining a plurality of track positions of the navigation track of the ship according to the message information of the automatic ship identification system; and judging whether the track position is effective or not through a segmented track clustering algorithm, if so, acquiring the ship type through the overwater mobile communication service identification code, and otherwise, filling the invalid track position by adopting a Lagrange interpolation method.

In the technical scheme, the message information of the automatic ship identification system further comprises ship position longitude and ship position latitude. And acquiring a plurality of track positions of the navigation track of the ship according to the ship position longitude and the ship position latitude. Each of the vessel position longitude and the vessel position latitude corresponds to a set of coordinates. The position information of the ship can be determined according to the coordinate information. Further, after obtaining the message information of the ship automatic identification system sent by the ship, the method for estimating the real-time power of the ship further comprises the following specific steps:

and determining a plurality of track positions of the navigation track of the ship according to the message information of the automatic ship identification system. And acquiring a plurality of track positions of the navigation track of the ship according to the ship position longitude and the ship position latitude. Each of the vessel position longitude and the vessel position latitude corresponds to a set of coordinates. The position information of the ship can be determined according to the coordinate information;

and judging whether the track position is effective or not through a segmented track clustering algorithm, if so, acquiring the ship type through the overwater mobile communication service identification code, and otherwise, filling the invalid track position by adopting a Lagrange interpolation method. The track points are clustered in advance by the segmented track clustering algorithm, and the track points which cannot be clustered by the algorithm are considered as noise points and are removed in advance. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved.

In the above technical solution, before determining whether the track position is valid by using a segmented track clustering algorithm, the method for estimating the real-time power of the ship further includes: and (4) performing rarefaction on the track position through an iterative adaptive point algorithm.

In the technical scheme, before prejudging the data effectiveness, the method for estimating the real-time power of the ship further comprises the following specific steps:

and (4) performing rarefaction on the track position through an iterative adaptive point algorithm. The iterative adaptive point algorithm is the douglas-pock algorithm. An iterative adaptive point algorithm is one that approximates a curve as a series of points and reduces the number of points. And filling or thinning the track points by using a Douglas-Pock algorithm and a Lagrange interpolation method so as to improve the calculation efficiency or the calculation precision.

In the above technical solution, the first mathematical model is an Ada-boost model.

In the technical scheme, the first mathematical model adopts an iterative algorithm, and the core idea is to train different classifiers (weak classifiers) aiming at the same training set and then assemble the weak classifiers to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve.

In the above technical solution, the second mathematical model is a BPSP model.

In the technical scheme, the core of the BPSP model is to calculate or estimate the real-time power of the ship. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the propeller speeds of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the configuration of the vessel. Optionally, the ratio data of the ship pitch to the ship diameter is a value obtained by the study of the vessel, and the set value is different due to different sizes of ship types or tonnage.

In the above technical solution, determining the maximum navigational speed according to the historical speed distribution of the ship specifically includes: the maximum speed is 97% of the point of the historical speed distribution of the ship.

In the technical scheme, 97% quantile points of historical speed distribution of the ship are taken as the maximum navigational speed, so that the accuracy of maximum navigational speed estimation and the accuracy of the finally acquired real-time power are improved.

The second aspect of the present invention provides a real-time power estimation system for a ship, comprising: the system comprises an information acquisition unit, a data processing unit and a data processing unit, wherein the information acquisition unit is used for acquiring ship automatic identification system message information sent by a ship, and the ship automatic identification system message information comprises a water mobile communication service identification code, a ship length, a ship width and a real-time navigational speed; the first information processing unit is used for acquiring the ship type through the water mobile communication service identification code, judging whether the ship type is effective or not, if so, determining the ship type, and if not, taking the historical attachment frequency, the navigation time length, the real-time navigation speed, the on-berth time length, the equal-berth time length and the attachment rates of different berth attributes of the ship as features, and simulating and calculating the ship type through a first mathematical model; the second information processing unit is used for judging whether the ship length is effective or not by a length-width scatter matrix region method, determining the ship length if the ship length is effective, and simulating and calculating the ship length by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship type as characteristics if the ship length is not effective; the third information processing unit is used for judging whether the ship width is effective or not by a long-wide scatter matrix area method, determining the ship width if the ship width is effective, and simulating and calculating the ship width by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics if the ship width is not effective; the fourth information processing unit is used for acquiring the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, and if not, simulating and calculating the maximum power by using a decision tree model by taking the ship length, the ship width and the ship type as characteristics; the fifth information processing unit is used for acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective or not, if so, determining the maximum navigational speed, and otherwise, determining the maximum navigational speed according to the historical speed distribution of the ship; the sixth information processing unit is used for acquiring the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed in combination with an experience dictionary table; and the seventh information processing unit is used for acquiring the load rate coefficient of the ship through the second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship.

According to the technical scheme of the ship real-time power estimation system, the ship real-time power estimation system comprises an information acquisition unit, a first information processing unit, a second information processing unit, a third information processing unit, a fourth information processing unit, a fifth information processing unit, a sixth information processing unit and a seventh information processing unit. Specifically, the information acquisition unit is used for acquiring ship automatic identification system message information sent by a ship. The message information of the automatic ship identification system comprises an identification code of the aquatic mobile communication service, the ship length, the ship width and the real-time navigational speed. And the message information of the automatic ship identification system is AIS message information. An Automatic Identification System (AIS) for ships is composed of a base station or satellite facility and AIS equipment. GPS signals are accessed through the shipborne AIS equipment, and radio signals are sent to the outside through the AIS equipment and are used for navigation collision avoidance. The shore-based and satellite equipment can store and transmit the signals, and is the technical basis of the current shipping position big data. The identification code of the water mobile communication service is MMSI information. The type (ship type) of the ship, the maximum power of the ship, the maximum navigational speed of the ship and other data can be obtained through the marine mobile communication service identification code.

Further, the first information processing unit is used for obtaining the ship type through the water mobile communication service identification code, judging whether the ship type is effective or not, if not, determining the ship type, and if not, taking the historical attachment frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the attachment rates of different parking attributes of the ship as features, and simulating and calculating the ship type through a first mathematical model. After the type (ship type) of the ship is acquired through the marine mobile communication service identification code, the acquired information of the ship type needs to be judged to judge whether the ship type is valid or not. If the acquired information of the ship type is effective, determining the ship type; if the acquired ship model information is invalid (such as the situations of filling by mistake, missing information and the like), the ship model needs to be simulated and calculated through the first mathematical model. Optionally, the first mathematical model is an Ada-boost model. Alternatively, the first mathematical model adopts an iterative algorithm, and its core idea is to train different classifiers (weak classifiers) for the same training set, and then to group these weak classifiers together to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, the kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve.

Further, the second information processing unit is used for judging whether the ship length is effective or not through a long-wide scatter matrix area method, if so, the ship length is determined, and if not, the ship length is simulated and calculated through a decision tree method by taking the historical attachment berth attribute, the real-time navigational speed and the ship type as characteristics. If the point where the captain is located is within the matrix area, the captain is valid; and if the point where the ship length is located is not in the matrix area, the ship length is invalid, and the ship length is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values.

Further, the third information processing unit is used for judging whether the ship width is effective or not through a long-wide scatter matrix area method, if so, the ship width is determined, and if not, the ship width is simulated and calculated through a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point at which the beam is located is within the matrix area, the beam is valid; if the point of the ship width is not in the matrix area, the ship width is invalid, and the ship width is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in decision by using probability and a tree in a graph theory so as to obtain an optimal scheme.

Further, the fourth information processing unit is used for obtaining the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, and if not, simulating and calculating the maximum power through a decision tree model by taking the ship length, the ship width and the ship type as characteristics. After the maximum power of the ship is obtained through the overwater mobile communication service identification code, the information or data of the obtained maximum power needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum power is effective (the value of the maximum power is in a reasonable range), determining the maximum power; if the obtained information of the maximum power is invalid (such as mis-filling, missing information or out of a reasonable range), the ship model needs to be simulated and calculated through the decision tree model. The decision tree model adopts a decision tree analysis method. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values.

Further, the fifth information processing unit is used for acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective or not, if so, determining the maximum navigational speed, and otherwise, determining the maximum navigational speed according to the historical speed distribution of the ship. After the maximum navigational speed of the ship is acquired through the overwater mobile communication service identification code, the acquired information or data of the maximum navigational speed needs to be judged to judge whether the maximum power is effective or not. If the obtained information of the maximum navigational speed is effective (the numerical value of the maximum navigational speed is in a reasonable range), determining the maximum navigational speed; and if the acquired information of the maximum navigational speed is invalid (such as mis-filling, missing information or out of a reasonable range), determining the maximum navigational speed according to the historical speed distribution of the ship.

Further, the sixth information processing unit is used for acquiring the ratio of the ship pitch to the ship pitch diameter through a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed by combining an experience dictionary table. The experience dictionary table is formed by feedback of questionnaires from a plurality of shipyards, shipowners, maritime offices, etc., which are manually visited in the field. The lagrange interpolation is a polynomial interpolation that gives a polynomial function that exactly passes through several known points on a two-dimensional plane. Polynomials of degree not exceeding n that satisfy the interpolation condition are present and unique.

Further, the seventh information processing unit is used for obtaining a load rate coefficient of the ship through the second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship. Optionally, the second mathematical model is the BPSP model (Basic Principles of Ship Propulsion). The core of the BPSP model is to calculate or estimate the real-time power of the vessel. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the propeller speeds of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the vessel type configuration. Optionally, the data of the ratio of the ship pitch to the ship diameter is a numerical value obtained by the study of the visit, and the numerical value is different according to the ship type or the tonnage.

In the technical scheme defined by the invention, the ship real-time power estimation system can dynamically estimate the real-time power of a ship with a large magnitude order, provides theoretical support for future ship design and construction, reasonably optimizes the configuration of a ship main engine, and can avoid the waste phenomenon of 'large horse-drawn trolleys' caused by mismatching of the main engine power and the actual operation condition to a great extent. In addition, the acquired real-time power can be used as basic data, and the oil consumption data can be obtained by multiplying the oil consumption coefficient and the duration, or the atmospheric emission data can be obtained by multiplying the atmospheric emission coefficient and the duration. The ship real-time power estimation system remotely carries out simulation monitoring on the ship real-time power by means of AIS (automatic identification system) space-time data. The ship real-time power estimation system judges the data validity in advance, and then fills up missing data by using a machine learning method, so that the logic rationality of calculation is improved.

A third aspect of the present invention provides an electronic device, comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method for estimating real-time power of a ship in any of the above embodiments.

A fourth aspect of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the ship real-time power estimation method in any of the above embodiments.

A fifth aspect of the present invention provides a chip, where the chip includes a processor and a communication interface, and the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the steps of the real-time power estimation method for a ship in any of the above embodiments.

Additional aspects and advantages of the present teachings will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present teachings.

Drawings

FIG. 1 illustrates a first flowchart of a vessel real-time power estimation method according to one embodiment of the invention;

FIG. 2 illustrates a second flowchart of a vessel real-time power estimation method according to one embodiment of the invention;

FIG. 3 shows a schematic diagram of a vessel real-time power estimation system according to one embodiment of the invention.

Wherein, the corresponding relationship between the reference numbers and the names of the components in fig. 3 is:

400: a ship real-time power estimation system; 410: an information acquisition unit; 421: a first information processing unit; 422: a second information processing unit; 423: a third information processing unit; 424: a fourth information processing unit; 425: a fifth information processing unit; 426: a sixth information processing unit; 427: a seventh information processing unit.

Detailed Description

In order that the above objects, features and advantages of the embodiments of the present invention can be more clearly understood, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, embodiments of the present invention may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.

A ship real-time power estimation method, a ship real-time power estimation system 400, an electronic device, a computer-readable storage medium, and a chip provided according to some embodiments of the present invention are described below with reference to fig. 1 to 3.

In an embodiment according to the present invention, as shown in fig. 1, the method for estimating real-time power of a ship includes the following specific steps:

s102, acquiring message information of an automatic ship identification system sent by a ship, wherein the message information of the automatic ship identification system comprises a water mobile communication service identification code, a ship length, a ship width and a real-time speed. And the message information of the automatic ship identification system is AIS message information. An Automatic Identification System (AIS) for ships is composed of a base station or satellite facility and AIS equipment. GPS signals are accessed through the shipborne AIS equipment, and radio signals are sent to the outside through the AIS equipment and are used for navigation collision avoidance. The shore-based and satellite equipment can store and transmit the signals, and is the technical basis of the current ship position shipping big data. The identification code of the water mobile communication service is MMSI information. The type (ship type) of the ship, the maximum power of the ship, the maximum navigational speed of the ship and other data can be acquired through the overwater mobile communication service identification code;

and S104, acquiring the ship type through the identification code of the water mobile communication service, judging whether the ship type is effective, if so, determining the ship type, and if not, simulating and calculating the ship type through a first mathematical model by taking the historical attachment frequency, the navigation time, the real-time navigation speed, the on-berth time, the equal-berth time and the attachment rates of different berth attributes of the ship as features. After the type (ship type) of the ship is acquired through the marine mobile communication service identification code, the acquired information of the ship type needs to be judged to judge whether the ship type is valid or not. If the acquired information of the ship type is effective, determining the ship type; if the acquired ship model information is invalid (such as the situations of filling by mistake, missing information and the like), the ship model needs to be simulated and calculated through the first mathematical model. Optionally, the first mathematical model is an Ada-boost model. Alternatively, the first mathematical model adopts an iterative algorithm, and its core idea is to train different classifiers (weak classifiers) for the same training set, and then to group these weak classifiers together to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, the kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S106, judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, determining the ship length, otherwise, simulating and calculating the ship length by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point where the captain is located is within the matrix area, the captain is valid; and if the point where the ship length is located is not in the matrix area, the ship length is invalid, and the ship length is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree consists of tree roots (decision nodes), other interior points (scheme nodes and state nodes), leaves (terminal points), branches (scheme branches and probability branches), probability values and benefit values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S108, judging whether the ship width is effective or not by a long-wide scatter matrix area method, if so, determining the ship width, and otherwise, simulating and calculating the ship width by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point at which the beam is located is within the matrix area, the beam is valid; if the point of the ship width is not in the matrix area, the ship width is invalid, and the ship width is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. In the step, the effectiveness of the data is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S110, acquiring the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective, if so, determining the maximum power, otherwise, simulating and calculating the maximum power by using a decision tree model with the characteristics of the ship length, the ship width and the ship type as characteristics. After the maximum power of the ship is obtained through the overwater mobile communication service identification code, the obtained maximum power information or data needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum power is effective (the value of the maximum power is in a reasonable range), determining the maximum power; if the obtained information of the maximum power is invalid (such as mis-filling, missing information or out of a reasonable range), the ship model needs to be simulated and calculated through the decision tree model. The decision tree model adopts a decision tree analysis method. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

s112, acquiring the maximum navigational speed of the ship through the overwater mobile communication service identification code, judging whether the maximum navigational speed is effective, if so, determining the maximum navigational speed, and otherwise, determining the maximum navigational speed according to the historical speed distribution of the ship. After the maximum navigational speed of the ship is obtained through the overwater mobile communication service identification code, the obtained information or data of the maximum navigational speed needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum navigational speed is effective (the numerical value of the maximum navigational speed is in a reasonable range), determining the maximum navigational speed; and if the acquired information of the maximum navigational speed is invalid (such as mis-filling, missing information or out of a reasonable range), determining the maximum navigational speed according to the historical speed distribution of the ship. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S114, acquiring the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed and by combining an empirical dictionary table. The experience dictionary table is formed by feedback of questionnaires from a plurality of shipyards, shipowners, maritime offices, etc., which are manually visited in the field. The lagrange interpolation is a polynomial interpolation that gives a polynomial function that exactly passes through several known points on a two-dimensional plane. Polynomials of degree not exceeding n that satisfy the interpolation condition are present and unique;

and S116, obtaining a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship. Optionally, the second mathematical model is a BPSP model (Basic Principles of Ship Propulsion). The core of the BPSP model is to calculate or estimate the real-time power of the vessel. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the speed of the propeller of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the vessel type configuration. Optionally, the ratio data of the ship pitch to the ship diameter is a value obtained by the study of the vessel, and the set value is different due to different sizes of ship types or tonnage.

In the technical scheme defined by the invention, the ship real-time power estimation method can dynamically estimate the real-time power of a ship with a large magnitude order, provides theoretical support for future ship design and construction, reasonably optimizes the configuration of a ship main engine, and can avoid the waste phenomenon of 'large horse-drawn trolleys' caused by mismatching of the main engine power and the actual operation condition to a great extent. In addition, the acquired real-time power can be used as basic data, and the oil consumption data can be obtained by multiplying the oil consumption coefficient and the time length, or the atmospheric emission data can be obtained by multiplying the atmospheric emission coefficient and the time length. The ship real-time power estimation method is used for remotely carrying out simulation monitoring on the ship real-time power by means of AIS (automatic identification system) space-time data. The ship real-time power estimation method firstly prejudges the data effectiveness and then fills up missing data by using a machine learning method, so that the logic rationality of calculation is improved.

In an embodiment according to the present invention, as shown in fig. 2, the method for estimating real-time power of a ship includes the following specific steps:

s202, acquiring message information of an automatic ship identification system sent by a ship, wherein the message information of the automatic ship identification system comprises a water mobile communication service identification code, a ship length, a ship width, a real-time navigational speed, a ship position longitude and a ship position latitude. And the message information of the automatic ship identification system is AIS message information. An Automatic Identification System (AIS) for ships is composed of a base station or satellite facility and AIS equipment. GPS signals are accessed through the shipborne AIS equipment, and radio signals are sent to the outside through the AIS equipment and are used for navigation collision avoidance. The shore-based and satellite equipment can store and transmit the signals, and is the technical basis of the current ship position shipping big data. The identification code of the water mobile communication service is MMSI information. The type (ship type) of the ship, the maximum power of the ship, the maximum navigational speed of the ship and other data can be acquired through the overwater mobile communication service identification code;

and S204, determining a plurality of track positions of the navigation track of the ship according to the message information of the automatic ship identification system. And acquiring a plurality of track positions of the navigation track of the ship according to the ship position longitude and the ship position latitude. Each of the vessel position longitude and the vessel position latitude corresponds to a set of coordinates. The position information of the ship can be determined according to the coordinate information;

and S206, performing rarefaction on the track position through an iterative adaptive point algorithm. The iterative adaptive point algorithm is the douglas-pock algorithm. An iterative adaptive point algorithm is an algorithm that approximates a curve as a series of points and reduces the number of points. Filling or thinning the track points by using a Douglas-Puck algorithm and a Lagrange interpolation method so as to improve the calculation efficiency or the calculation precision;

and S208, judging whether the track position is effective or not through a segmented track clustering algorithm, if so, acquiring the ship type through the overwater mobile communication service identification code, and otherwise, filling the invalid track position by adopting a Lagrange interpolation method. The track points are clustered in advance by the segmented track clustering algorithm, and the track points which cannot be clustered by the algorithm are considered as noise points and are removed in advance. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S210, acquiring the ship type through the identification code of the water mobile communication service, judging whether the ship type is effective or not, if not, determining the ship type, and if not, simulating and calculating the ship type through a first mathematical model by taking the historical attachment frequency, the navigation time, the real-time navigation speed, the on-berth time, the equal-berth time and the attachment rates of different berth attributes of the ship as characteristics. After the type (ship type) of the ship is acquired through the marine mobile communication service identification code, the acquired information of the ship type needs to be judged to judge whether the ship type is valid or not. If the acquired information of the ship type is effective, determining the ship type; if the acquired ship model information is invalid (such as the situations of filling by mistake, missing information and the like), the ship model needs to be simulated and calculated through the first mathematical model. Optionally, the first mathematical model is an Ada-boost model. Alternatively, the first mathematical model adopts an iterative algorithm, and its core idea is to train different classifiers (weak classifiers) for the same training set, and then to group these weak classifiers together to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, the kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S212, judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, determining the ship length, and if not, simulating and calculating the ship length by a decision tree method by taking the historical attached berth attribute, the real-time speed and the ship type as characteristics. If the point at which the captain is located is within the matrix area, the captain is valid; and if the point where the ship length is located is not in the matrix area, the ship length is invalid, and the ship length is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree consists of tree roots (decision nodes), other interior points (scheme nodes and state nodes), leaves (terminal points), branches (scheme branches and probability branches), probability values and benefit values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

s214, judging whether the ship width is effective or not by a long-wide scatter matrix area method, if so, determining the ship width, and if not, simulating and calculating the ship width by a decision tree method by taking the historical berth attribute, the real-time navigational speed and the ship shape as characteristics. If the point at which the craft width is located is within the matrix area, then the craft width is valid; if the point of the ship width is not in the matrix area, the ship width is invalid, and the ship width is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

s216, obtaining the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, and if not, simulating and calculating the maximum power by using a decision tree model with the characteristics of the ship length, the ship width and the ship type as characteristics. After the maximum power of the ship is obtained through the overwater mobile communication service identification code, the information or data of the obtained maximum power needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum power is effective (the value of the maximum power is in a reasonable range), determining the maximum power; if the obtained information of the maximum power is invalid (such as mis-filling, missing information or out of a reasonable range), the ship model needs to be simulated and calculated through the decision tree model. The decision tree model adopts a decision tree analysis method. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

s218, acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective or not, if so, determining the maximum navigational speed, and otherwise, taking 97% quantile points of the historical speed distribution of the ship as the maximum navigational speed. After the maximum navigational speed of the ship is acquired through the overwater mobile communication service identification code, the acquired information or data of the maximum navigational speed needs to be judged to judge whether the maximum power is effective or not. If the obtained information of the maximum navigational speed is effective (the numerical value of the maximum navigational speed is in a reasonable range), determining the maximum navigational speed; and if the acquired information of the maximum navigational speed is invalid (such as mis-filling, missing information or out of a reasonable range), determining the maximum navigational speed according to the historical speed distribution of the ship. By taking 97% quantiles of the historical speed distribution of the ship as the maximum navigational speed, the accuracy of maximum navigational speed estimation and the accuracy of the finally-obtained real-time power are improved. In the step, the data effectiveness is pre-judged, and then the missing data is filled by using a machine learning method, so that the logic rationality of calculation is improved;

and S220, acquiring the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed and by combining an experience dictionary table. The experience dictionary table is formed by feedback of questionnaires from a plurality of shipyards, shipowners, maritime offices, etc., which are manually visited in the field. The lagrange interpolation is a polynomial interpolation that gives a polynomial function that exactly passes through several known points on a two-dimensional plane. Polynomials of degree not exceeding n that satisfy the interpolation condition are present and unique;

s222, obtaining a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship. Optionally, the second mathematical model is a BPSP model (Basic Principles of Ship Propulsion). The core of the BPSP model is to calculate or estimate the real-time power of the vessel. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the propeller speeds of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the vessel type configuration. Optionally, the data of the ratio of the ship pitch to the ship diameter is a numerical value obtained by the study of the visit, and the numerical value is different according to the ship type or the tonnage.

In one embodiment according to the present invention, as shown in fig. 3, the ship real-time power estimation system 400 includes an information acquisition unit 410, a first information processing unit 421, a second information processing unit 422, a third information processing unit 423, a fourth information processing unit 424, a fifth information processing unit 425, a sixth information processing unit 426, and a seventh information processing unit 427. Specifically, the information obtaining unit 410 is configured to obtain ship automatic identification system message information sent by a ship. The message information of the automatic ship identification system comprises an identification code of the aquatic mobile communication service, the ship length, the ship width and the real-time navigational speed. And the message information of the automatic ship identification system is AIS message information. An Automatic Identification System (AIS) for ships comprises a base station or satellite facility and a ship AIS device. GPS signals are accessed through the shipborne AIS equipment, and radio signals are sent to the outside through the AIS equipment and are used for navigation collision avoidance. The shore-based and satellite equipment can store and transmit the signals, and is the technical basis of the current shipping position big data. The identification code of the water mobile communication service is MMSI information. The type (ship type) of the ship, the maximum power of the ship, the maximum navigational speed of the ship and other data can be obtained through the marine mobile communication service identification code.

Further, the first information processing unit 421 is configured to obtain a ship model through the marine mobile communication service identification code, determine whether the ship model is valid, determine the ship model if the ship model is valid, and simulate and calculate the ship model through a first mathematical model if the ship model is not valid, and otherwise take an average, a standard deviation, a kurtosis and a skewness as features of historical attachment frequency, navigation duration, real-time navigation speed, berthing duration of a ship, and attachment rates of different berth attributes. After the type (ship type) of the ship is acquired through the marine mobile communication service identification code, the acquired information of the ship type needs to be judged to judge whether the ship type is valid or not. If the acquired information of the ship type is effective, determining the ship type; if the acquired ship model information is invalid (such as the situations of filling by mistake, missing information and the like), the ship model needs to be simulated and calculated through the first mathematical model. Optionally, the first mathematical model is an Ada-boost model. Alternatively, the first mathematical model adopts an iterative algorithm, and its core idea is to train different classifiers (weak classifiers) for the same training set, and then to group these weak classifiers together to form a stronger final classifier (strong classifier). Specifically, the historical docking frequency, the navigation time, the real-time navigation speed, the parking time, the equal parking time and the docking rates of different parking attributes of the ship are used as characteristics or parameters, and the average value, the standard deviation, the kurtosis and the skewness are taken. Wherein the average includes an arithmetic average, a geometric average, a squared average, a harmonic average, a weighted average, and the like. The standard deviation is the arithmetic square root of the arithmetic mean (i.e., the variance) of the squared deviation. The standard deviation is also called standard deviation, or experimental standard deviation, and is most commonly used in probability statistics as a measure of the degree of statistical distribution. The kurtosis is also called as a kurtosis coefficient and represents the characteristic number of the probability density distribution curve of the peak value height at the average value. Intuitively, the kurtosis reflects the sharpness of the peak. In statistics, kurtosis measures the kurtosis of the probability distribution of real random variables. High kurtosis means that the variance increase is caused by extreme differences at low frequencies that are greater or less than the mean. Skewness is also called skewness and skewness coefficient, and is a measure of the skewness direction and degree of statistical data distribution, and is also a digital characteristic of the asymmetry degree of the statistical data distribution. Intuitively, skewness is the relative length of the tail of the density function curve.

Further, the second information processing unit 422 is configured to determine whether the ship length is valid by using a length-width scatter matrix area method, determine the ship length if the ship length is valid, and simulate and calculate the ship length by using a decision tree method if the ship length is not valid by using the historical attached berth attribute, the real-time navigational speed, and the ship type as characteristics if the ship length is not valid. If the point where the captain is located is within the matrix area, the captain is valid; and if the point where the ship length is located is not in the matrix area, the ship length is invalid, and the ship length is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values.

Further, the third information processing unit 423 is configured to determine whether the ship width is valid by using a long-wide scatter matrix area method, determine the ship width if the ship width is valid, and simulate and calculate the ship width by using a decision tree method by using the historical berth attribute, the real-time navigational speed, and the ship shape as features if the ship width is not valid. If the point at which the beam is located is within the matrix area, the beam is valid; if the point of the ship width is not in the matrix area, the ship width is invalid, and the ship width is simulated and calculated through a decision tree method. Decision tree methods are decision tree analysis methods. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme.

Further, the fourth information processing unit 424 is configured to obtain a maximum power of the ship through the marine mobile communication service identification code, determine whether the maximum power is valid, determine the maximum power if the maximum power is valid, and simulate and calculate the maximum power through a decision tree model with the ship length, the ship width, and the ship type as features if the maximum power is not valid. After the maximum power of the ship is obtained through the overwater mobile communication service identification code, the information or data of the obtained maximum power needs to be judged, and whether the maximum power is effective or not is judged. If the obtained information of the maximum power is effective (the value of the maximum power is in a reasonable range), determining the maximum power; if the obtained information of the maximum power is invalid (such as mis-filling, missing information or out of a reasonable range), the ship model needs to be simulated and calculated through the decision tree model. The decision tree model adopts a decision tree analysis method. The decision tree analysis method is a risk type decision method which compares different schemes in a decision by using probability and a tree in a graph theory so as to obtain an optimal scheme. The tree in the graph theory is a connected and loop-free directed graph, a point with an in-degree of 0 is called a root, a point with an out-degree of 0 is called a leaf, and points except the leaf are called inner points. The decision tree is composed of tree roots (decision nodes), other interior points (scheme nodes, state nodes), leaves (end points), branches (scheme branches, probability branches), probability values and profit and loss values.

Further, the fifth information processing unit 425 is configured to obtain the maximum speed of the ship through the marine mobile communication service identification code, determine whether the maximum speed is valid, determine the maximum speed if the maximum speed is valid, and determine the maximum speed according to the historical speed distribution of the ship if the maximum speed is not valid. After the maximum navigational speed of the ship is acquired through the overwater mobile communication service identification code, the acquired information or data of the maximum navigational speed needs to be judged to judge whether the maximum power is effective or not. If the obtained information of the maximum navigational speed is effective (the numerical value of the maximum navigational speed is in a reasonable range), determining the maximum navigational speed; and if the acquired information of the maximum navigational speed is invalid (such as mis-filling, missing information or out of a reasonable range), determining the maximum navigational speed according to the historical speed distribution of the ship.

Further, the sixth information processing unit 426 is configured to obtain a ratio of the ship pitch to the ship pitch diameter by a lagrangian interpolation method according to the ship type, the ship length, the ship width, and the historical ship speed, and by combining an empirical dictionary table. The experience dictionary table is formed by feedback of questionnaires from a plurality of shipyards, shipowners, maritime offices, etc., which are manually visited in the field. The lagrange interpolation is a polynomial interpolation that gives a polynomial function that exactly passes through several known points on a two-dimensional plane. Polynomials of degree not exceeding n that satisfy the interpolation condition are present and unique.

Further, the seventh information processing unit 427 is configured to obtain a load factor of the ship through the second mathematical model according to the real-time speed, the maximum speed and the ratio, and multiply the maximum power by the load factor to obtain the real-time power of the ship. Optionally, the second mathematical model is a BPSP model (Basic Principles of Ship Propulsion). The core of the BPSP model is to calculate or estimate the real-time power of the ship. The real-time power ratio of the ship at the first moment and the second moment is equal to alph power of the ratio of the propeller speeds of the ship at the first moment and the second moment. Wherein, alph power refers to the ratio of the ship pitch to the ship pitch diameter. The ratio of the pitch of the vessel to the diameter of the vessel may also vary, typically between 3 and 4, depending on the vessel type configuration. Optionally, the data of the ratio of the ship pitch to the ship diameter is a numerical value obtained by the study of the visit, and the numerical value is different according to the ship type or the tonnage.

In one embodiment according to the present invention, an electronic device includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the ship real-time power estimation method in any of the above embodiments.

In an embodiment according to the invention, a computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of the method for real-time power estimation of a vessel in any of the above embodiments.

In an embodiment according to the present invention, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the steps of the real-time power estimation method for a ship in any of the above embodiments.

According to the embodiment of the ship real-time power estimation method, the ship real-time power estimation system, the electronic equipment, the computer readable storage medium and the chip, the real-time power of a ship with large magnitude can be dynamically estimated, theoretical support is provided for future ship design and construction, the ship main engine configuration is reasonably optimized, and the phenomenon of 'large horse pulls a trolley' caused by mismatching of the main engine power and the actual operation condition can be avoided to a great extent. In addition, the acquired real-time power can be used as basic data, and the oil consumption data can be obtained by multiplying the oil consumption coefficient and the duration, or the atmospheric emission data can be obtained by multiplying the atmospheric emission coefficient and the duration. The ship real-time power estimation method is used for remotely carrying out simulation monitoring on the ship real-time power by means of AIS (automatic identification system) space-time data. The ship real-time power estimation method firstly prejudges the data effectiveness and then fills up missing data by using a machine learning method, so that the logic rationality of calculation is improved.

In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; the term "plurality" means two or more unless expressly limited otherwise. The terms "mounted," "connected," "fixed," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection; "coupled" may be direct or indirect through an intermediary. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", "front", "rear", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or unit must have a specific direction, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.

In the description herein, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for estimating real-time power of a ship is characterized by comprising the following steps:

acquiring ship automatic identification system message information sent by a ship, wherein the ship automatic identification system message information comprises a water mobile communication service identification code, a ship length, a ship width and a real-time navigational speed;

acquiring a ship type through the water mobile communication service identification code, judging whether the ship type is effective or not, if so, determining the ship type, and if not, simulating and calculating the ship type through a first mathematical model by taking the historical attachment frequency, the navigation time, the real-time navigation speed, the on-berth time, the equal-berth time and the attachment rates of different berth attributes of the ship as features;

judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, determining the ship length, and if not, simulating and calculating the ship length by a decision tree method by taking the historical berthing attribute, the real-time navigational speed and the ship type as characteristics;

judging whether the ship width is effective or not by the long-wide scatter matrix region method, if so, determining the ship width, and if not, simulating and calculating the ship width by the decision tree method by taking the historical berthing attribute, the real-time navigational speed and the ship type as characteristics;

obtaining the maximum power of the ship through the overwater mobile communication service identification code, judging whether the maximum power is effective or not, if so, determining the maximum power, and if not, simulating and calculating the maximum power through a decision tree model by taking the ship length, the ship width and the ship type as characteristics;

acquiring the maximum speed of the ship through the overwater mobile communication service identification code, judging whether the maximum speed is effective or not, if so, determining the maximum speed, and otherwise, determining the maximum speed according to the historical speed distribution of the ship;

according to the ship type, the ship length, the ship width and the historical ship speed, and by combining an experience dictionary table, obtaining the ratio of the ship pitch to the ship pitch diameter by a Lagrange interpolation method;

and obtaining a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship.

2. The method according to claim 1, wherein the vessel automatic identification system message information further includes a vessel position longitude and a vessel position latitude, and after the obtaining of the vessel automatic identification system message information sent by the vessel, the vessel automatic identification system message information includes a marine mobile communication service identification code, a ship length, a ship width and a real-time speed, the method further includes:

determining a plurality of track positions of the navigation track of the ship according to the message information of the automatic ship identification system;

and judging whether the track position is effective or not through a segmented track clustering algorithm, if so, acquiring the ship type through the overwater mobile communication service identification code, and if not, filling the invalid track position by adopting the Lagrange interpolation method.

3. The method according to claim 2, wherein before the determining whether the track position is valid by the piecewise track clustering algorithm, the method further comprises:

and performing rarefaction on the track position through an iterative adaptive point algorithm.

4. The method according to any one of claims 1 to 3, wherein the first mathematical model is an Ada-boost model.

5. The method according to any one of claims 1 to 3, wherein the second mathematical model is a BPSP model.

6. The method for estimating real-time power of a ship according to any one of claims 1 to 3, wherein the determining the maximum speed according to the historical speed distribution of the ship comprises:

taking a 97% quantile of the historical speed profile of the vessel as the maximum speed.

7. A real-time power estimation system for a marine vessel, comprising:

the system comprises an information acquisition unit (410) and a control unit, wherein the information acquisition unit is used for acquiring ship automatic identification system message information sent by a ship, and the ship automatic identification system message information comprises a water mobile communication service identification code, a ship length, a ship width and a real-time navigational speed;

a first information processing unit (421) for acquiring a ship type through the identification code of the water mobile communication service, judging whether the ship type is valid or not, if so, determining the ship type, and if not, simulating and calculating the ship type through a first mathematical model by taking the historical attachment frequency, the navigation time, the real-time navigation speed, the berthing time, the equal berthing time of the ship, and the attachment rates of different berth attributes as characteristics, such as an average value, a standard deviation, a kurtosis and a skewness;

the second information processing unit (422) is used for judging whether the ship length is effective or not by a length-width scatter matrix region method, if so, the ship length is determined, and if not, the ship length is simulated and calculated by a decision tree method by taking the historical berthing attribute, the real-time navigational speed and the ship type as characteristics;

a third information processing unit (423) for judging whether the ship width is valid or not by the long-wide scatter matrix area method, if so, determining the ship width, and if not, simulating and calculating the ship width by the decision tree method by taking the historical berthing attribute, the real-time navigational speed and the ship type as characteristics;

a fourth information processing unit (424) for obtaining the maximum power of the ship through the marine mobile communication service identification code, judging whether the maximum power is effective, if so, determining the maximum power, and if not, simulating and calculating the maximum power through a decision tree model by taking the ship length, the ship width and the ship type as characteristics;

a fifth information processing unit (425) for acquiring the maximum navigational speed of the ship through the marine mobile communication service identification code, judging whether the maximum navigational speed is effective, if so, determining the maximum navigational speed, and if not, determining the maximum navigational speed according to the historical speed distribution of the ship;

a sixth information processing unit (426) for acquiring a ratio of a ship pitch to a ship pitch diameter by a Lagrange interpolation method according to the ship type, the ship length, the ship width and the historical ship speed in combination with an empirical dictionary table;

and the seventh information processing unit (427) is used for acquiring a load rate coefficient of the ship through a second mathematical model according to the real-time navigational speed, the maximum navigational speed and the ratio, and multiplying the maximum power by the load rate coefficient to obtain the real-time power of the ship.

8. An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the method of real-time power estimation of a vessel according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, carries out the steps of the method for real-time power estimation of a ship according to any one of claims 1 to 6.

10. A chip comprising a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to execute a program or instructions to carry out the steps of the method of real-time power estimation of a ship according to any one of claims 1 to 6.