CN115675780B - Ship draught prediction method and system, electronic equipment and readable storage medium - Google Patents
Ship draught prediction method and system, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN115675780B CN115675780B CN202211715318.9A CN202211715318A CN115675780B CN 115675780 B CN115675780 B CN 115675780B CN 202211715318 A CN202211715318 A CN 202211715318A CN 115675780 B CN115675780 B CN 115675780B
- Authority
- CN
- China
- Prior art keywords
- ship
- draft
- lockage
- historical
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 14
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 3
- 238000009472 formulation Methods 0.000 abstract description 3
- 239000000203 mixture Substances 0.000 abstract description 3
- 238000012954 risk control Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000003646 Spearman's rank correlation coefficient Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a ship draught prediction method, a ship draught prediction system, electronic equipment and a readable storage medium, wherein the method comprises the following steps: acquiring a historical ship lockage data set, wherein the historical ship lockage data set comprises a plurality of ship qualitative parameters; dividing a historical ship lockage data set into a plurality of historical ship lockage data subsets based on ship qualitative parameters, wherein each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft; determining a plurality of significant quantitative parameters of the plurality of quantitative parameters of the vessel that significantly affect the draft of the vessel; constructing an initial ship draft prediction model, and training the initial ship draft prediction model based on a plurality of remarkable quantitative parameters in each historical ship lockage data subset and ship draft to obtain a target ship draft prediction model; and determining the predicted draft of the ship to be predicted based on the target ship draft prediction model. The method improves the prediction precision and efficiency of the ship draft, and provides guidance for overwater safety management and risk control strategy formulation.
Description
Technical Field
The invention relates to the technical field of ship navigation, in particular to a ship draft prediction method, a ship draft prediction system, electronic equipment and a readable storage medium.
Background
The ship draft detection and prediction are important research subjects in the field of waterway transportation, and ship safety navigation guarantee and ship lock safety are concerned.
At present, the draught detection of ships is mainly based on two methods of manual observation and automatic detection. The manual observation is realized by reading the scale value of the water gauge on the ship body through visual observation, is not only easily influenced by weather, has low efficiency, but also can not overcome the phenomenon that the water gauge and the waterline are intentionally modified. The automatic detection mainly comprises the realization of automatic draft detection based on a pressure or electronic sensor arranged on the outer side of a ship body, the method is difficult to complete the ship-leaving detection task, and the sensor is easy to damage in the severe navigation environment. The draft detection technology based on the image processing technology has a poor measuring effect in foggy days and under the condition of poor visibility, and the conversion precision from the camera coordinate to the space coordinate also influences the measuring result. The laser monitoring technology is influenced by transmission attenuation in water, and the transmission distance is closely related to the water quality, so that a range blind area exists, and the precision cannot be guaranteed. The monitoring mode based on multi-beam upward scanning has the problems that severe interference caused by navigation environments (such as stormy waves and currents) easily exists, continuous power supply of equipment cannot be guaranteed, and the accuracy and the robustness cannot be guaranteed as a result.
Therefore, it is urgently needed to provide a ship draft prediction method, a ship draft prediction system, an electronic device and a readable storage medium, so that the precision and the acquisition efficiency of the ship draft are improved.
Disclosure of Invention
In view of the above, it is necessary to provide a method, a system, an electronic device and a readable storage medium for predicting draught of a ship, so as to solve the technical problems of low accuracy and low acquisition efficiency of the draught of the ship in the prior art.
In one aspect, the invention provides a ship draft prediction method, which comprises the following steps:
acquiring a historical ship lockage data set, wherein the historical ship lockage data set comprises a plurality of ship qualitative parameters;
dividing the historical ship lockage data set into a plurality of historical ship lockage data subsets based on the plurality of ship qualitative parameters, wherein each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
determining a plurality of significant quantitative parameters of the plurality of quantitative parameters of the vessel that significantly affect the draft of the vessel in each of the subsets of historical vessel lockage data;
constructing an initial ship draft prediction model, and training the initial ship draft prediction model based on the plurality of significant quantitative parameters and the ship draft in each historical ship lockage data subset to obtain a target ship draft prediction model;
and determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
In some possible implementations, the plurality of vessel qualitative parameters includes a vessel type, a vessel cargo type, a lockline, a lockspace position, and a locktime; the multiple ship quantitative parameters comprise total length, total width, model depth, full-load displacement, full-load draft, no-load displacement, maximum reference cargo capacity, width, length, power, maximum ship height, displacement, total cargo capacity, total tonnage, heavy tank quantity, flow level, maximum passing flow and implicit flow of the ship.
In some possible implementations, the determining a plurality of significant quantitative parameters of the plurality of quantitative parameters of the vessel that significantly affect the draft of the vessel in each of the subsets of historical vessel lockage data includes:
determining a correlation coefficient calculation model, and determining a plurality of correlation coefficients of the plurality of ship quantitative parameters and the ship draft in each historical ship lockage data subset based on the correlation coefficient calculation model;
carrying out significance check on the plurality of correlation coefficients to obtain a plurality of significance values;
and taking the ship quantitative parameter corresponding to the significant value larger than the preset significant value as the significant quantitative parameter.
In some possible implementations, the determining a correlation coefficient calculation model includes:
acquiring quantitative parameters of each ship and a histogram of the ship draft;
determining a hypothetical probability distribution model for each of the vessel quantitative parameters and the vessel draft based on the histogram plot;
the hypothesis probability distribution model is checked based on a preset checking model to obtain a checking result;
determining the correlation coefficient calculation model based on the inspection result.
In some possible implementations, after the obtaining the historical ship lockage data set, the method further includes:
acquiring a ship draft historical physical calculation model, and determining a plurality of model parameters in the ship draft historical physical calculation model;
and screening the plurality of ship quantitative parameters based on the plurality of model parameters.
In some possible implementations, after the obtaining the historical ship lockage data set, the method further includes:
acquiring parameter reference ranges of the quantitative parameters and the qualitative parameters of the ships;
judging whether the parameter values of the ship quantitative parameters and the ship qualitative parameters are within the parameter reference range;
and rejecting the ship quantitative parameters or the ship qualitative parameters with parameter values not within the parameter reference range.
In some possible implementations, after the determining the predicted draft of the ship to be predicted based on the target ship draft prediction model, the method further includes:
acquiring the actual draft of the ship to be predicted, and judging whether the difference value between the actual draft and the predicted draft is smaller than a preset difference value or not;
if the difference is greater than or equal to the preset difference, retraining the initial ship draft prediction model based on the plurality of significant quantitative parameters and the ship draft in each historical ship lockage data subset;
and if the difference is smaller than the preset difference, the predicted draft is the reliable draft.
In another aspect, the present invention provides a ship draft prediction system, including:
the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring a historical ship lockage data set which comprises a plurality of ship qualitative parameters;
the data dividing unit is used for dividing the historical ship lockage data set into a plurality of historical ship lockage data subsets based on the plurality of ship qualitative parameters, and each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
the ship quantitative parameter screening unit is used for determining a plurality of significant quantitative parameters which significantly influence ship draught in the plurality of ship quantitative parameters in each historical ship lockage data subset;
the ship draft prediction model training unit is used for constructing an initial ship draft prediction model, training the initial ship draft prediction model based on the plurality of significant quantitative parameters in each historical ship lockage data subset and the ship draft, and obtaining a target ship draft prediction model;
and the draft prediction unit is used for determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
In another aspect, the present invention also provides an electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps of the ship draught prediction method in any one of the possible implementation manners.
In another aspect, the present invention further provides a computer-readable storage medium for storing a computer-readable program or instructions, which when executed by a processor can implement the steps in the ship draft prediction method described in any one of the above possible implementation manners.
The beneficial effects of adopting the embodiment are as follows: according to the ship draft prediction method provided by the invention, a historical ship lockage data set is divided into a plurality of historical ship lockage data subsets based on a ship qualitative parameter, and an initial ship draft prediction model is trained based on a plurality of significant quantitative parameters which significantly influence ship draft in each historical ship lockage data subset and the ship draft to obtain a target ship draft prediction model. Furthermore, when the draft of the ship to be predicted is predicted, the draft can be obtained only according to the trained target ship draft prediction model, detection is not needed through manpower or other draft detection equipment, the acquisition efficiency of the draft of the ship is improved, and meanwhile, the manpower and material resource investment for surveying the draft of the ship is reduced. The method can accurately predict the draught of the ship, can be used for monitoring, managing and controlling and early warning the ship lockage risk, and provides guidance for overwater safety management and risk control strategy formulation.
Furthermore, the initial ship draft prediction model is trained by the determined plurality of significant quantitative parameters instead of training the initial ship draft prediction model by all the ship quantitative parameters, so that the calculated amount can be reduced, and the draft acquisition efficiency can be further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an embodiment of a ship draft prediction method provided by the present invention;
FIG. 2 is a schematic flow chart of another embodiment of S103 of FIG. 1 according to the present invention;
FIG. 3 is a flowchart illustrating an embodiment of S201 in FIG. 2 according to the present invention;
FIG. 4 is a schematic flow chart illustrating screening of a plurality of ship quantitative parameters according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of another embodiment of the present invention for screening a plurality of quantitative parameters of a ship;
FIG. 6 is a schematic structural diagram of an embodiment of the present invention for verifying a predicted draft;
FIG. 7 is a schematic structural diagram of a ship draft prediction system according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an embodiment of an electronic device provided in the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It should be apparent that the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the schematic drawings are not necessarily to scale. The flowcharts used in this disclosure illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the direction of this summary, may add one or more other operations to, or remove one or more operations from, the flowchart. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor systems and/or microcontroller systems.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention provides a ship draught prediction method, a ship draught prediction system, electronic equipment and a readable storage medium, which are respectively described below.
Fig. 1 is a schematic flow chart of an embodiment of a ship draft prediction method provided by the present invention, and as shown in fig. 1, the ship draft prediction method includes:
s101, acquiring a historical ship lockage data set, wherein the historical ship lockage data set comprises a plurality of ship qualitative parameters;
s102, dividing a historical ship lockage data set into a plurality of historical ship lockage data subsets based on a plurality of ship qualitative parameters, wherein each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
s103, determining a plurality of remarkable quantitative parameters which obviously influence ship draught in a plurality of ship quantitative parameters in each historical ship lockage data subset;
s104, constructing an initial ship draft prediction model, training the initial ship draft prediction model based on a plurality of significant quantitative parameters and ship drafts in each historical ship lockage data subset, and obtaining a target ship draft prediction model;
and S105, determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
Compared with the prior art, the ship draft prediction method provided by the embodiment of the invention divides the historical ship lockage data set into a plurality of historical ship lockage data subsets based on the ship qualitative parameters, trains the initial ship draft prediction model based on a plurality of significant quantitative parameters which significantly affect the ship draft in each historical ship lockage data subset and the ship draft, obtains the target ship draft prediction model, can comprehensively consider the influence of the quantitative parameters and the qualitative parameters on the draft when predicting the ship draft, enables the predicted ship draft to be more fit with the reality, and improves the accuracy and precision of the predicted draft. Furthermore, when the draft of the ship to be predicted is predicted, the draft can be obtained only according to the trained target ship draft prediction model, detection is not needed through manpower or other draft detection equipment, the ship draft obtaining efficiency is improved, and meanwhile, the manpower and material resource investment for surveying the ship draft is reduced. The embodiment of the invention can accurately predict the ship draft, can be used for monitoring, managing and controlling and early warning the ship lockage risk, and provides guidance for overwater safety management and risk control strategy formulation.
Furthermore, the initial ship draft prediction model is trained through the determined plurality of remarkable quantitative parameters instead of training the initial ship draft prediction model by using all ship quantitative parameters, so that the calculated amount can be reduced, and the draft acquisition efficiency is further improved.
In step S101, the historical ship lockage data set may be acquired in a manner including, but not limited to: obtained from a storage medium storing a historical ship lockage data set.
It should be understood that: the model structures of the initial ship draught prediction model and the target ship draught prediction model in step S104 include, but are not limited to, a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a Convolutional network (CNN), a Deep Generative Model (DGM), a Generative Adaptive Network (GAN), a Long/short term memory network (Long/short term memory, LSTM), a Support Vector Machine (SVM), a Deep cross model (Deep cross), and the like.
It should be noted that: step S105 specifically includes: the method comprises the steps of obtaining ship real-time parameters of a ship to be predicted, wherein the ship real-time parameters comprise real-time qualitative parameters and real-time quantitative parameters, and inputting the real-time qualitative parameters and the real-time quantitative parameters into a target ship draft prediction model to obtain the predicted draft of the ship to be predicted.
In an embodiment of the invention, the plurality of ship qualitative parameters comprise ship type, ship cargo type, lockage route, lockage spatial position and lockage time; the plurality of vessel quantitative parameters include vessel overall length, overall width, profile depth, full load displacement, full load draft, empty displacement, maximum reference cargo capacity, width, length, power, maximum vessel height, displacement, total cargo capacity, total tonnage, number of heavy tanks, flow rating, maximum allowable flow, and implicit flow. .
It should be noted that: the qualitative ship parameters and the quantitative ship parameters may also include other parameters besides the above parameters according to different practical application scenarios, which are not described in detail herein.
Specifically, the types of ships include cargo ships, passenger ships, tugboats, multipurpose ships, and the like. The ship cargo comprises a chemical ship, a container ship, a bulk cargo ship, a commodity vehicle rolling ship, a tourist passenger ship, a general dry cargo ship, an oil tanker, a self-unloading sand ship and the like. The gate passing routes comprise an ascending route and a descending route, for example: taking the heading of the three gorges gate as an example, the heading comprises an ascending route and a descending route of the three gorges gate. The spatial position of the passing gate represents the route at different spatial positions.
The total length of the ship refers to the sum of the width of the ship and the width of the leaning handle, and the total width of the ship refers to the sum of the width of the ship and the width of the leaning handle.
In some embodiments of the present invention, as shown in fig. 2, step S103 comprises:
s201, determining a correlation coefficient calculation model, and determining a plurality of correlation coefficients of a plurality of ship quantitative parameters and ship draft in each historical ship lockage data subset based on the correlation coefficient calculation model;
s202, carrying out significance check on the plurality of correlation coefficients to obtain a plurality of significance values;
and S203, taking the ship quantitative parameter with the significance value larger than the preset significance value as the significant quantitative parameter.
It should be noted that: the Correlation Coefficient calculation model may be any one of a Pearson Correlation Coefficient (Pearson Correlation Coefficient) model, a Kendall (Kendall) Correlation Coefficient model, or a Spearman Correlation Coefficient model.
In the embodiment of the present invention, the correlation coefficient model is a Spearman correlation coefficient model, and if the qualitative ship parameter is not considered, the correlation coefficients of the ship draft and various quantitative ship parameters are shown in table 1:
TABLE 1 correlation coefficient of ship draft and various ship quantitative parameters
As can be seen from table 1: the correlation coefficients of the quantitative parameters of the ships and the ship draft are different, and after the significance verification, the quantitative parameters of other ships except for the quantitative parameters of the heavy boxes, the flow levels, the maximum accessible flow and the hidden flow in the table 1 are the significant ship quantitative parameters.
When the qualitative parameters of the ship are the lockage spatial position and the lockage air route, taking the lockage spatial position including the three gorges air route and the three gorges gate air route as an example, and taking the lockage air route including the three gorges north line, the three gorges south line, the three gorges gate down line and the three gorges gate up line as an example, the correlation coefficients of the ship draft and each lockage air route and the lockage spatial position are shown in table 2:
TABLE 2 correlation coefficient of ship draft and each lockage route
As can be seen from Table 2: when the lockage air route and the lockage space position are different, the correlation coefficient of each ship quantitative parameter and the ship draft is also different, the embodiment of the invention considers the characteristic difference of the ship quantitative parameters on the space (the lockage course and the lockage space position), and improves the reliability of the determined target ship draft prediction model, thereby improving the accuracy and precision of the draft prediction.
In some embodiments of the present invention, the gate-passing time may be divided into a first quarter, a second quarter, a third quarter, and a fourth quarter, which may also be divided into a flood period and a dry season period, and the specific division manner may be determined according to the actual application scenario.
When the qualitative parameter of the ship is the lockage time, the correlation coefficient of the ship draft and the lockage time is shown in table 3:
TABLE 3 correlation coefficient of draft and lockage of ship
As can be seen from table 3: when the lockage time is different, the correlation coefficients of the ship quantitative parameters and the ship draft are also different, the embodiment of the invention considers the characteristic diversity of the ship quantitative parameters in time (lockage time), and further improves the reliability of the determined target ship draft prediction model, thereby further improving the accuracy and precision of the draft prediction.
Similarly, when the ship type and the ship cargo type are different, the correlation coefficients of the quantitative parameters of each ship and the ship draft are also different, and the specific correlation coefficients are not described herein again. According to the embodiment of the invention, the ship quantitative parameters and the ship draft correlation coefficients when the ship qualitative parameters are different are determined, so that the remarkable quantitative parameters under different ship qualitative parameters can be screened out, and the reliability and the accuracy of the determined remarkable quantitative parameters are improved.
Since the correlation coefficient calculation model may be any one of a pearson correlation coefficient model, a kender correlation coefficient model, or a spearman correlation coefficient model, different correlation coefficient calculation models also have an influence on the accuracy of the prediction of the ship draft, and in order to improve the rationality of the determined correlation coefficient calculation model, in some embodiments of the present invention, as shown in fig. 3, the determining of the correlation coefficient calculation model in step S201 includes:
s301, acquiring quantitative parameters of each ship and a histogram of ship draft;
s302, determining a hypothesis probability distribution model of quantitative parameters and ship draft of each ship based on the histogram;
s303, checking the hypothesis probability distribution model based on a preset checking model to obtain a checking result;
and S304, determining a correlation coefficient calculation model based on the inspection result.
The embodiment of the invention firstly determines the hypothesis probability distribution model of each ship quantitative parameter based on the histogram, then tests the hypothesis probability distribution model based on the preset test model, and determines the correlation coefficient calculation model according to the test result, so that the fitness of the correlation coefficient calculation model and each ship quantitative parameter can be improved, namely: the reliability and the rationality of the relevant calculation model are improved, and therefore the prediction precision of the ship draft can be improved.
In the specific embodiment of the invention, the assumed probability distribution model of each ship quantitative parameter and ship draft is as follows:
in the formula,
taking the value of the draught of the ship as
The probability of (d);
draft of a ship
Taking values;
the total number of values taken for the draught of the ship.
And the probability satisfies the condition
Thus, the probability distribution function for the ship draft is:
in the same way, the probability distribution of the quantitative parameters of each ship can be obtained.
The test model preset in step S303 may be any one of a variance test model, a chi-square fitting test model, and a (Kolmogorov-Smirnov, KS) test model. In an embodiment of the present invention, the predetermined test model is a chi-square fitting test model.
Specifically, the chi-square fit test model is:
if chi-square value
The larger the size of the hole is,
and
the greater the degree of deviation; conversely, the smaller the deviation; if it is
And
when the quantitative parameters are completely equal, the quantitative parameters of the ship are completely consistent
And (4) distribution.
Through hypothesis testing, the probability distribution of the ship draft basically does not conform to normal distribution and is not necessarily linearly related, so that a Spearman correlation coefficient calculation model is adopted to calculate the correlation coefficient of the ship draft and each ship quantitative parameter.
In a specific embodiment of the invention, taking the ship draft and the ship length as examples, the Spearman correlation coefficient calculation model is as follows:
in the formula,
for the calculation of the resulting pearson correlation coefficient,
the number of samples of a certain vessel quantitative parameter,
is a first
The draught of the ship with various values,
is a first
The length of the ship which takes the value,
is the average number of samples of the ship's draft,
is the average number of samples of the length of the vessel.
Wherein,
，
in order to realize positive correlation, the first phase is the first phase,
is a negative correlation of the two signals,
in order to be in a completely positive correlation,
is completely negative correlation.
When in use
In the meantime, the hypothesis that the ship draft is irrelevant to the ship length is rejected, and the hypothesis that the ship draft is irrelevant to the ship length cannot be rejected by a person who does not reject the hypothesis. Wherein,
is a preset value, which is a value obtained by looking up the Spearman rank correlation coefficient test critical value table according to the number of sample observations, the hypothesis (single-sided or double-sided) and the given significance level.
Since the historical ship lockage data set includes a plurality of types of ship quantitative parameters, and some ship quantitative parameters are unrelated to ship draft, if the unrelated ship quantitative parameters are eliminated through significance analysis, the calculated amount is large, so that the efficiency of ship draft prediction is low, and in order to further improve the efficiency of ship draft prediction, in some embodiments of the present invention, as shown in fig. 4, after step S101, the method further includes:
s401, acquiring a ship draft historical physical calculation model, and determining a plurality of model parameters in the ship draft historical physical calculation model;
s402, screening a plurality of ship quantitative parameters based on the plurality of model parameters.
According to the embodiment of the invention, the plurality of ship quantitative parameters are screened through the plurality of model parameters in the ship draft historical physical calculation model, so that the efficiency of eliminating the ship quantitative parameters irrelevant to the ship draft can be improved, the calculation amount of the subsequent calculation correlation coefficient is reduced, and the prediction efficiency of the ship draft can be improved. And moreover, a plurality of ship quantitative parameters are screened based on the ship draft historical physical computation model, and the logical association between the reserved ship quantitative parameters and draft can be ensured, so that the fitness of the determined target draft prediction and the actual application scene can be further improved.
In an embodiment of the invention, the ship draft history physical calculation model can be a physical calculation formula of ship draft and water plane coefficients.
It should be noted that: in order to avoid mistakenly removing the ship quantitative parameters, the model parameters in step S401 include the original model parameters and the associated parameters associated with the original model parameters, and then step S401 specifically includes: the method comprises the steps of obtaining a ship draft historical physical calculation model, and determining original model parameters and associated parameters associated with the original model parameters in the ship draft historical physical calculation model. For example: the physical calculation formula of the water plane coefficient is the ratio of the water plane area to the rectangular area enclosed by the corresponding ship length and the corresponding model width, wherein the water plane area, the ship length and the model width are original model parameters, and the water plane area is related to the parameters such as total cargo capacity and total ton, and the total cargo capacity and the total ton are related parameters.
In order to avoid the technical problem that the trained target draft prediction model is inaccurate and thus the ship draft prediction is wrong when the data in the historical ship lockage data set is wrong, in some embodiments of the present invention, as shown in fig. 5, after step S101, the method further includes:
s501, acquiring a parameter reference range of each ship quantitative parameter and each ship qualitative parameter;
s502, judging whether the parameter values of the ship quantitative parameters and the ship qualitative parameters are within a parameter reference range;
s503, removing the ship quantitative parameters or the ship qualitative parameters of which the parameter values are not in the parameter reference range.
According to the embodiment of the invention, after the historical ship lockage data set is obtained, the parameter values of the ship quantitative parameters and the ship qualitative parameters are judged, and the parameters which are not in the parameter reference range are eliminated, so that the reliability of the ship quantitative parameters and the ship qualitative parameters for training can be ensured, the reliability of the trained target ship draft prediction model is further improved, and the prediction precision and the accuracy of the ship draft can be further improved.
It should also be understood that: the parameter reference range may be set or adjusted according to an actual application scenario or an empirical value, which is not described herein again.
In order to verify the reliability of the predicted draft obtained by the target ship draft prediction model, in some embodiments of the present invention, as shown in fig. 6, after step S105, the method further includes:
s601, acquiring the actual draft of the ship to be predicted, and judging whether the difference value between the actual draft and the predicted draft is smaller than a preset difference value or not;
s602, if the difference is larger than or equal to a preset difference, retraining the initial ship draft prediction model based on a plurality of significant quantitative parameters and ship drafts in each historical ship lockage data subset;
and S603, if the difference value is smaller than the preset difference value, predicting the draught to be reliable.
According to the embodiment of the invention, the reliability of the draft predicted by the target ship draft prediction model can be ensured by judging whether the difference value between the actual draft and the predicted draft is smaller than the preset difference value or not and retraining the initial ship draft prediction model when the difference value is larger than or equal to the preset difference value.
It should be understood that: the preset difference may be set or adjusted according to an actual application scenario or an empirical value, which is not described herein again.
In order to better implement the ship draft prediction method in the embodiment of the present invention, on the basis of the ship draft prediction method, as shown in fig. 7, correspondingly, an embodiment of the present invention further provides a ship draft prediction system, where the ship draft prediction system 700 includes:
a data acquisition unit 701, configured to acquire a historical ship lockage data set, where the historical ship lockage data set includes a plurality of ship qualitative parameters;
the data dividing unit 702 is configured to divide the historical ship lockage data set into a plurality of historical ship lockage data subsets based on a plurality of ship qualitative parameters, where each historical ship lockage data subset includes a plurality of ship quantitative parameters and ship draft;
the ship quantitative parameter screening unit 703 is configured to determine a plurality of significant quantitative parameters that significantly affect ship draft, among the plurality of ship quantitative parameters in each historical ship lockage data subset;
the ship draft prediction model training unit 704 is used for constructing an initial ship draft prediction model, and training the initial ship draft prediction model based on a plurality of significant quantitative parameters in each historical ship lockage data subset and ship draft to obtain a target ship draft prediction model;
a draft prediction unit 705 for determining a predicted draft of the vessel to be predicted based on the target vessel draft prediction model.
The ship draft prediction system 700 provided by the embodiment of the invention fully considers ship lockage space-time information, deeply researches qualitative and quantitative influence factors of ship draft, obtains ship draft space-time difference characteristics and influence and rule characteristics of different factors on ship draft, combines a current mainstream machine learning method, realizes high-precision prediction of ship draft, makes up the defect that the current manual detection and passive monitoring cannot effectively work in severe environment, can support draft prediction in ship lockage or navigation, and has great potential in aspects of ship navigation guarantee, ship safety supervision and traffic supervision.
The ship draft prediction system 700 provided in the above embodiment may implement the technical solutions described in the above embodiments of the ship draft prediction method, and the specific implementation principles of the above modules or units may refer to the corresponding contents in the above embodiments of the ship draft prediction method, which are not described herein again.
As shown in fig. 8, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802, and a display 803. Fig. 8 shows only some of the components of the electronic device 800, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The memory 802 may be an internal storage unit of the electronic device 800 in some embodiments, such as a hard disk or memory of the electronic device 800. The memory 802 may also be an external storage device of the electronic device 800 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc., provided on the electronic device 800.
Further, the memory 802 may also include both internal storage units and external storage devices of the electronic device 800. The memory 802 is used for storing application software and various data installed in the electronic device 800.
The display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch panel, or the like in some embodiments. The display 803 is used to display information at the electronic device 800 as well as to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.
In some embodiments of the present invention, when the processor 801 executes a vessel draft prediction program in the memory 802, the following steps may be implemented:
acquiring a historical ship lockage data set, wherein the historical ship lockage data set comprises a plurality of ship qualitative parameters;
dividing a historical ship lockage data set into a plurality of historical ship lockage data subsets based on a plurality of ship qualitative parameters, wherein each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
determining a plurality of significant quantitative parameters which significantly influence the ship draught in a plurality of ship quantitative parameters in each historical ship lockage data subset;
constructing an initial ship draft prediction model, and training the initial ship draft prediction model based on a plurality of remarkable quantitative parameters in each historical ship lockage data subset and ship draft to obtain a target ship draft prediction model;
and determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
It should be understood that: the processor 801, when executing the ship draft prediction program in the memory 802, may perform other functions in addition to the above functions, which may be specifically referred to the description of the corresponding method embodiments above.
Further, the type of the electronic device 800 is not particularly limited in the embodiment of the present invention, and the electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a Personal Digital Assistant (PDA), a wearable device, and a laptop computer (laptop). Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices that carry an IOS, android, microsoft, or other operating system. The portable electronic device may also be other portable electronic devices such as laptop computers (laptop) with touch sensitive surfaces (e.g., touch panels) and the like. It should also be understood that in other embodiments of the present invention, the electronic device 800 may not be a portable electronic device, but may be a desktop computer having a touch-sensitive surface (e.g., a touch pad).
Accordingly, the present application further provides a computer-readable storage medium, which is used for storing a computer-readable program or instruction, and when the program or instruction is executed by a processor, the steps or functions of the ship draft prediction method provided by the above method embodiments can be implemented.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by instructing relevant hardware (such as a processor, a controller, etc.) by a computer program, and the computer program may be stored in a computer readable storage medium. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The ship draft prediction method, the ship draft prediction system, the electronic device and the readable storage medium provided by the invention are described in detail, specific examples are applied in the description to explain the principle and the implementation of the invention, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for those skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as limiting the present invention.
Claims (10)
1. A ship draft prediction method is characterized by comprising the following steps:
acquiring a historical ship lockage data set, wherein the historical ship lockage data set comprises a plurality of ship qualitative parameters;
dividing the historical ship lockage data set into a plurality of historical ship lockage data subsets based on the plurality of ship qualitative parameters, wherein each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
determining a plurality of significant quantitative parameters of the plurality of quantitative parameters of the vessel that significantly affect the draft of the vessel in each of the subsets of historical vessel lockage data;
constructing an initial ship draft prediction model, and training the initial ship draft prediction model based on the plurality of significant quantitative parameters and the ship draft in each historical ship lockage data subset to obtain a target ship draft prediction model;
and determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
2. The method of claim 1, wherein the plurality of vessel qualitative parameters comprise vessel type, vessel cargo type, lockage course, lockage spatial location, and lockage time; the plurality of vessel quantitative parameters include vessel overall length, overall width, profile depth, full load displacement, full load draft, empty displacement, maximum reference cargo capacity, width, length, power, maximum ship height, displacement, total cargo capacity, total tonnage, number of heavy tanks, flow rate rating, maximum allowable flow rate, and implicit flow rate.
3. The method of predicting ship draft according to claim 1, wherein said determining a plurality of significant quantitative parameters of said plurality of ship quantitative parameters in each of said historical ship lockage data subsets that significantly affect ship draft comprises:
determining a correlation coefficient calculation model, and determining a plurality of correlation coefficients of the plurality of ship quantitative parameters and the ship draft in each historical ship lockage data subset based on the correlation coefficient calculation model;
carrying out significance check on the plurality of correlation coefficients to obtain a plurality of significance values;
and taking the ship quantitative parameter corresponding to the significant value larger than the preset significant value as the significant quantitative parameter.
4. The method of predicting draft of a ship according to claim 3, wherein said determining a correlation coefficient calculation model comprises:
acquiring a histogram of each ship quantitative parameter and ship draft;
determining a hypothetical probability distribution model for each of the vessel quantitative parameters and the vessel draft based on the histogram map;
the hypothesis probability distribution model is tested based on a preset test model, and a test result is obtained;
determining the correlation coefficient calculation model based on the inspection result.
5. The method of predicting draft of a ship according to claim 1, further comprising, after said obtaining the historical ship lockage data set:
acquiring a ship draft historical physical calculation model, and determining a plurality of model parameters in the ship draft historical physical calculation model;
and screening the plurality of ship quantitative parameters based on the plurality of model parameters.
6. The method of predicting draft of a ship according to claim 1, further comprising, after said obtaining the historical ship lockage data set:
acquiring parameter reference ranges of the quantitative parameters and the qualitative parameters of the ships;
judging whether the parameter values of the ship quantitative parameters and the ship qualitative parameters are within the parameter reference range;
and rejecting the ship quantitative parameters or the ship qualitative parameters with parameter values not within the parameter reference range.
7. The ship draft prediction method according to claim 1, further comprising, after said determining a predicted draft of a ship to be predicted based on said target ship draft prediction model:
acquiring the actual draft of the ship to be predicted, and judging whether the difference value between the actual draft and the predicted draft is smaller than a preset difference value or not;
if the difference is greater than or equal to the preset difference, retraining the initial ship draft prediction model based on the plurality of significant quantitative parameters and the ship draft in each historical ship lockage data subset;
and if the difference value is smaller than the preset difference value, the predicted draft is the reliable draft.
8. A ship draft prediction system, comprising:
the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring a historical ship lockage data set which comprises a plurality of ship qualitative parameters;
the data dividing unit is used for dividing the historical ship lockage data set into a plurality of historical ship lockage data subsets based on the plurality of ship qualitative parameters, and each historical ship lockage data subset comprises a plurality of ship quantitative parameters and ship draft;
the ship quantitative parameter screening unit is used for determining a plurality of significant quantitative parameters which significantly influence ship draught in the plurality of ship quantitative parameters in each historical ship lockage data subset;
the ship draft prediction model training unit is used for constructing an initial ship draft prediction model, training the initial ship draft prediction model based on the plurality of significant quantitative parameters in each historical ship lockage data subset and the ship draft, and obtaining a target ship draft prediction model;
and the draft prediction unit is used for determining the predicted draft of the ship to be predicted based on the target ship draft prediction model.
9. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled with the memory, is configured to execute the program stored in the memory to implement the steps in the ship draft prediction method according to any one of the preceding claims 1 to 7.
10. A computer-readable storage medium storing a computer-readable program or instructions, which when executed by a processor, is capable of implementing the steps in the ship draft prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211715318.9A CN115675780B (en) | 2022-12-30 | 2022-12-30 | Ship draught prediction method and system, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211715318.9A CN115675780B (en) | 2022-12-30 | 2022-12-30 | Ship draught prediction method and system, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115675780A CN115675780A (en) | 2023-02-03 |
| CN115675780B true CN115675780B (en) | 2023-03-14 |
Family
ID=85057043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211715318.9A Active CN115675780B (en) | 2022-12-30 | 2022-12-30 | Ship draught prediction method and system, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115675780B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599995B (en) * | 2016-12-09 | 2019-04-30 | 上海海事大学 | A method of according to maritime meteorology information prediction ship's navigation meteorological factor |
| CN107238837B (en) * | 2017-05-23 | 2020-04-10 | 浙江海洋大学 | Ship draught detection method |
| AU2018440246A1 (en) * | 2018-09-06 | 2021-03-18 | Nippon Yusen Kabushiki Kaisha | Draft estimation system, draft estimation apparatus, information transmission apparatus, and loading/unloading simulation apparatus |
| CN111959708B (en) * | 2020-04-29 | 2022-07-29 | 中船第九设计研究院工程有限公司 | Ship draft simulation system |
| CN114782905B (en) * | 2022-06-17 | 2022-09-27 | 长江信达软件技术（武汉）有限责任公司 | Ship draft detection method based on video monitoring |
-
2022
- 2022-12-30 CN CN202211715318.9A patent/CN115675780B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 周祥明 ; 陈员义 ; 林苑 ; 程帅鹏 ; .基于机器学习的船舶吃水动态检测系统设计.2019,(10),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115675780A (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6759673B2 (en) | Collision risk calculation program, collision risk calculation method and collision risk calculation device | |
| CN111046491B (en) | Method and device for estimating fuel consumption of diesel engine of large ship | |
| CN110263713B (en) | Lane line detection method, lane line detection device, electronic device, and storage medium | |
| KR100966289B1 (en) | Target detection method applied in marine radar system, and record carrier, arpa board and radar using the same | |
| CN113536544A (en) | Ship probability conflict detection method based on minimum safe distance model | |
| CN113807686A (en) | Multi-target offshore emergency resource allocation method and device | |
| Parunov et al. | Uncertainties in modelling the low-frequency wave-induced global loads in ships | |
| CN112441196A (en) | Processing method, system and storage medium of ship navigation risk assessment information | |
| CN110555352A (en) | interest point identification method, device, server and storage medium | |
| Karolius et al. | Risk-based, sensor-fused detection of flooding casualties for emergency response | |
| CN115675780B (en) | Ship draught prediction method and system, electronic equipment and readable storage medium | |
| KR102607165B1 (en) | Ship management device, ship, ship management system, and ship management method | |
| Karolius et al. | Tearing down the wall–The inclining experiment | |
| US20230314144A1 (en) | System and method for estimating drift path of marine floating body | |
| Alyoubi et al. | Connotation of fuzzy logic system in Underwater communication systems for navy applications with data indulgence route | |
| Paudel et al. | Study on utilization of Inland deep-draft waterway based on ship trajectories: Applied to Sabine-Neches Waterway | |
| Sauder et al. | Estimation of top tensions in mooring lines by sensor fusion | |
| CN118314771B (en) | Ship collision risk assessment method and system | |
| Smolarek et al. | Risk modelling for passages in approach channel | |
| Yan et al. | Computational Analysis for Estimation of Mooring Force Acting on Various Ships in Busan New Port | |
| Kirilenko et al. | Automatic Recognition of Draft Marks on a Ship’s Board Using Deep Learning System | |
| Penttilä et al. | Use of Level Sensors in Breach Estimation for a Damaged Ship | |
| CN109138018A (en) | Control method of grabbing bucket and system, computer equipment, computer storage medium | |
| Pereira et al. | A 3-D Lightweight Convolutional Neural Network for Detecting Docking Structures in Cluttered Environments | |
| Ryu et al. | Reference load for a conventional 138K CBM LNG carrier in a comparative approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |