CN111738500A - Navigation time prediction method and device based on deep learning - Google Patents
Navigation time prediction method and device based on deep learning Download PDFInfo
- Publication number
- CN111738500A CN111738500A CN202010530842.3A CN202010530842A CN111738500A CN 111738500 A CN111738500 A CN 111738500A CN 202010530842 A CN202010530842 A CN 202010530842A CN 111738500 A CN111738500 A CN 111738500A
- Authority
- CN
- China
- Prior art keywords
- navigation
- time
- ship
- data
- voyage
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013135 deep learning Methods 0.000 title claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 230000000306 recurrent effect Effects 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a navigation time prediction method based on deep learning, which comprises the following steps: acquiring AIS data; processing the acquired AIS data to obtain the navigation time data of different navigation sections and different time periods; constructing a navigation time prediction model, and inputting the navigation time data into the constructed navigation time prediction model for training; and combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value. The technical scheme of the invention can accurately predict the navigation time, so that the ship can know the estimated time passing through a certain navigation section in advance and select the optimal path in advance, thereby improving the traffic efficiency and economic benefit of the navigation and laying a foundation for intelligent navigation of the ship.
Description
Technical Field
The invention relates to the technical field of voyage time prediction, in particular to a voyage time prediction method and device based on deep learning.
Background
Inland river shipping is taken as an important component of a modern comprehensive transportation system in China, has the outstanding advantages of large transportation capacity, light pollution, low cost, low energy consumption and the like, plays an important role in promoting the rapid coordinated development of regional economy, and is counted as follows: in China, five thousand or more river tracks have the total length of 42 kilometers, the total length of inland river channels is about 13.51 kilometers, wherein the high-level channels account for 46.56 percent, the total length is about 6.29 kilometers, inland river ports are as many as 1300, the number of productive berths is about 2.6 kilometers, and the number of transport ships is as high as 20 and more than ten thousand.
With the continuous increase of inland river traffic, the congestion situation is increasingly severe. Traffic management departments also explore traffic management methods all the time to optimize travel experience. The navigation time is one of inland river traffic information, the function is quite important, accurate navigation time prediction can help a ship to know the estimated time of passing a certain navigation section in advance, and the optimal route is selected in advance, so that the navigation efficiency and the economic benefit are improved.
However, the current method of estimating the voyage time for inland rivers includes:
1) estimating according to experience;
2) and according to the distance of the ship route and the initial speed, dividing the distance and the initial speed to obtain the estimated time of the ship navigation.
The method for estimating the navigation time of the inland river does not fully consider the periodicity and regularity of the time sequence of the navigation time and the spatial correlation between the channels, and the navigation time of the ship cannot be accurately estimated.
Disclosure of Invention
In light of the above-mentioned technical problems, a method for predicting a flight time based on deep learning is provided. The method mainly utilizes a navigation time prediction model and fuses channel static information (channel length, water depth, historical average navigation time and the like) to improve the prediction precision of the model.
The technical means adopted by the invention are as follows:
a method for predicting voyage time based on deep learning comprises the following steps:
acquiring AIS data;
processing the acquired AIS data to obtain the navigation time data of different navigation sections and different time periods;
constructing a navigation time prediction model, and inputting the navigation time data into the constructed navigation time prediction model for training;
and combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value.
Further, the processing the received AIS data to obtain the voyage time data of different voyage segments and different time segments includes:
cutting and segmenting the channel according to channel characteristics, wherein ships with similar types in each channel have similar navigation behaviors and navigation time;
calculating the average navigation speed of the ship in each navigation section by using the ship navigation speed information in the AIS data, and further calculating the average navigation time required for the ship to pass through the whole navigation section according to the average speed;
and according to the traffic flow characteristics, setting the time interval to be n hours, and counting the navigation time of each navigation segment in different time intervals.
Further, the AIS data comprises ship static data, ship dynamic data, ship voyage data and voyage safety information;
the ship static data comprises a ship name, a call sign, a marine mobile service identification code (MMSI), an International Maritime Organization (IMO) number, a ship length, a ship width and a ship type;
the dynamic data of the ship comprises ship position data, ground speed/course and ship fore-direction information;
the ship voyage data comprises ship state, draft, destination and ETA information;
the navigation safety information comprises navigation warning and weather report information.
Further, the average voyage time required for the ship to pass through the whole voyage section is calculated according to the average speed, and the calculation formula is as follows:
wherein T is the average voyage time, ViThe speed of the ith ship is defined, n is the number of ships in the leg, and l is the mileage of the leg.
Further, the constructed time-of-flight prediction model comprises a convolutional neural network for capturing spatial correlation between adjacent flight segments and a cyclic neural network for capturing temporal correlation.
Further, the inputting the flight time data into the constructed flight time prediction model for training includes:
setting L1, L2 and L3 to represent the navigation time sequence of the upstream flight segment, the navigation time sequence of the target flight segment and the navigation time sequence of the downstream flight segment respectively;
splicing the navigation time sequences of the three navigation sections into a characteristic by using Concat operation on the L1, the L2 and the L3, and recording the characteristic as L; l ═ Concat [ L1, L2, L3]
And extracting the spliced feature L by adopting a one-dimensional convolution neural network, wherein the extracted feature is marked as F, and F is F (∑) according to the one-dimensional convolution operationi∈MHi*Wi+ b), where H is the time-of-flight sequence, W is the weight of the convolution translation operator, b is the bias executionF (·) is an activation function;
inputting the extracted feature F into the recurrent neural network to obtain the feature extracted by the navigation time prediction model; the cyclic neural network has 20 inputs which are respectively used for predicting the flight time characteristics of the first 20 periods, and each flight time characteristic is obtained by comprehensively extracting three flight periods through the one-dimensional convolution neural network according to the spatiality;
fusing the spatial characteristics of the channel with the characteristics extracted by the navigation time prediction model, wherein the spatial characteristics of the channel participating in prediction comprise three elements of the length of the navigation section, the navigation width and the water depth;
and then fusing the 1 channel historical similarity characteristic, the spatial characteristics of the three channels and the characteristics extracted by the navigation time prediction model, inputting the fused characteristics into a full connection layer, and finally outputting the navigation time of the specified navigation section in the next time period.
Further, the convolutional neural network adopts a one-dimensional convolutional neural network; the recurrent neural network adopts a GRU structure.
Further, each of the voyage time sequences is composed of voyage time of the current time period and 20 time periods before the current time period.
The invention also provides a navigation time prediction device based on deep learning, which comprises the following components:
an acquisition unit for acquiring AIS data;
the calculation unit is used for processing the AIS data acquired by the acquisition unit to obtain the navigation time data of different navigation sections and different time periods;
the training unit is used for constructing a navigation time prediction model and inputting the navigation time data into the constructed navigation time prediction model for training;
and the generating unit is used for combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value.
A computer-readable storage medium having a set of computer instructions stored therein; the set of computer instructions, when executed by the processor, implement the method for deep learning based voyage time prediction described above.
Compared with the prior art, the invention has the following advantages:
1. the invention constructs a navigation time prediction model fusing various characteristic information by using a more advanced deep learning technology, and can obtain better prediction precision compared with other ship navigation time prediction methods.
2. The method for predicting the voyage time based on the deep learning can accurately predict the voyage time, so that the ship can know the estimated time passing through a certain voyage section in advance and select an optimal path in advance, the passing efficiency and the economic benefit of the voyage are improved, and a foundation is laid for intelligent navigation of the ship.
3. The navigation time prediction model can be deployed as a public service interface and combined with an airline planning technology, so that navigation time prediction service is provided for social public and crews through the mobile phone APP, and the navigation channel information service level is improved.
Based on the reason, the method can be widely popularized in the fields of flight time prediction and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of an AIS data structure according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a segment cutting according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a time-of-flight prediction model according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a recurrent neural network according to an embodiment of the present invention.
Fig. 6 is a navigation time relationship curve according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
At present, the method for estimating the navigation time of an inland river does not fully consider the periodicity and regularity of a time sequence of the navigation time and the spatial correlation between channels, and the navigation time of a ship cannot be accurately estimated.
The invention provides a navigation time prediction method based on deep learning, which specifically comprises the following steps: acquiring AIS data; processing the acquired AIS data to obtain the navigation time data of different navigation sections and different time periods; constructing a navigation time prediction model, and inputting the navigation time data into the constructed navigation time prediction model for training; and combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value. The method constructs a navigation time prediction model, fully considers the spatial correlation and the time periodicity of the navigation time in the channel, and simultaneously fuses channel characteristics and channel historical average time into the model to obtain better prediction precision.
The embodiments of the present invention will be described in detail with reference to the accompanying drawings.
A method for predicting voyage time based on deep learning is disclosed, as shown in FIG. 1, and comprises the following steps:
step 1: acquiring AIS data; as shown in fig. 2, the AIS data includes ship static data, ship dynamic data, ship voyage data, and voyage safety information;
the ship static data comprises a ship name, a call sign, a marine mobile service identification code (MMSI), an International Maritime Organization (IMO) number, a ship length, a ship width and a ship type;
the dynamic data of the ship comprises ship position data, ground speed/course and ship fore-direction information;
the ship voyage data comprises ship state, draft, destination and ETA information;
the navigation safety information comprises navigation warning and weather report information.
It can be seen that the AIS data does not have direct information about the voyage time, and therefore, when the AIS is used to analyze the voyage time of the ship, the processing and calculation are performed through the Marine Mobile Service Identification (MMSI), the ship longitude and latitude, the ship speed, the timestamp of the AIS data, and the like in the AIS data.
The voyage time is for a section of the ship from the starting point to the end point of the route, however, because the planned route is too long, the time for directly counting and estimating the whole route according to historical data will generate a large error. In order to improve the accuracy of the prediction of the navigation time, the scheme adopts a sectional prediction method to perform the statistical analysis of the navigation time in sections. Specifically, the method comprises the following steps:
step 2: processing the AIS data to obtain the navigation time data of different navigation sections and different time periods, comprising the following steps:
cutting and segmenting the channel according to channel characteristics (channel trend, channel water depth, channel width and the like), wherein ships with similar types in each channel have similar navigation behaviors and navigation time; as shown in fig. 3, a schematic diagram of the cutting of the legs is shown, each having its own number.
Calculating the average navigation speed of the ship in each navigation section by using the ship navigation speed information in the AIS data, and further calculating the average navigation time required for the ship to pass through the whole navigation section according to the average speed; calculating the average voyage time required for the ship to pass through the whole voyage section according to the average speed, wherein the calculation formula is as follows:
wherein T is the average voyage time, ViThe speed of the ith ship is defined, n is the number of ships in the leg, and l is the mileage of the leg.
According to the traffic flow characteristics, the average sailing speed of the ship is greatly different in different time periods in each navigation section. Therefore, in order to improve the statistical accuracy of the voyage time, the voyage time statistics in different time periods is further performed for each flight period, in this embodiment, 2 hours are used as a time interval, and the following table shows the statistical result of the voyage time in different time periods, which is finally obtained based on the AIS data statistics.
And step 3: constructing a navigation time prediction model, and inputting the navigation time data into the constructed navigation time prediction model for training; as shown in FIG. 4, the constructed time-of-flight prediction model includes a convolutional neural network for capturing spatial correlation between adjacent flight segments and a recurrent neural network for capturing temporal correlation. The convolution neural network adopts a one-dimensional convolution neural network; the recurrent neural network adopts a GRU structure.
Inputting the navigation time data into the constructed navigation time prediction model for training, wherein the training comprises the following steps:
l1, L2 and L3 in fig. 4 represent the voyage time series of the upstream leg, the target leg and the downstream leg, respectively; each voyage time sequence is composed of voyage time of the voyage segment in the current time segment and 20 time segments before the current time segment.
Splicing the navigation time sequences of the three navigation sections into a characteristic by using Concat operation on L1, L2 and L3, and recording the characteristic as L; l ═ Concat [ L1, L2, L3 ];
and extracting the spliced feature L by adopting a one-dimensional convolution neural network, wherein the extracted feature is marked as F, and F is F (∑) according to the one-dimensional convolution operationi∈MHi*Wi+ b), where H is the voyage time series, W is the weight of the convolution translation operator, b is the bias execution, and f (·) is the activation function; in the one-dimensional convolutional neural network, each convolution translation operator represents a system for extracting the characteristic of the navigation time sequence, and the weight parameters of the convolution translation operators are continuously adjusted in a reverse error propagation mode in the training process, so that the best space correlation characteristic among three navigation sections is finally learned.
Inputting the extracted feature F into the recurrent neural network to obtain the feature extracted by the navigation time prediction model; the cyclic neural network has 20 inputs which are respectively used for predicting the flight time characteristics of the first 20 periods, and each flight time characteristic is obtained by comprehensively extracting three flight periods through the one-dimensional convolution neural network according to the spatiality; when the invention predicts the navigation time, the invention adopts the recurrent neural network with the GRU structure, and the structure is shown in figure 5. It contains 1 GRU layer, input is 20, output 1, namely output this section future a period of time of voyage.
The spatial characteristics of the channel comprise the length, the width and the depth of water of the navigation section, which are related to the traffic capacity of the channel, so that the traffic speed of the ship is influenced to a great extent, and the navigation time of the ship passing through the navigation section is influenced. Therefore, in order to increase the comprehensiveness of the consideration factors of the prediction model and improve the prediction effect of the model, the spatial characteristics of the channel are further fused with the characteristics extracted by the navigation time prediction model, and the spatial characteristics of the channel participating in prediction comprise three elements, namely the length of the flight segment, the flight width and the water depth; in this example, the values are shown in the following table:
in addition, for a fixed time period of a flight segment in one day, the traffic behaviors occurring in the fixed time period have certain similarity, and the similarity is helpful for improving the prediction effect, so that 1 flight path historical similarity feature, the spatial features of three flight paths and the features extracted by the flight time prediction model are fused, input into a full connection layer together, and finally output the flight time of the specified flight segment in the next time period.
To evaluate how long historical data was taken to calculate historical correlation features, the voyage times for 12 time periods per day (2 hours each) were correlated with the average voyage time for the time period corresponding to the previous n days. Taking the navigation section No. 6 as an example, the navigation time of the navigation section No. 2018/5/7 in each time section is compared with the navigation time corresponding to each time section n days before the navigation section No. 6, and the result shows that the average value of the navigation section No. 7 days before the navigation section No. 6 is adopted has better similarity and the calculation consumption brought by the similarity is more reasonable. The table below shows specific corresponding values, while fig. 6 reflects their similarity. In fig. 6, the abscissa is the time of day for each time period, the ordinate is the time of flight, the blue curve is the time of flight for 2018/5/7 days for each time period, and the yellow curve is the average time of flight for the first seven days for each time period. As can be seen from the figure, the two curves have similar trends and have higher relevance.
In conclusion, the features extracted by the flight time prediction model (convolutional neural network + GRU recurrent neural network) are fused with 3 channel space features and 1 channel historical similarity feature, and are input into a full connection layer together, and finally, the flight time of the specified flight segment in the next time segment is output.
Corresponding to the method for predicting the voyage time based on the deep learning in the application, the application also provides a device for predicting the voyage time based on the deep learning, which comprises the following steps: the device comprises an acquisition unit, a calculation unit, a training unit and a generation unit; wherein:
an acquisition unit for acquiring AIS data;
the calculation unit is used for processing the AIS data acquired by the acquisition unit to obtain the navigation time data of different navigation sections and different time periods;
the training unit is used for constructing a navigation time prediction model and inputting the navigation time data into the constructed navigation time prediction model for training;
and the generating unit is used for combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value.
For the embodiments of the present invention, the description is simple because it corresponds to the above embodiments, and for the related similarities, please refer to the description in the above embodiments, and the detailed description is omitted here.
In order to verify the effect of the prediction model, besides the prediction model fusing various characteristics, a prediction model based on LSTM alone, a prediction model based on GRU alone and a prediction model only containing ship traffic dynamic characteristics are realized for comparative analysis.
By utilizing the four models, AIS data and flight segment data of 11 months in 2018-year 2019 of No. 2-8 flight segments are respectively trained, 1 month data is used as a verification set to carry out a test experiment, relative errors are used as evaluation criteria, and the final experiment result is shown in the following table. As can be seen from the table below, the multi-feature fused prediction model has the smallest relative error, i.e., has the highest prediction accuracy.
The embodiment of the application also discloses a computer-readable storage medium, wherein a computer instruction set is stored in the computer-readable storage medium, and when the computer instruction set is executed by a processor, the method for predicting the voyage time based on deep learning, which is provided by any one of the above embodiments, is implemented.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for predicting voyage time based on deep learning is characterized by comprising the following steps:
acquiring AIS data;
processing the acquired AIS data to obtain the navigation time data of different navigation sections and different time periods;
constructing a navigation time prediction model, and inputting the navigation time data into the constructed navigation time prediction model for training;
and combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value.
2. The method of predicting voyage time according to claim 1, wherein said processing the received AIS data to obtain voyage time data of different voyage segments and different time segments comprises:
cutting and segmenting the channel according to channel characteristics, wherein ships with similar types in each channel have similar navigation behaviors and navigation time;
calculating the average navigation speed of the ship in each navigation section by using the ship navigation speed information in the AIS data, and further calculating the average navigation time required for the ship to pass through the whole navigation section according to the average speed;
and according to the traffic flow characteristics, setting the time interval to be n hours, and counting the navigation time of each navigation segment in different time intervals.
3. The voyage time prediction method according to claim 1 or 2, characterized in that the AIS data comprises vessel static data, vessel dynamic data, vessel voyage data, and voyage safety information;
the ship static data comprises a ship name, a call sign, a marine mobile service identification code (MMSI), an International Maritime Organization (IMO) number, a ship length, a ship width and a ship type;
the dynamic data of the ship comprises ship position data, ground speed/course and ship fore-direction information;
the ship voyage data comprises ship state, draft, destination and ETA information;
the navigation safety information comprises navigation warning and weather report information.
4. The method of claim 2, wherein the calculating the average voyage time required for the vessel to traverse the entire leg based on the average speed is based on the following equation:
wherein T is the average voyage time, ViThe speed of the ith ship is defined, n is the number of ships in the leg, and l is the mileage of the leg.
5. The method of claim 1, wherein the constructed time-of-flight prediction model comprises a convolutional neural network for capturing spatial correlations between adjacent flight segments and a recurrent neural network for capturing temporal correlations.
6. The method of claim 1, wherein the inputting the voyage data into the constructed voyage prediction model for training comprises:
setting L1, L2 and L3 to represent the navigation time sequence of the upstream flight segment, the navigation time sequence of the target flight segment and the navigation time sequence of the downstream flight segment respectively;
splicing the navigation time sequences of the three navigation sections into a characteristic by using Concat operation on the L1, the L2 and the L3, and recording the characteristic as L; l ═ Concat [ L1, L2, L3]
And extracting the spliced feature L by adopting a one-dimensional convolution neural network, wherein the extracted feature is marked as F, and F is F (∑) according to the one-dimensional convolution operationi∈MHi*Wi+ b), where H is the voyage time series, W is the weight of the convolution translation operator, b is the bias execution, and f (·) is the activation function;
inputting the extracted feature F into the recurrent neural network to obtain the feature extracted by the navigation time prediction model; the cyclic neural network has 20 inputs which are respectively used for predicting the flight time characteristics of the first 20 periods, and each flight time characteristic is obtained by comprehensively extracting three flight periods through the one-dimensional convolution neural network according to the spatiality;
fusing the spatial characteristics of the channel with the characteristics extracted by the navigation time prediction model, wherein the spatial characteristics of the channel participating in prediction comprise three elements of the length of the navigation section, the navigation width and the water depth;
and then fusing the 1 channel historical similarity characteristic, the spatial characteristics of the three channels and the characteristics extracted by the navigation time prediction model, inputting the fused characteristics into a full connection layer, and finally outputting the navigation time of the specified navigation section in the next time period.
7. The method of claim 5, wherein the convolutional neural network is a one-dimensional convolutional neural network; the recurrent neural network adopts a GRU structure.
8. The method of claim 6, wherein each voyage time sequence comprises the voyage time of the current slot and 20 slots before the current slot.
9. A deep learning-based travel time prediction apparatus, comprising:
an acquisition unit for acquiring AIS data;
the calculation unit is used for processing the AIS data acquired by the acquisition unit to obtain the navigation time data of different navigation sections and different time periods;
the training unit is used for constructing a navigation time prediction model and inputting the navigation time data into the constructed navigation time prediction model for training;
and the generating unit is used for combining the trained flight time prediction model with a flight path planning technology to obtain an accurate flight time prediction value.
10. A computer-readable storage medium having a set of computer instructions stored therein; the set of computer instructions, when executed by a processor, implement a deep learning based voyage time prediction method as claimed in any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010530842.3A CN111738500B (en) | 2020-06-11 | 2020-06-11 | Navigation time prediction method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010530842.3A CN111738500B (en) | 2020-06-11 | 2020-06-11 | Navigation time prediction method and device based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111738500A true CN111738500A (en) | 2020-10-02 |
| CN111738500B CN111738500B (en) | 2024-01-12 |
Family
ID=72648851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010530842.3A Active CN111738500B (en) | 2020-06-11 | 2020-06-11 | Navigation time prediction method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738500B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118143A (en) * | 2020-11-18 | 2020-12-22 | 迈普通信技术股份有限公司 | Traffic prediction model, training method, prediction method, device, apparatus, and medium |
| CN112561452A (en) * | 2021-02-19 | 2021-03-26 | 深圳普罗空运有限公司 | Goods tracking method based on international air transportation logistics APP |
| CN113096481A (en) * | 2021-05-19 | 2021-07-09 | 江苏科技大学 | Ship path planning training system for laboratory |
| CN113221450A (en) * | 2021-04-27 | 2021-08-06 | 中国科学院国家空间科学中心 | Dead reckoning method and system for sparse and uneven time sequence data |
| CN113393048A (en) * | 2021-06-24 | 2021-09-14 | 武汉长江船舶设计院有限公司 | Electric cruise ship navigation energy consumption prediction and control method |
| CN113610347A (en) * | 2021-07-05 | 2021-11-05 | 上海海事大学 | Ship shipping market transport capacity assessment method |
| CN114118604A (en) * | 2021-12-02 | 2022-03-01 | 武汉理工大学 | Ferry channel crossing behavior prediction method and system based on machine learning |
| WO2022105296A1 (en) * | 2020-11-18 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Blockchain-based barge berthing method and apparatus, and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103531043A (en) * | 2013-09-27 | 2014-01-22 | 重庆大学 | Point-to-point ship sailing time estimation method based on ship route matching |
| CN107316501A (en) * | 2017-06-28 | 2017-11-03 | 北京航空航天大学 | A kind of SVMs Travel Time Estimation Method based on grid search |
| CN109035761A (en) * | 2018-06-25 | 2018-12-18 | 复旦大学 | Travel time estimation method based on back-up surveillance study |
| CN109214107A (en) * | 2018-09-26 | 2019-01-15 | 大连海事大学 | A kind of ship's navigation behavior on-line prediction method |
| CN110110943A (en) * | 2019-05-21 | 2019-08-09 | 大连海事大学 | A kind of fleet's efficiency comprehensive intelligent Optimal Management System and optimization method based on big data |
| CN110321785A (en) * | 2019-05-09 | 2019-10-11 | 北京尚文金泰教育科技有限公司 | A method of introducing ResNet deep learning network struction dermatoglyph classification prediction model |
| CN110555568A (en) * | 2019-09-12 | 2019-12-10 | 重庆交通大学 | Road traffic running state real-time perception method based on social network information |
| GB201917510D0 (en) * | 2019-11-29 | 2020-01-15 | Percy Iain Bryden | Navigation guidance method and system |
| CN110827543A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on deep learning and spatio-temporal data fusion |
| CN111091708A (en) * | 2019-12-13 | 2020-05-01 | 中国科学院深圳先进技术研究院 | Vehicle track prediction method and device |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
-
2020
- 2020-06-11 CN CN202010530842.3A patent/CN111738500B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103531043A (en) * | 2013-09-27 | 2014-01-22 | 重庆大学 | Point-to-point ship sailing time estimation method based on ship route matching |
| CN107316501A (en) * | 2017-06-28 | 2017-11-03 | 北京航空航天大学 | A kind of SVMs Travel Time Estimation Method based on grid search |
| CN109035761A (en) * | 2018-06-25 | 2018-12-18 | 复旦大学 | Travel time estimation method based on back-up surveillance study |
| CN109214107A (en) * | 2018-09-26 | 2019-01-15 | 大连海事大学 | A kind of ship's navigation behavior on-line prediction method |
| CN110321785A (en) * | 2019-05-09 | 2019-10-11 | 北京尚文金泰教育科技有限公司 | A method of introducing ResNet deep learning network struction dermatoglyph classification prediction model |
| CN110110943A (en) * | 2019-05-21 | 2019-08-09 | 大连海事大学 | A kind of fleet's efficiency comprehensive intelligent Optimal Management System and optimization method based on big data |
| CN110555568A (en) * | 2019-09-12 | 2019-12-10 | 重庆交通大学 | Road traffic running state real-time perception method based on social network information |
| CN110827543A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on deep learning and spatio-temporal data fusion |
| GB201917510D0 (en) * | 2019-11-29 | 2020-01-15 | Percy Iain Bryden | Navigation guidance method and system |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
| CN111091708A (en) * | 2019-12-13 | 2020-05-01 | 中国科学院深圳先进技术研究院 | Vehicle track prediction method and device |
Non-Patent Citations (4)
| Title |
|---|
| MINGYANG PAN等: "Water Level Prediction Model Based on GRU and CNN", 《ACCESS》, pages 60090 - 60100 * |
| WENJIE ZHANG等: "Roll Motion Prediction of Unmanned Surface Vehicle Based on Coupled CNN and LSTM", 《FUTURE INTERNET》, pages 1 - 15 * |
| 潘明阳等: "基于改进A*算法的内河水网航线规划及应用", 《上海海事大学学报》, pages 40 - 45 * |
| 钱正锋;: "信息化时代的内河船员服务", 中国海事, no. 07, pages 13 - 14 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118143A (en) * | 2020-11-18 | 2020-12-22 | 迈普通信技术股份有限公司 | Traffic prediction model, training method, prediction method, device, apparatus, and medium |
| WO2022105296A1 (en) * | 2020-11-18 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Blockchain-based barge berthing method and apparatus, and storage medium |
| CN112561452A (en) * | 2021-02-19 | 2021-03-26 | 深圳普罗空运有限公司 | Goods tracking method based on international air transportation logistics APP |
| CN113221450A (en) * | 2021-04-27 | 2021-08-06 | 中国科学院国家空间科学中心 | Dead reckoning method and system for sparse and uneven time sequence data |
| CN113221450B (en) * | 2021-04-27 | 2024-03-12 | 中国科学院国家空间科学中心 | Space-time prediction method and system for sparse non-uniform time sequence data |
| CN113096481A (en) * | 2021-05-19 | 2021-07-09 | 江苏科技大学 | Ship path planning training system for laboratory |
| CN113393048A (en) * | 2021-06-24 | 2021-09-14 | 武汉长江船舶设计院有限公司 | Electric cruise ship navigation energy consumption prediction and control method |
| CN113393048B (en) * | 2021-06-24 | 2023-09-15 | 武汉长江船舶设计院有限公司 | Electric cruise ship navigation energy consumption prediction and control method |
| CN113610347A (en) * | 2021-07-05 | 2021-11-05 | 上海海事大学 | Ship shipping market transport capacity assessment method |
| CN113610347B (en) * | 2021-07-05 | 2024-04-05 | 上海海事大学 | Ship shipping market capacity assessment method |
| CN114118604A (en) * | 2021-12-02 | 2022-03-01 | 武汉理工大学 | Ferry channel crossing behavior prediction method and system based on machine learning |
| CN114118604B (en) * | 2021-12-02 | 2024-05-28 | 武汉理工大学 | Method and system for predicting ferry crossing channel behavior based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111738500B (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738500B (en) | Navigation time prediction method and device based on deep learning | |
| Zhang et al. | A predictive analytics method for maritime traffic flow complexity estimation in inland waterways | |
| Xiao et al. | Maritime traffic probabilistic forecasting based on vessels’ waterway patterns and motion behaviors | |
| US11235774B2 (en) | Road condition predicting method and apparatus, computer device and readable medium | |
| CN107316501B (en) | Grid search based travel time prediction method for support vector machine | |
| Luo et al. | AccuAir: Winning solution to air quality prediction for KDD Cup 2018 | |
| Miller et al. | Mining traffic incidents to forecast impact | |
| CN114936332A (en) | Method and device for analyzing ship traffic flow in water area of wind power plant and storage medium | |
| Liu et al. | A data mining method to extract traffic network for maritime transport management | |
| He et al. | Mining channel water depth information from IoT-based big automated identification system data for safe waterway navigation | |
| CN102376025A (en) | Method for simulating mobile phone data and evaluating urban road network traffic condition | |
| CN108875032B (en) | Region type determination method and device | |
| Zhang et al. | Strength-weighted flow cluster method considering spatiotemporal contiguity to reveal interregional association patterns | |
| CN116823572B (en) | Population flow data acquisition method and device and computer readable storage medium | |
| CN116562487B (en) | Moving destination prediction method considering intersection space-time correlation and history travel semantics | |
| Galbrun et al. | Safe navigation in urban environments | |
| Lee et al. | Congestion pattern model for predicting short-term traffic decongestion times | |
| Sang et al. | An agent-based simulation on navigational capacity of multi-bridge waterways | |
| Netto et al. | Modeling oceanic variables with dynamic graph neural networks | |
| Abbas et al. | Scaling deep learning models for large spatial time-series forecasting | |
| CN115965163A (en) | Rail transit short-time passenger flow prediction method for generating countermeasures to loss based on space-time diagram | |
| Salamanis et al. | Evaluating the effect of time series segmentation on STARIMA-based traffic prediction model | |
| Molavipour et al. | Causality graph of vehicular traffic flow | |
| CN111949840A (en) | Topological graph structure construction method and device based on Internet of things data | |
| Fuentes et al. | A spatial framework for extracting Suez Canal transit information from AIS |
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 |