CN115946820A - Training method of floating environment data prediction model, floating control method and equipment - Google Patents
Training method of floating environment data prediction model, floating control method and equipment Download PDFInfo
- Publication number
- CN115946820A CN115946820A CN202310244196.8A CN202310244196A CN115946820A CN 115946820 A CN115946820 A CN 115946820A CN 202310244196 A CN202310244196 A CN 202310244196A CN 115946820 A CN115946820 A CN 115946820A
- Authority
- CN
- China
- Prior art keywords
- floating
- underwater
- data
- energy consumption
- sample data
- 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.)
- Pending
Links
- 238000007667 floating Methods 0.000 title claims abstract description 211
- 238000000034 method Methods 0.000 title claims abstract description 106
- 238000012549 training Methods 0.000 title claims abstract description 94
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000005265 energy consumption Methods 0.000 claims description 82
- 230000033001 locomotion Effects 0.000 claims description 67
- 238000005457 optimization Methods 0.000 claims description 36
- 230000006870 function Effects 0.000 claims description 26
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 238000013178 mathematical model Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 3
- 210000004205 output neuron Anatomy 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 17
- 239000000126 substance Substances 0.000 description 10
- 239000013535 sea water Substances 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- -1 and for example Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
A training method, a floating control method and equipment of a floating environment data prediction model are disclosed, wherein the method comprises the following operations which are repeatedly executed until a training result meets a preset ending condition: executing a training sample data set generating process to generate a training sample data set; training a floating environmental data prediction model to be trained by utilizing a training sample data set; executing a training sample data set generation process, wherein the generation of the training sample data set comprises the following steps: under the condition that the training result does not meet the preset ending condition, the following operations are repeatedly executed until the floating times of the underwater surveying system meet the preset floating times: acquiring a plurality of initial floating environment data in the floating process of an underwater surveying system; dividing a plurality of initial floating environment data into a plurality of first-order sample data sets based on a dividing strategy; processing each first-order sample data set into second-order sample data based on a processing strategy to generate a second-order sample data set; and generating a training sample data set based on a plurality of second-order sample data sets.
Description
Technical Field
The invention relates to the technical field of surveying, in particular to a training method of a floating environment data prediction model, a floating control method and equipment.
Background
An underwater survey system may be used to monitor an underwater environment. However, the service life and the number of operating sections of the existing underwater surveying system are limited by the capacity of a battery and the operating power consumption, so that the existing underwater surveying system is harmful to the health of the underwater environment and is not beneficial to the continuous application of the underwater surveying system.
Therefore, the method has great significance for researching how to prolong the service life of the battery of the underwater surveying system and reduce the influence on the underwater environment.
Disclosure of Invention
In view of this, embodiments of the present invention provide a training method for a floating environment data prediction model, a floating control method for an underwater surveying system, and an electronic device.
In one aspect of the invention, a training method for a floating environment data prediction model is provided, which includes repeatedly executing the following operations until a training result meets a preset end condition to obtain the floating environment data prediction model, wherein the floating environment data prediction model is used for predicting floating environment data of the next floating movement of an underwater surveying system: executing a training sample data set generating process to generate a training sample data set; training a floating environmental data prediction model to be trained by utilizing the training sample data set; wherein, the executing the training sample data set generating process, and generating the training sample data set includes: under the condition that the training result does not meet a preset ending condition, the following operations are repeatedly executed until the floating times of the underwater surveying system meet preset floating times: acquiring a plurality of initial floating environment data in the floating process of the underwater surveying system; dividing the plurality of initial floating environment data into a plurality of first-order sample data sets based on a dividing strategy; processing each first-order sample data set into second-order sample data based on a processing strategy to generate a second-order sample data set; and generating the training sample data set based on a plurality of second-order sample data sets.
According to an embodiment of the present invention, each of the initial floating environment data includes temperature data and density data of the water measured by the underwater surveying system during a current floating period.
According to the embodiment of the invention, the prediction model of the floating environment data to be trained is a neural network time sequence model, wherein the number of output neurons of the prediction model of the floating environment data to be trained is 1, the number of hidden layer nodes is 5, and the learning rate is 0.15, and the neural network time sequence model is formed by adding time sequence parameters on the basis of the neural network model.
In another aspect of the present invention, there is provided a float control method of an underwater surveying system, including: predicting the prediction model of the floating environment data obtained by training by the training method to obtain predicted floating environment data; establishing a floating energy consumption optimization model by utilizing the predicted floating environment data; obtaining predicted energy consumption data in the floating process of the underwater surveying system based on the floating energy consumption optimization model, wherein the predicted energy consumption data is characterized by total energy consumption of the underwater surveying system for the next floating motion; based on the predicted energy consumption data, obtaining optimized floating data of the underwater surveying system by using a floating energy consumption optimization calculation method; and controlling the underwater surveying system to do floating motion based on the optimized floating data.
According to the embodiment of the invention, the establishing of the floating energy consumption optimization model by utilizing the predicted floating environment data comprises the following steps: performing piecewise fitting on the predicted floating environment data based on a piecewise fitting strategy to obtain a temperature fitting function and a density fitting function; establishing a motion mathematical model of the underwater surveying system based on the relation between the stress condition of the underwater surveying system and the motion speed and the motion depth, wherein the motion depth is determined by the current oil discharge amount of the underwater surveying system; and obtaining the floating energy consumption optimization model by utilizing the temperature fitting function, the density fitting function and the motion mathematical model based on an energy consumption optimization strategy.
According to an embodiment of the present invention, the obtaining of the optimized floating data of the underwater surveying system by using a floating energy consumption optimization calculation method based on the predicted energy consumption data includes: initializing a population by taking the predicted energy consumption data as an objective function and taking the total oil discharge amount of the upward movement in the section of the underwater surveying system finished once and a preset upward speed threshold value as constraint conditions, wherein the total oil discharge amount is determined by the total distance of the upward movement in the section of the underwater surveying system finished once; iterating the following operations based on a group voting method until the iteration times reach a preset iteration time: inputting the initialized population into the floating energy consumption optimization model to obtain predicted total energy consumption of a plurality of individuals; performing variation treatment and cross treatment on the initialized population to update the population to obtain an initially updated population; inputting the initially updated population into the floating energy consumption optimization model to obtain total updated energy consumption of individuals in the initially updated population; and screening the population based on the population voting method to obtain an optimized individual with the optimized floating data.
According to an embodiment of the present invention, the predicted floating environment data includes predicted temperature data and predicted density data of water for a next floating motion of the underwater surveying system.
According to the embodiment of the invention, the optimized floating data comprises the optimized oil discharge times of the underwater surveying system for the next floating motion, the optimized oil discharge amount of each oil discharge and the optimized floating speed threshold value in the floating process of the underwater surveying system.
According to an embodiment of the present invention, the initialized population includes a plurality of randomly generated individuals with random oil drainage times, random oil drainage amount, and random speed threshold information.
In another aspect of the present invention, an electronic device is provided, including: one or more processors; and a memory configured to store one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method.
According to the embodiment of the invention, the training sample data set can be generated for multiple times by continuously acquiring the initial floating environment data in the floating process of the underwater surveying system for multiple times, so that the floating environment data prediction model can be trained by the real-time initial floating environment data in the floating process of the underwater surveying system, the influence factors of the working environment in the movement of the underwater surveying system can be reduced, the working efficiency of the underwater surveying system is improved, the service life of a battery of the underwater surveying system is prolonged, the complexity of the training sample can be reduced by processing the initial floating environment data through a partition strategy and a processing strategy, and the effect of predicting the floating environment data of the next floating movement of the underwater surveying system more accurately can be realized.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates an exemplary system architecture to which a method of training a floating environment data prediction model, a method of floating control for an underwater survey system, according to an embodiment of the present invention, may be applied;
FIG. 2 schematically illustrates a flow diagram of a method of training a floating environment data prediction model according to an embodiment of the invention;
fig. 3 schematically shows a flowchart of executing a training sample data set generating process to generate a training sample data set when a training result does not satisfy a preset end condition according to an embodiment of the present invention;
FIG. 4 schematically illustrates a flow chart of a float control method of an underwater survey system according to an embodiment of the invention;
FIG. 5 schematically illustrates a flow diagram for building a buoyant energy consumption optimization model using predicted buoyant environment data, according to an embodiment of the invention;
FIG. 6 schematically illustrates a flow chart for obtaining optimized float data for an underwater survey system using a float energy consumption optimization calculation method based on predicted energy consumption data, in accordance with an embodiment of the invention;
FIG. 7 schematically illustrates a flow chart for controlling an underwater survey system to perform a heave motion based on optimized heave data according to an embodiment of the invention; and
FIG. 8 schematically illustrates a block diagram of electronics for a method of training a buoyant environment data predictive model and a method of buoyant control for an underwater survey system, in accordance with an embodiment of the invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). Where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.).
Fig. 1 schematically illustrates an exemplary system architecture to which a training method of a buoyant environment data prediction model, a buoyant control method of an underwater survey system, according to an embodiment of the present invention, may be applied.
It should be noted that fig. 1 is only an example of a system architecture to which the embodiment of the present invention may be applied to help those skilled in the art understand the technical content of the present invention, and does not mean that the embodiment of the present invention may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, a system architecture 100 according to this embodiment may include a subsea survey system 101, a terminal device 102, and a network 103. The network 103 is used to provide a medium for communication links between the underwater survey system 101 and the terminal devices 102. Network 103 may include various connection types, such as wired and/or wireless communication links, and so forth.
A user may use the terminal device 102 to interact with the underwater survey system 101 through the network 103 to receive or send messages or the like. The underwater survey system 101 and the terminal device 102 may be installed with various communication client applications.
The underwater survey system 101 may be a system device having an underwater survey function, for example, a buoy. The underwater survey system 101 may be equipped with various sensors for acquiring information such as temperature, density, and depth under water. The terminal device 102 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The underwater survey system 101 and the terminal device 102 may be used with terminal devices of various types of servers. For example, the Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service extensibility in a conventional physical host and VPS service (Virtual Private Server). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be noted that the training method of the floating environment data prediction model and the floating control method of the underwater surveying system provided by the embodiment of the present invention can be generally executed by the terminal device 102. The training method of the floating environment data prediction model and the floating control method of the underwater surveying system provided by the embodiment of the invention can also be executed by a server or a server cluster which can communicate with the underwater surveying system 101 and the terminal device 102. Alternatively, the training method of the floating environment data prediction model and the floating control method of the underwater surveying system provided by the embodiment of the present invention may be executed by other terminal devices different from the underwater surveying system 101 or the terminal device 102.
For example, the data to be processed may be originally stored in either the underwater survey system 101 or the terminal device 102 (e.g., but not limited to the terminal device 102), or stored on an external storage device and may be imported into the terminal device 102. Then, the terminal device 102 may locally perform the training method of the floating environment data prediction model and the floating control method of the underwater surveying system provided by the embodiment of the present invention, or transmit the data to be processed to another terminal device, a server, or a server cluster, and perform the training method of the floating environment data prediction model and the floating control method of the underwater surveying system provided by the embodiment of the present invention by another terminal device, a server, or a server cluster receiving the image to be processed.
It should be understood that the number of terminal devices and networks in fig. 1 is merely illustrative. There may be any number of terminal devices and networks, as desired for implementation.
It should be noted that the sequence numbers of the respective operations in the following methods are merely used as representations of the operations for description, and should not be construed as representing the execution order of the respective operations. The method need not be performed in the exact order shown, unless explicitly stated.
In the process of implementing the concept of the present invention, the inventors found that at least the following problems exist in the related art:
because the underwater survey system can carry a limited amount of battery energy, there is a need to accurately control the power consumption of the operation of the underwater survey system in order to extend the operating time of the underwater survey system and reduce the waste of battery energy. Furthermore, because the motion environment of the underwater surveying system influences the power consumption of the underwater surveying system, the power consumption of the underwater surveying system can be calculated by predicting the motion environment of the next section of the underwater surveying system, and because the upward floating motion energy consumption accounts for a higher ratio in the section motion process of the underwater surveying system, the upward floating environment data of the next upward floating motion of the underwater surveying system can be predicted, so that the power consumption of the section motion of the underwater surveying system is reduced, and the service life of a battery of the underwater surveying system is prolonged.
In order to at least partially solve the technical problems in the related art, the invention provides a training method of a floating environment data prediction model, a floating control method of an underwater surveying system and an electronic device. The method can be applied to the field of survey equipment control.
According to the embodiment of the invention, on one hand, a training method of a floating environment data prediction model is provided.
Fig. 2 schematically shows a flow chart of a training method of a floating environment data prediction model according to an embodiment of the present invention.
As shown in fig. 2, the method 200 may include repeatedly performing the following operations S210 to S220 until the training result satisfies a preset ending condition, so as to obtain a floating environment data prediction model:
in operation S210, a training sample data set generation process is performed to generate a training sample data set.
In operation S220, a floating environment data prediction model to be trained is trained using a training sample data set.
Fig. 3 schematically shows a flowchart of executing a process of generating a training sample data set to generate a training sample data set when a training result does not satisfy a preset termination condition according to an embodiment of the present invention.
As shown in FIG. 3, operation S210 may include repeatedly performing the following operations S310-S340 until the number of buoys of the underwater survey system satisfies a preset number of buoys:
at operation S310, a plurality of initial float environment data during a float of an underwater survey system is acquired.
In operation S320, a plurality of initial floating environment data is divided into a plurality of first-order sample data sets based on a division policy.
In operation S330, each first-order sample data set is processed into second-order sample data based on a processing policy to generate a second-order sample data set.
In operation S340, a training sample data set is generated based on a plurality of second order sample data sets.
According to the embodiment of the invention, the floating environment data prediction model can be used for predicting the floating environment data of the next floating motion of the underwater surveying system.
According to an embodiment of the invention, each initial float environment data may include temperature data and density data of the water measured by the underwater survey system during a current float cycle. Each initial floating environment data can comprise temperature data and density data of water measured by the underwater surveying system in the t-1 floating period, and floating environment data predicted by the corresponding trained floating environment data prediction model can be the temperature data and the density data of the water of the underwater surveying system in the t floating period, wherein t is a positive integer greater than 1. The underwater survey system can acquire temperature data of water and density data of water in a plurality of floating periods through a plurality of floating movements. The collected temperature data and density data of water in a plurality of floating periods can be processed to improve the accuracy of training, for example, the temperature data and density data of water, which have a large influence on the underwater surveying system, can be marked as abnormal values, and the abnormal values can be corrected to normal values, and the normal values can be average values of the obtained temperature data and density data of water in a plurality of floating periods after the abnormal values are removed.
According to the embodiment of the invention, after a floating environment data prediction model trained for the t-2 th time is trained by utilizing a generated t-1 st training sample data set, under the condition that a training result does not meet a preset ending condition, initial floating environment data of the t-th floating motion of the underwater surveying system is obtained, the t-1 st training sample data set is updated to be a t-th training sample data set, and then the t-th training sample data set is utilized to train the floating environment data prediction model trained for the t-1 th time, wherein t is a positive integer greater than or equal to 2. And updating the t-1 th training sample data set into the t-th training sample data set, wherein the acquired initial floating environment data of the t-th floating motion of the underwater surveying system is processed into a t-th second-order sample data set, and then the acquired initial floating environment data is added into the t-1 th training sample data set to obtain the t-th training sample data set.
According to the embodiment of the present invention, the preset end condition may include at least one of: the training error reaches the target error, and the training times reaches the preset training times. The preset training times can be times of actually needing the underwater surveying system to carry out floating movement and collecting initial floating environment data. The predetermined number of training sessions may include an estimated maximum number of profile motions based on prior experience and the amount of battery power carried by the underwater survey system during actual use.
According to the embodiment of the invention, the preset floating times can comprise the minimum section times for starting training of model training and can comprise the minimum times for obtaining initial floating environment data meeting the requirement of model training.
According to an embodiment of the present invention, the partitioning strategy may be a strategy of partitioning a floating distance of the underwater survey system, for example, in case that the floating distance is 4000 meters in 1-time profile motion of the underwater survey system, the 4000 meters may be equally divided into 4000 sections, each of which is 1 meter. For example, in a 1-pass profile of the underwater survey system, with an upward floating distance of 4000 meters, 4000 meters may be divided into two sections, 0-2000 being a first section and 2000-4000 being a second section, the first section may be divided equally into 1000 segments and the second section may be divided equally into 2000 segments.
According to the embodiment of the invention, the underwater surveying system can acquire the initial floating environment data once within the interval t time, the floating distance is 4000 meters, and under the condition that 4000 meters are divided into 4000 sections, the number of the first-order sample data sets can be the same as that of the sections, the first-order sample data sets can be the initial floating environment data set in each section, and can comprise the steps that the underwater surveying system executes the acquiring action in the section and acquires the acquired set of the initial floating environment data in the section. For example, where the underwater survey system makes 1 profile movement, 3 initial float environment data may be obtained per segment of the underwater survey system, each first order sample data set may include 3 initial float environment data.
According to the embodiment of the present invention, the processing policy may be a policy of processing the first-order sample data set into second-order sample data, for example, the processing policy may be averaging a plurality of data in the first-order sample data set, and the processing policy may be averaging the first-order sample data set after removing the maximum value and the minimum value. The above-mentioned average value may be characterized as second-order sample data, and the second-order sample data set may be a set of a plurality of second-order sample data.
According to the embodiment of the invention, the sample of the training sample data set for training the floating environment data prediction model to be trained can be historical profile data, and the prediction of the trained floating environment data prediction model can be time sequence prediction. The training sample data set may be a set of multiple second order sample data sets after multiple profile motions by the underwater survey system. For example, where the underwater survey system makes 5 profile motions, each with a float distance of 4000 meters, bisecting 4000 meters into 4000 segments, the training sample data set may be a set comprising 5 second order sample data sets, where each second order sample data set may comprise 4000 second order sample data. Each second order sample data carries temperature data and density data information for the water at the corresponding section of the underwater survey system. The data volume of the training sample data set can be increased by increasing the number of the sections in real time, and further the influence of the change of the environment where the underwater surveying system is located on predicting the power consumption of the underwater surveying system can be reduced.
According to the embodiment of the invention, the process of training the floating environment data prediction model to be trained by utilizing the training sample data set can comprise the iterative processes of network initialization, hidden layer output calculation, error calculation, weight updating, threshold updating and the like.
According to the embodiment of the invention, the training sample data set can be generated for multiple times by continuously acquiring the initial floating environment data in the floating process of the underwater surveying system for multiple times, so that the floating environment data prediction model can be trained by the real-time initial floating environment data in the floating process of the underwater surveying system, the influence factors of the working environment in the movement of the underwater surveying system can be reduced, the working efficiency of the underwater surveying system is improved, the service life of a battery of the underwater surveying system is prolonged, the complexity of the training sample can be reduced by processing the initial floating environment data through a partition strategy and a processing strategy, and the effect of predicting the floating environment data of the next floating movement of the underwater surveying system more accurately can be realized.
According to the embodiment of the invention, the prediction model of the floating environment data to be trained is a neural network time sequence model. The neural network time series model can be added with time series parameters on the basis of the neural network model.
According to an embodiment of the present invention, the training sample data set may be represented as
，/>
Second order sample data comprising a plurality of sections corresponding to the first section @>
Second order sample data representative of a plurality of sections corresponding to the second section->
Second-order sample data representing a plurality of cross sections corresponding to the nth section, wherein n is a positive integer.
According to the embodiment of the present invention, the excitation function may be a Sigmoid function, and the expression thereof is:
according to the embodiment of the invention, the number of output neurons of the prediction model of the floating environment data to be trained is 1, the number of nodes of the hidden layer is 5, and the learning rate is 0.15. The output of the prediction of the trained floating environment data prediction model can be floating environment data of the next floating movement of the underwater surveying system, and can be classified as a single regression problem, so that the number of neurons can be set to 1, the number of nodes of a hidden layer can be 5, the learning rate can be set to 0.15, the training times can be set to 200, and the target error can be set to 0.005.
FIG. 4 schematically shows a flow chart of a float control method of an underwater surveying system according to an embodiment of the invention.
As shown in FIG. 4, the method 400 may include the following operations S410-S450.
In operation S410, predicted floating environment data may be obtained by using the prediction model prediction of floating environment data obtained by training in the training method 200.
In operation S420, a floating energy consumption optimization model may be established using the predicted floating environment data.
In operation S430, predicted energy consumption data of the underwater surveying system during the ascent process may be obtained based on the ascent energy consumption optimization model.
In operation S440, optimized floating data of the underwater survey system may be obtained using a floating energy consumption optimization calculation method based on the predicted energy consumption data.
Based on the optimized ascent data, the underwater surveying system may be controlled to make an ascent motion in operation S450.
According to embodiments of the invention, the predicted ascent environment data may include predicted temperature data and predicted density data for water for the next ascent movement by the underwater survey system.
According to the embodiment of the invention, the floating energy consumption optimization model can be used for predicting the predicted energy consumption data of the underwater surveying system in the floating process. The predicted energy consumption data may be characterized as the total energy consumption of the underwater survey system to perform the next ascent movement.
According to the embodiment of the invention, the optimized floating data comprises the optimized oil discharge times of the next floating movement of the underwater surveying system, the optimized oil discharge amount of each oil discharge and the optimized floating speed threshold value in the floating process of the underwater surveying system.
Fig. 5 schematically shows a flow chart for building a floating energy consumption optimization model using predicted floating environment data according to an embodiment of the present invention.
As shown in FIG. 5, operation S420 includes the following operations S510-S530.
In operation S510, the predicted floating environment data is piecewise fitted based on a piecewise fitting strategy to obtain a temperature fitting function and a density fitting function.
In operation S520, a motion mathematical model of the underwater surveying system is established based on the relationship between the force condition of the underwater surveying system and the motion speed and the motion depth.
In operation S530, a floating energy consumption optimization model is obtained based on the energy consumption optimization strategy by using the temperature fitting function, the density fitting function, and the motion mathematical model.
According to an embodiment of the invention, the depth of motion is determined by the current oil displacement of the underwater survey system.
According to the embodiment of the invention, the piecewise fitting strategy can be a strategy for performing piecewise fitting on the predicted floating environment data.
For example, the density data of water in the floating environment data can be predicted, and segmented according to different influences of different depths of water on the density of water, and for example, seawater density data of 0-1500m can be subjected to double-exponential fitting, and seawater density data of more than 1500m can be subjected to linear fitting, so that the following density fitting function can be obtained:
wherein the content of the first and second substances,
represents sea water density, unit: kg/m 3 (ii) a A, B, C, D, E, K, B are constant term coefficients, D represents depth, in units: and m is selected.
The temperature data of water in the floating environment data can be predicted, segmentation can be performed according to different influences of different depths of water on the temperature of the water, for example, sea water is taken as an example, the sea water temperature data of 0-2000m can be subjected to double-exponential fitting, the sea water temperature data of more than 2000m can be regarded as a constant, and the following temperature fitting functions can be obtained:
wherein, the first and the second end of the pipe are connected with each other,
represents the seawater temperature, in units: DEG C; l, M, N, O, P, Q are constant term coefficients, d represents depth, in units: and m is selected.
According to an embodiment of the invention, the stress condition of the underwater surveying system can be expressed as follows:
wherein the content of the first and second substances,
for buoyancy of the underwater survey system>
The resistance to which the underwater surveying system is subjected, G is the gravity of the underwater surveying system itself, and the units are allMay be N; m may be the mass of the underwater survey system in kg; />
Is the acceleration of the upward motion of the underwater survey system and t may be time, in units of s.
Drag of an underwater survey system according to an embodiment of the invention
The coefficient of friction resistance, total wet area and density of seawater for a subsurface survey system can be expressed as follows:
wherein the content of the first and second substances,
coefficient of friction resistance experienced by an underwater survey system, in units: n; s is the total wet area of the underwater survey system, in units: m is 2 ；/>
Is the floating speed of the underwater surveying system, unit: m/s 2 。
The rate of ascent of an underwater survey system can be shown as follows:
wherein the content of the first and second substances,
is a time interval.
According to embodiments of the present invention, the buoyancy of the underwater survey system may be expressed in terms of acceleration of gravity, density of water, and volume of the underwater survey system, as shown in the following equation:
wherein g isThe gravity acceleration can be 9.8m/s 2 ；
Is the volume of the body of the underwater survey system, in units: m is 3 ；
Is the volume of the oil mass of the outer oil bladder connected to the main body of the underwater survey system in units: m is 3 。/>
According to the embodiment of the invention, the oil volume of the outer oil bag
Can be expressed as:
wherein the content of the first and second substances,
is the oil discharge speed, unit: m is a unit of 3 And/s, can be expressed as:
where t is time, unit: s; d (t) is the depth corresponding to t time, unit: and m is selected. The underwater surveying system consists of an underwater surveying system main body and an outer oil bag. The underwater surveying system main body can be provided with a detector for surveying environment, and various sensors such as a temperature sensor, a pressure sensor and the like can be arranged in the detector to obtain temperature data, density data and depth data of water in which the underwater surveying system is positioned. The underwater surveying system comprises an inner oil bag in the main body, the inner oil bag is communicated with an outer oil bag, in the floating process of the underwater surveying system, in order to ensure that the floating process of the underwater surveying system keeps a certain acceleration, the oil in the inner oil bag in the main body of the underwater surveying system can be discharged to the outer oil bag, so that the whole volume of the underwater surveying system is increased, and the transmission quantity of the oil quantity can be monitored by a flowmeter.
According to the embodiment of the invention, the volume of the underwater surveying system body is influenced by temperature and pressure and changes when the depths are different, and the change amount can be expressed as:
wherein, the first and the second end of the pipe are connected with each other,
may be the amount by which the volume of the body of the underwater survey system varies with depth; />
May be the volume of the body of the underwater survey system in a marked condition; />
The volume change coefficient can be obtained by fitting the underwater surveying system main body in a pressure test;dmay be depth.
According to an embodiment of the invention, the volume change of the body of the underwater surveying system with the temperature can be expressed as:
wherein the content of the first and second substances,
may be a temperature coefficient; />
May be at different depths of the seawater temperature.
According to the embodiment of the invention, through the above formulas (4) to (9), a motion mathematical model of the underwater surveying system can be established.
According to the embodiment of the invention, the energy consumption optimization strategy can be a strategy for classifying and expressing the energy consumption in the floating process of the underwater surveying system. For example, the division may be performed according to the floating time or floating distance, or may be performed according to the energy consumption subject. The energy consumption main body in the floating process of the underwater surveying system is divided into examples, and the static energy consumption of the main control board and the dynamic energy consumption of the oil pump driving motor can be divided into the examples.
According to the embodiment of the invention, the static energy consumption of the main control board is basically kept stable, and the static energy consumption of the underwater surveying system can be considered as the integral of time.
According to the embodiment of the invention, the dynamic energy consumption of the driving motor is influenced by the floating distance (the depth of the underwater surveying system), the dynamic energy consumption is inconsistent at different depths, the power consumption is larger under the condition of deeper depth, and under the condition of 0-4000m depth, the dynamic energy consumption can be expressed as:
wherein the content of the first and second substances,
dynamic energy consumption can be achieved; />
May be a fitting coefficient; k may be the dynamic power consumption of the dynamic energy consumption operating on the water surface.
According to the embodiment of the invention, the floating energy consumption optimization model can be expressed as:
wherein the content of the first and second substances,
representing the total energy consumption of the upward motion in a profile motion performed by the underwater surveying system;
may be static energy consumption.
FIG. 6 schematically illustrates a flow chart for obtaining optimized float data for an underwater survey system using a float energy consumption optimization calculation method based on predicted energy consumption data, according to an embodiment of the invention.
As shown in FIG. 6, operation S440 includes the following operations S610-S620.
In operation S610, a population is initialized with the predicted energy consumption data as an objective function and with a total oil discharge amount of the upward floating motion in the section where the underwater surveying system completes one time and a preset upward floating speed threshold as constraint conditions.
In operation S620, iterating the following operations S621 to S624 based on a group voting method until the iteration number reaches a preset iteration number:
in operation S621, the initialized population is input to the floating energy consumption optimization model to obtain predicted total energy consumption of the plurality of individuals.
In operation S622, mutation processing and crossover processing are performed on the initialized population to update the population, resulting in an initial updated population.
In operation S623, the initially updated population is input into the floating energy consumption optimization model, and total updated energy consumption of individuals in the initially updated population is obtained.
In operation S624, populations are screened based on a population voting method to obtain optimized individuals with optimized float data.
According to embodiments of the invention, the total oil drainage may be determined by the total distance that the underwater survey system completes the uplift motion in a section.
According to an embodiment of the invention, the preset float speed threshold may be based on prior experience and an optimal speed estimate of the underwater surveying system at the time of actual use, e.g. the preset float speed threshold may be 0.01m/s.
According to an embodiment of the present invention, the initialized population includes a plurality of randomly generated individuals with random oil drain times, random oil drain amounts, and random speed threshold information.
According to an embodiment of the present invention, the random oil drain number may be expressed as:
according to an embodiment of the present invention, the random oil drainage amount may be expressed as:
according to an embodiment of the present invention, the random speed threshold may be expressed as:
according to the embodiment of the invention, the initialized population is input into the floating energy consumption optimization model, and the obtained predicted total energy consumption of the ith individual can be expressed as:
。
according to the embodiment of the present invention, performing the mutation process may be expressed as:
wherein the content of the first and second substances,
can be the individuals of the current population, a is not equal to b is not equal to c, a, b and c can be the number of the individuals of the current population,
may be a new individual of variation; f may be the coefficient of variation; />
Vector expression of oil discharge times, oil discharge amount and speed threshold information can be carried out on a normal individual a in the current population; />
Vector expression of oil discharge times, oil discharge amount and speed threshold information can be carried out on a normal individual b in the current population; />
The number of oil drainage times can be provided for a normal individual c in the current population,and vector expression of oil discharge amount and speed threshold information.
According to the embodiment of the present invention, the performing of the intersection processing may be expressed as:
wherein the content of the first and second substances,
can be the parameters of the next generation of individuals after crossing; />
May be a parameter of the current individual;
may be a parameter of the variant individual; c may be a crossover factor.
According to the embodiment of the invention, the iteration speed can be improved by utilizing the group voting method, and the population screening based on the group voting method can be based on the total energy consumption for updating of the individuals in the population, for example, the individual with the optimal total energy consumption for updating of the individuals in the population is screened as the screening result.
According to the embodiment of the invention, the initially updated population can be divided into a plurality of small groups, total energy consumption corresponding to all the initially updated population is compared, and excellent individuals are screened to enter the next generation population to obtain a new population.
According to the embodiment of the present invention, the preset iteration number may be an optimal iteration number determined based on previous experience, for example, the preset iteration number is set to 200, if the preset iteration number is greater than 200, the screening result is output, that is, the individual is optimized, otherwise, the next iteration is performed.
According to an embodiment of the invention, the preset float speed threshold may be a minimum preset float speed threshold set by previous experience that takes into account the total energy consumption of the underwater surveying system and the optimal speed of the underwater surveying system. The optimized floating speed threshold value can be an optimized minimum optimized floating speed threshold value obtained by using a floating energy consumption optimization calculation method. The random speed threshold may be a minimum random speed threshold generated within a minimum speed range determined based on previous experience.
Examples
FIG. 7 schematically illustrates a flow chart for controlling an underwater survey system to float based on optimized float data according to an embodiment of the invention.
As shown in fig. 7, after oil is discharged based on optimized floating data by controlling an oil pump in an underwater survey system, the underwater survey system starts floating, and when the current depth is judged to be less than or equal to 0, that is, the current depth is a preset depth or the water surface, the floating motion of this time is finished, and when the current depth is judged to be greater than 0, whether the oil discharge amount of the current section reaches the total oil discharge amount is further judged, the total oil discharge amount may be the total oil discharge amount of the floating motion in the section motion of this time output by a floating energy consumption optimization model, or the total oil discharge amount of the floating distance in the section motion of this time, and when the judgment result is that the total oil discharge amount is reached, the floating is stopped, the underwater survey system continues floating, and when the judgment result is that the total oil discharge amount is not reached, whether the current oil discharge amount reaches the optimized oil discharge amount of this time is further judged, and when the judgment result is that the oil discharge rate of the current oil pump reaches the optimized oil discharge amount reaches the optimized threshold, the oil discharge rate is judged to be the minimum oil discharge rate after the oil discharge rate reaches the optimal speed of the floating motion of the underwater survey system, and the minimum oil discharge rate is judged to be the optimal again, and the optimal oil discharge rate of the floating motion of the underwater survey system is judged to be the minimum oil discharge rate of the minimum oil discharge rate after the floating. The accuracy of the oil discharge amount may be set to 1mL. The optimized oil discharge amount can be the total oil discharge amount from the starting time to the ending time when the underwater surveying system performs one oil discharge action at the corresponding depth based on the floating energy consumption optimization calculation method.
FIG. 8 schematically illustrates a block diagram of electronics for a method of training a buoyant environment data predictive model and a method of buoyant control for an underwater survey system, in accordance with an embodiment of the invention. The electronic device shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 8, an electronic device 800 according to an embodiment of the present invention includes a processor 801 which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 801 may also include onboard memory for caching purposes. The processor 801 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present invention.
In the RAM 803, various programs and data necessary for the operation of the electronic apparatus 800 are stored. The processor 801, ROM 802, and RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flow according to the embodiment of the present invention by executing programs in the ROM 802 and/or the RAM 803. Note that the programs may also be stored in one or more memories other than the ROM 802 and RAM 803. The processor 801 may also perform various operations of method flows according to embodiments of the present invention by executing programs stored in the one or more memories.
According to an embodiment of the invention, the method flow according to an embodiment of the invention may be implemented as a computer software program. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable storage medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program, when executed by the processor 801, performs the above-described functions defined in the system of the embodiment of the present invention. The above described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules according to embodiments of the present invention.
The present invention also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement a method according to an embodiment of the invention.
According to an embodiment of the present invention, the computer readable storage medium may be a non-volatile computer readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
For example, according to embodiments of the present invention, a computer-readable storage medium may include the ROM 802 and/or the RAM 803 described above and/or one or more memories other than the ROM 802 and the RAM 803.
Embodiments of the invention further comprise a computer program product comprising a computer program comprising program code for performing the method provided by embodiments of the invention, for causing an electronic device to carry out the above-mentioned method provided by embodiments of the invention, when the computer program product is run on the electronic device.
The computer program, when executed by the processor 801, performs the above-described functions defined in the system/apparatus of an embodiment of the present invention. The above described systems, devices, modules, units, etc. may be implemented by computer program modules according to embodiments of the invention.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, and the like. In another embodiment, the computer program may also be transmitted in the form of a signal on a network medium, distributed, downloaded and installed via communication section 809, and/or installed from removable media 811. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
According to embodiments of the present invention, program code for executing a computer program provided by embodiments of the present invention may be written in any combination of one or more programming languages, and in particular, may be implemented using a high level procedural and/or object oriented programming language, and/or assembly/machine language. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, "C" or the like. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It will be appreciated by a person skilled in the art that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present invention are possible, even if such combinations or combinations are not explicitly recited in the present invention. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present invention may be made without departing from the spirit or teaching of the invention. All such combinations and/or associations fall within the scope of the present invention.
The embodiments of the present invention have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the invention is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the invention, and these alternatives and modifications are intended to fall within the scope of the invention.
Claims (10)
1. The training method of the floating environment data prediction model is characterized by comprising the following steps of repeatedly executing the following operations until a training result meets a preset finishing condition to obtain the floating environment data prediction model, wherein the floating environment data prediction model is used for predicting floating environment data of the next floating movement of an underwater surveying system:
executing a training sample data set generating process to generate a training sample data set;
training a floating environment data prediction model to be trained by utilizing the training sample data set;
wherein, the executing the training sample data set generating process, and generating the training sample data set includes: under the condition that the training result does not meet a preset ending condition, repeatedly executing the following operations until the floating times of the underwater surveying system meet preset floating times:
acquiring a plurality of initial floating environment data in the floating process of the underwater surveying system;
dividing the plurality of initial floating environment data into a plurality of first-order sample data sets based on a dividing strategy;
processing each first-order sample data set into second-order sample data based on a processing strategy to generate a second-order sample data set;
generating the training sample data set based on a plurality of the second order sample data sets.
2. The method of claim 1, wherein each of the initial float environment data comprises temperature data and density data of the water measured by the underwater survey system during a current float cycle.
3. The method according to claim 1, wherein the floating environment data prediction model to be trained is a neural network time series model, wherein the number of output neurons of the floating environment data prediction model to be trained is 1, the number of hidden layer nodes is 5, and the learning rate is 0.15, and wherein the neural network time series model is formed by adding time series parameters on the basis of the neural network model.
4. A method of float control for an underwater survey system, comprising:
forecasting by using a floating environment data forecasting model obtained by training according to any one of claims 1 to 3 to obtain forecasting floating environment data;
establishing a floating energy consumption optimization model by utilizing the predicted floating environment data;
obtaining predicted energy consumption data in the floating process of the underwater surveying system based on the floating energy consumption optimization model, wherein the predicted energy consumption data is represented as total energy consumption of the underwater surveying system for the next floating movement;
obtaining optimized floating data of the underwater surveying system by using a floating energy consumption optimization calculation method based on the predicted energy consumption data;
and controlling the underwater surveying system to do floating motion based on the optimized floating data.
5. The method of claim 4, wherein said using said predicted buoyant environment data to create a buoyant energy consumption optimization model comprises:
performing piecewise fitting on the predicted floating environment data based on a piecewise fitting strategy to obtain a temperature fitting function and a density fitting function;
establishing a motion mathematical model of the underwater surveying system based on the relation between the stress condition of the underwater surveying system and the motion speed and the motion depth, wherein the motion depth is determined by the current oil discharge amount of the underwater surveying system;
and obtaining the floating energy consumption optimization model by utilizing the temperature fitting function, the density fitting function and the motion mathematical model based on an energy consumption optimization strategy.
6. The method of claim 4, wherein obtaining optimized float data for the underwater survey system using a float energy consumption optimization calculation method based on the predicted energy consumption data comprises:
initializing a population by taking the predicted energy consumption data as an objective function and taking the total oil discharge amount of the upward movement in the section of finishing one time of the underwater surveying system and a preset upward speed threshold value as constraint conditions, wherein the total oil discharge amount is determined by the total distance of the upward movement in the section of finishing one time of the underwater surveying system;
iterating the following operations based on a group voting method until the iteration times reach a preset iteration time:
inputting the initialized population into the floating energy consumption optimization model to obtain the predicted total energy consumption of a plurality of individuals;
performing variation processing and cross processing on the initialized population to update the population to obtain an initially updated population;
inputting the initially updated population into the floating energy consumption optimization model to obtain total updated energy consumption of individuals in the initially updated population;
and screening the population based on the population voting method to obtain an optimized individual with the optimized floating data.
7. The method of claim 4, wherein the predicted ascent environment data comprises predicted temperature data and predicted density data of water for a next ascent motion by the underwater survey system.
8. The method of claim 4, wherein the optimized float data includes an optimized number of oil discharges for the next float motion performed by the underwater survey system, an optimized oil discharge per discharge, and an optimized float speed threshold during float of the underwater survey system.
9. The method of claim 6, wherein the initialized population comprises a plurality of randomly generated individuals with random oil drain times, random oil drains, and random speed threshold information.
10. An electronic device, comprising:
one or more processors; and
a memory configured to store one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244196.8A CN115946820A (en) | 2023-03-15 | 2023-03-15 | Training method of floating environment data prediction model, floating control method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244196.8A CN115946820A (en) | 2023-03-15 | 2023-03-15 | Training method of floating environment data prediction model, floating control method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115946820A true CN115946820A (en) | 2023-04-11 |
Family
ID=87288003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310244196.8A Pending CN115946820A (en) | 2023-03-15 | 2023-03-15 | Training method of floating environment data prediction model, floating control method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115946820A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180247362A1 (en) * | 2017-02-24 | 2018-08-30 | Sap Se | Optimized recommendation engine |
| CN112232565A (en) * | 2020-10-15 | 2021-01-15 | 武汉科技大学 | Two-stage time sequence prediction method, prediction system, terminal and medium |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN114706144A (en) * | 2022-02-24 | 2022-07-05 | 南方海洋科学与工程广东省实验室(湛江) | Marine environment forecasting method, device, system and storage medium |
| CA3177585A1 (en) * | 2021-04-16 | 2022-10-16 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
| CN115238937A (en) * | 2021-04-22 | 2022-10-25 | 中国科学院沈阳自动化研究所 | Ocean temperature salt prediction method and system |
-
2023
- 2023-03-15 CN CN202310244196.8A patent/CN115946820A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180247362A1 (en) * | 2017-02-24 | 2018-08-30 | Sap Se | Optimized recommendation engine |
| CN112232565A (en) * | 2020-10-15 | 2021-01-15 | 武汉科技大学 | Two-stage time sequence prediction method, prediction system, terminal and medium |
| CA3177585A1 (en) * | 2021-04-16 | 2022-10-16 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
| CN115238937A (en) * | 2021-04-22 | 2022-10-25 | 中国科学院沈阳自动化研究所 | Ocean temperature salt prediction method and system |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN114706144A (en) * | 2022-02-24 | 2022-07-05 | 南方海洋科学与工程广东省实验室(湛江) | Marine environment forecasting method, device, system and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘明聪: "深海自持式智能浮标能耗分析及优化", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
| 张桐: "基于Argo数据的海洋温度预测方法研究", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11036211B2 (en) | Orchestration of learning and execution of model predictive control tool for manufacturing processes | |
| US20210089910A1 (en) | Reinforcement learning using meta-learned intrinsic rewards | |
| CN114519311A (en) | Prediction method, system, storage medium and application of total harbor basin wave effective wave height | |
| Quéau et al. | Artificial neural network development for stress analysis of steel catenary risers: sensitivity study and approximation of static stress range | |
| CN116432820A (en) | Flood inundation evolution prediction and early warning method and system | |
| CN111044926A (en) | Method for predicting service life of proton exchange membrane fuel cell | |
| Li et al. | Study on the forecasting models of slope stability under data mining | |
| Wen et al. | Lake level dynamics exploration using deep learning, artificial neural network, and multiple linear regression techniques | |
| CN114580309B (en) | Drift speed prediction method, drift speed prediction device, calculation equipment and storage medium | |
| CN116595356A (en) | Time sequence signal prediction method and device, electronic equipment and storage medium | |
| CN116971765A (en) | System and method for predicting and controlling hydrocarbon reservoir pressure | |
| CN115946820A (en) | Training method of floating environment data prediction model, floating control method and equipment | |
| Kazeminezhad et al. | An alternative approach for investigation of the wave-induced scour around pipelines | |
| CN117875504A (en) | Dam break prediction and model training method and device, electronic equipment and storage medium | |
| WO2023170034A1 (en) | System and method for predicting corrosion rate in a pipe section | |
| CN117113798A (en) | Drift velocity prediction method, device, equipment and storage medium for floating object | |
| Lu et al. | Motion estimation and system identification of a moored buoy via physics-informed neural network | |
| Sagdatullin et al. | Development of a cyber-physical subsystem for support and decision making of managing oil production and transportation processes under uncertainty conditions | |
| JPWO2019106726A1 (en) | Measurement control program, measurement control method, and measurement control device | |
| Verma et al. | Optimal operation of the multi-reservoir system: a comparative study of robust metaheuristic algorithms | |
| Gao et al. | Real-time prediction of fish cage behaviors under varying currents using deep neural network | |
| Eskilsson et al. | Hierarchical approaches to train recurrent neural networks for wave-body interaction problems | |
| CN114718525B (en) | Pumping unit control method, computer equipment and storage medium | |
| CN117575109B (en) | Method and device for predicting underground station personnel capacity in flood scene | |
| US20240126812A1 (en) | Fast exploration and learning of latent graph models |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230411 |
|
| RJ01 | Rejection of invention patent application after publication |