CN117390895B - Semi-submersible ship ballast system simulation method, device and storage medium - Google Patents
Semi-submersible ship ballast system simulation method, device and storage medium Download PDFInfo
- Publication number
- CN117390895B CN117390895B CN202311675587.1A CN202311675587A CN117390895B CN 117390895 B CN117390895 B CN 117390895B CN 202311675587 A CN202311675587 A CN 202311675587A CN 117390895 B CN117390895 B CN 117390895B
- Authority
- CN
- China
- Prior art keywords
- data
- ballast
- value
- ballast tank
- simulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 49
- 238000005259 measurement Methods 0.000 claims description 42
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000007613 environmental effect Effects 0.000 claims description 24
- 238000009499 grossing Methods 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 73
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 230000000737 periodic effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 239000013535 sea water Substances 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
- G09B9/02—Simulators for teaching or training purposes for teaching control of vehicles or other craft
- G09B9/06—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of ships, boats, or other waterborne vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Business, Economics & Management (AREA)
- Educational Technology (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a semi-submersible ship ballast system simulation method, a semi-submersible ship ballast system simulation device and a storage medium. The method comprises the steps of carrying out period division on the shaking period of a ship caused by the surge according to collected data, carrying out fitting by utilizing the complete data of one period, carrying out prediction on the data of the next period according to a curve obtained by fitting, simultaneously utilizing the characteristic that the data has periodicity, obtaining a second group of prediction data by utilizing a Holt-Winters method, calculating the difference between the two prediction data, and adjusting the weight of an expression term of a fitting curve according to different differences by combining the physical quantity and the weight range corresponding to the obtained fitting curve term, so that the fitting curve is more attached to the actual data, more accurate data prediction is realized, the simulation result is closer to the actual situation, and the training of a semi-submersible senior shipman through a simulation system is facilitated, and the training effect is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of simulation systems, in particular to a semi-submersible ship ballast system simulation method, a semi-submersible ship ballast system simulation device and a storage medium.
Background
Semi-submersible vessels are a special way of designing vessels, unlike general surface vessels, which generally have a deeper draft, but are not completely submerged like submarines, but have parts of their hull or structure exposed to the outside of the surface. Because the volume proportion of the semi-submersible vessel which is submerged in the water is high, the semi-submersible vessel is not easily influenced by waves on the sea surface, can keep better stability and is suitable for being used as a working platform on the water.
In the loading of large cargo, it is necessary to rapidly complete ballasting due to the influence of the marine environment, particularly wind and tide, and to fill the ballast tank with seawater. In some cases, the heights of the decks on the two sides also need to be adjusted by ballasting, and the large cargo is fixed in place by utilizing the inclination in cooperation with a winch. Rapid control and deployment of the ballast system is a requisite skill for the senior crewman of the semi-submersible vessel.
Currently, training of a semi-submersible ballast system is generally performed by using a ballast simulation system of a common ship. The simulation system is provided with a plurality of controls which are matched with the actual ship ballast system, and the personnel participating in training can learn the ballast system by controlling the controls. The existing semi-submersible ship ballast simulation system usually only pays attention to the design of operation control, and the simulation of the display result after operation is fed back only through the measurement and calculation of a simple ballast pump flow list. And cannot give a proper feedback result according to various circumstances. The semi-submersible vessel ballast needs to be quickly responded and adjusted, and an operator needs to flexibly control and adjust according to a correct feedback result, but the existing simulation system cannot meet the requirements.
Disclosure of Invention
The embodiment of the invention provides a semi-submersible ship ballast system simulation method, a device and a storage medium, which are used for solving the technical problem that a feedback result of a semi-submersible ship ballast simulation system to a ballast system simulation operation is simply distorted in the prior art.
In a first aspect, an embodiment of the present invention provides a method for simulating a ballast system of a semi-submersible vessel, including:
determining a collection period according to the shaking change of the ship body, and collecting environmental parameters and ballast control parameters of one collection period in the actual ballasting process of the semi-submersible, wherein the environmental parameters comprise: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data;
creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method;
calculating a predicted sequence of the next period by using a ballast tank measured value time one-dimensional function after fitting and solving;
carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation;
Comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by over fitting;
receiving simulation environment parameters and simulation ballast control parameters which are input in a simulation system, generating simulation data by using a corrected ballast tank measured value time one-dimensional function based on the simulation environment parameters and the simulation ballast control parameters, and displaying the simulation data by adopting a display control. In a second aspect, an embodiment of the present invention further provides a device for simulating a ballast system of a semi-submersible vessel, including:
the acquisition module is used for determining an acquisition period according to the shaking change of the ship body and acquiring an environmental parameter and a ballast control parameter of one acquisition period in the actual ballasting process of the semi-submersible ship, wherein the environmental parameter comprises: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data;
the ballast tank measuring value time one-dimensional function is fitted and solved by utilizing a least square method;
The calculation module is used for calculating a predicted sequence of the next period by using a one-dimensional function of the ballast tank measured value time after fitting and solving;
the utilization module is used for carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation;
the adjustment module is used for comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so that the prediction error caused by the over fitting is avoided;
the display module is used for receiving the simulation environment parameters and the simulation ballast control parameters which are input in the simulation system, generating simulation data by utilizing the corrected ballast tank measured value time one-dimensional function based on the simulation environment parameters and the simulation ballast control parameters, and displaying the simulation data by adopting a display control.
In a third aspect, embodiments of the present invention also provide a storage medium containing computer executable instructions which, when executed by a computer processor, are used to perform a semi-submersible vessel ballast system simulation method as provided by the above embodiments.
According to the simulation method, the simulation device and the storage medium for the semi-submersible vessel ballast system, provided by the embodiment of the invention, the environment parameters and the ballast control parameters of one acquisition period in the actual ballast process of the semi-submersible vessel are acquired by determining the acquisition period according to the shaking change of the hull, wherein the environment parameters comprise: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data; creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method; calculating a predicted sequence of the next period by using a ballast tank measured value time one-dimensional function after fitting and solving; carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation; comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by over fitting; and receiving the selected environmental parameters in the simulation system, generating simulation data according to the corrected ballast tank measured value time one-dimensional function based on the environmental parameters, and displaying the simulation data by adopting a display control. The method comprises the steps of carrying out period division on the shaking period of a ship caused by the surge according to collected data, carrying out fitting by utilizing the complete data of one period, carrying out prediction on the data of the next period according to a curve obtained by fitting, simultaneously utilizing the characteristic that the data has periodicity, obtaining a second group of prediction data by utilizing a Holt-Winters method, calculating the difference between the two, collecting the physical quantity and the weight range corresponding to the fitting curve sub-term actually obtained according to different differences, adjusting the weight of the expression sub-term of the fitting curve, enabling the fitting curve to be more attached to the actual data, realizing more accurate data prediction, displaying a prediction result through a display control, enabling the simulation result to be more close to the actual situation, facilitating training of a semi-submersible advanced shipman through a simulation system, and improving the training effect.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method for simulating a ballast system of a semi-submersible vessel according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for simulating a ballast system of a semi-submersible vessel according to a second embodiment of the present invention;
fig. 3 is a structural diagram of a semi-submersible vessel ballast system simulation apparatus provided in a third embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a semi-submersible vessel ballast system simulation method according to an embodiment of the present invention, where the method may be applied to a situation of performing simulation on a semi-submersible vessel ballast system simulation, and the method may be performed by a vehicle body impact welding production device, and specifically includes the following steps:
and 110, determining a collection period according to the ship body shaking change, and collecting environmental parameters and ballast control parameters of one collection period in the actual ballasting process of the semi-submersible.
In this embodiment, various data may be collected from the actual situation of the semi-submersible vessel when the actual ballasting is performed, and the various data may include: the water level data measured by the bottom pressure sensors arranged in each ballast compartment, the opening degree of the valve for controlling the water inlet of the ballast compartment, and the external environment parameters at that time, such as: wind force, wind direction, tidal flow rate of sea water, etc., and measured angle changes of ship roll and forward tilt, etc. In particular environmental parameters and ballast control parameters, said environmental parameters comprising: the ship transverse shaking angle and the ship longitudinal shaking angle.
In the ballast process, the semi-submersible vessel is slightly swayed due to the influence of tide and sea surface surge, so that the seawater in the ballast tank is swayed, the value measured by the bottom pressure sensor fluctuates around the actual water level value, and the fluctuation is also periodically changed due to the periodicity of the sea surface surge. Thus, complete data for at least one cycle needs to be acquired. In this embodiment, the cycle time may be determined according to the collected ship shake data, so as to obtain complete data in the cycle, and in addition, the cycle time under different sea conditions may be predicted according to weather and sea conditions.
And 120, creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method.
The least square method is a formula method in a matrix form for solving linear fitting parameters by adopting a square loss function under linear regression. From the above disclosure, it can be seen that the measured value of ballast water for each compartment is made up of a number of factors and is substantially linear. The fitting prediction method is suitable for the linear least square method. The linear least square has a closed solution, can be solved by a least square method, and can also be solved by an iteration method (such as gradient descent).
And 130, calculating a predicted sequence of the next period by using a one-dimensional function of the ballast tank measured value time after fitting and solving.
Since the time one-dimensional function of the ballast tank measured value obtained by fitting is a function taking time as a variable, the time one-dimensional adjustment can be used for predicting to obtain a sequence of the time change of the ballast tank measured value of the next period.
And 140, carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a predicted check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation.
Because the data volume of one period is smaller, the fitting phenomenon is easy to occur in the fitting process by adopting a least square method, and larger errors can be generated in the prediction process, so that the ballast tank measured value time one-dimensional function obtained by fitting the data volume is required to be corrected, and an accurate prediction result is obtained. In this embodiment, the measurement data of the ballast water in the tank may be predicted in another manner, and the one-dimensional function of the ballast tank measurement value time obtained by fitting may be corrected based on the prediction result. In this embodiment, according to the characteristic that the data has periodicity, the Holt-windows algorithm may be adopted to perform three exponential smoothing calculations. The Holt-windows method is a time series analysis and prediction method. The method is applicable to non-stationary sequences containing linear trends and periodic fluctuations, and model parameters are continuously adapted to the changes of the non-stationary sequences by using an exponential smoothing method (EMA) and short-term forecast of future trends is carried out. In the present practiceIn the embodiment, taking the periodic factor into consideration, an addition model is mainly employed, that is, assuming that the trend component of the time series is in addition to the seasonal component, in which the trend component linearly increases (or decreases) with time, the seasonal component being the time component of the periodic component. In practice, the linear increment speed and time of the trend component are only relatively fixed in a short term due to the non-stationarity of the time sequence, and can be changed slowly in a long term. In addition, irregular noise components may be contained in the time series. Therefore, it is necessary to use an exponential smoothing method (EMA) to time-sequence values based on actual observed values The trend component and the season component in the model are continuously calibrated. The three parameters in the Holt-windows algorithm are obtained by utilizing the preset three equations to respectively cover the level, the trend and the periodic composition and the solution, and the three parameters are utilized
The prediction is performed and a prediction sequence of the next cycle is obtained, which in this embodiment may be used as a prediction check sequence.
And 150, comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by the over fitting.
After the predicted check sequence is obtained, it can be compared with the predicted sequence obtained by the ballast tank measurement time one-dimensional function. And adjusting the weight value of each one-dimensional influence factor in the ballast tank measured value time one-dimensional function according to the comparison result. In this embodiment, since the overfitting is generally caused by that the weight value of each influence factor exceeds a reasonable range, in this embodiment, when it is determined that a certain deviation exists between the two predicted results, it is determined that a problem exists in the weight value of each influence factor in the ballast tank measured value time one-dimensional function, and therefore, the adjustment is required to obtain a more accurate ballast tank measured value time one-dimensional function, and the purpose of accurate prediction can be achieved by using the ballast tank measured value time one-dimensional function after each sub-weight value is adjusted.
Step 160, receiving the simulated environment parameters and the simulated ballast control parameters which are input in the simulation system, generating simulated data by using the corrected ballast tank measured value time one-dimensional function based on the simulated environment parameters and the simulated ballast control parameters, and displaying the simulated data by adopting a display control.
After obtaining a more accurate ballast tank measurement value time one-dimensional function, training personnel can input corresponding simulated environment parameters on a man-machine interaction interface of simulation software, substitute the ballast tank measurement value time one-dimensional function into the input environment parameters, generate corresponding simulated ballast tank measurement simulation values, generate corresponding sequences according to time, and display sequence data according to time dimension by utilizing display control. The accurate simulation of the semi-submersible ballast system is realized.
According to the embodiment, various data adopted by actual ballasting under different environments are collected, one collection period can be determined according to the change degree of wind current and surge, and the data of one collection period can be completely collected; creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method; calculating a predicted sequence of the next period by using a ballast tank measured value time one-dimensional function after fitting and solving; carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation; comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by over fitting; and receiving the selected environmental parameters in the simulation system, generating simulation data according to the corrected ballast tank measured value time one-dimensional function based on the environmental parameters, and displaying the simulation data by adopting a display control. The method comprises the steps of carrying out period division on the shaking period of a ship caused by the surge according to collected data, carrying out fitting by utilizing the complete data of one period, carrying out prediction on the data of the next period according to a curve obtained by fitting, simultaneously utilizing the characteristic that the data has periodicity, obtaining a second group of prediction data by utilizing a Holt-Winters method, calculating the difference between the two, collecting the physical quantity and the weight range corresponding to the fitting curve sub-term actually obtained according to different differences, adjusting the weight of the expression sub-term of the fitting curve, enabling the fitting curve to be more attached to the actual data, realizing more accurate data prediction, displaying a prediction result through a display control, enabling the simulation result to be more close to the actual situation, facilitating training of a semi-submersible advanced shipman through a simulation system, and improving the training effect.
Example two
Fig. 2 is a flow chart of a simulation method of a ballast system of a semi-submersible vessel according to a second embodiment of the present invention, wherein the optimization is performed based on the above embodiment, and in this embodiment, the ballast tank measurement time one-dimensional function may be defined as:where f (x) is the ballast tank measurement, x is the time variable,(x) As m-th one-dimensional influence factor function, +.>A weight value of the function of the m-th one-dimensional influence factor; correspondingly, the method can further comprise the following steps: establishing an initial matrix according to the ballast tank measurement data, the ballast tank valve opening degree data, the ship transverse shaking angle and the ship longitudinal shaking angle of one acquisition period, wherein each column is one type of sequence data; wherein each column is one type of sequence data; carrying out dimensionless treatment on the sequence data of each column to obtain a dimensionless matrix; calculating the difference value between the first row and other rows of the dimensionless matrix to generate an absolute difference matrix; searching the maximum value and the minimum value in the absolute difference matrix, and calculating each element in the absolute difference matrix based on the maximum value and the minimum valueGenerating an association coefficient matrix by the association coefficients of the elements; and calculating the weight range of each data according to the association coefficient.
Referring to fig. 2, the semi-submersible vessel ballast system simulation method includes:
step 210, determining a collection period according to the hull shaking change, and collecting environmental parameters and ballast control parameters of one collection period in the actual ballasting process of the semi-submersible.
And 220, creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method.
Accordingly, the ballast tank measurement time one-dimensional function may be defined as:wherein x is a time variable,
(x) As m-th one-dimensional influence factor function, +.>The weight value of the function of the m-th one-dimensional influence factor. f (x) is a ballast tank measurement.
Step 230, establishing an initial matrix according to the ballast tank measurement data, the ballast tank valve opening degree data, the ship transverse shaking angle and the ship longitudinal shaking angle of the one acquisition period, wherein each column is one type of sequence data.
In this embodiment, since the ballast tank measurement time one-dimensional function is a linear expression that is commonly affected by a plurality of factors, each term corresponds to an influence factor. Therefore, the physical quantity and the weight range specifically corresponding to each influence factor need to be judged, so that the influence factors which are over-fitted in the ballast tank measured value time one-dimensional function are judged when over-fitting is performed, and the corresponding weights are adjusted, so that the over-fitting phenomenon is avoided. Thus, it is first necessary to determine possible influencing factors. Optionally, an initial matrix may be established according to the data acquired in the first acquisition period; each column being one type of sequence data.
Step 240, performing dimensionless processing on the sequence data of each column to obtain a dimensionless matrix, and calculating the difference between the first row and the other rows of the dimensionless matrix to generate an absolute difference matrix.
Since the index raw data of each column has different dimensions and lacks comparability, it is necessary to make the data dimensionless. Alternatively, the sequence data may be subjected to dimensionless processing by using a range transformation method, specifically:
for the dimensionless result of the ith data in the jth type,/for example>For the ith data in the jth type, < +.>Maximum value of j-th type data, +.>Minimum value of j-th type data.
The non-dimensionalization is carried out by the mode, and a non-dimensionalization matrix is obtained,
；
。
step 250, searching for a maximum value and a minimum value in the absolute difference matrix, calculating an association coefficient of each element in the absolute difference matrix based on the maximum value and the minimum value, generating an association coefficient matrix, and calculating a weight range of each data according to the association coefficient.
The absolute value of the difference between the first row and the remaining rows of the absolute difference matrix may be calculated to form the absolute difference matrix.
By way of example, the calculation may be referred to as follows:
the maximum value and the minimum value are respectively the maximum value and the minimum value in the absolute value difference matrix.
Calculating a correlation coefficient, and performing the following transformation on the data in the absolute difference matrix:
obtaining a correlation coefficient matrix:
wherein, delta (min) is the minimum value, delta (max) is the maximum value,and p is a resolution coefficient, wherein the p is an element corresponding to the j-th row of the ith column in the correlation coefficient matrix.
The resolution coefficient ρ may be empirically set, typically smaller representing the difference between the correlation coefficients.
The correlation coefficient is calculated by:
wherein r is i For the correlation coefficient of the ith column of the correlation coefficient matrix, < >>And n is the total number of columns of the correlation coefficient matrix, wherein n is the element of the ith column in the correlation coefficient matrix.
And determining the corresponding relation of each type of data in the ballast tank measurement value time one-dimensional function according to the attribute of each column of the associated element and the size of the associated coefficient, namely, the linear expression of strong association is in front, and sequencing according to the size to obtain the ballast tank measurement value time one-dimensional function corresponding to each type of data. And the weight value range corresponding to each type of data can be determined according to the size of the association coefficient of each column, and then each type of data determines the corresponding one-dimensional influence factor in the ballast tank measured value time one-dimensional function.
And 260, calculating a predicted sequence of the next period by using the ballast tank measured value time one-dimensional function after fitting and solving.
And 270, carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a predicted check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation.
And 280, comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by the over fitting.
In this embodiment, the weight value of each sub-term may be adjusted according to different situations, so as to avoid the occurrence of an overfitting situation.
For example, when the difference value is greater than a preset difference value threshold value, the correcting the weight value in the ballast tank measurement value time one-dimensional function after the fitting and solving may include: when the difference value is the integral difference value, acquiring at least two acquisition cycle data of other ballast compartments; judging whether the integral difference value between the data of the second acquisition period and the data of the first acquisition period of the other ballast compartments is smaller than a preset integral difference value threshold; and when the flow weight value of the ballast valve is smaller than a preset integral difference value threshold, increasing the flow weight value of the ballast valve, otherwise, acquiring the ship body inclination angle change sequence data in the two acquisition periods, and setting a corresponding weight range for the weight in the ballast tank measured value time one-dimensional function after fitting and solving according to the inclination angle change sequence data.
In this embodiment, the overall difference value is a predicted sequence curve of the next period obtained by calculating a ballast tank measurement value time one-dimensional function after fitting and solving, and the overall difference value is a predicted check sequence curve of the next period obtained by Holt-windows calculated by using a three-time exponential smoothing curve, and the shape of the predicted check sequence curve is similar, so that the weight of the core element of the predicted check sequence curve is judged to be problematic, and therefore, the flow weight value of the ballast valve can be increased. So that the two curves are closer.
In another case, because the water injected into different ballast tanks is different, the whole ship body tilts, and in this case, the whole difference value is generated, so that at least two acquisition cycle data of the ballast tanks need to be acquired, whether the micro-tilting occurs is determined according to the at least two acquisition cycle data of other ballast tanks, and when the micro-tilting is determined, the weight value of the tilting angle of the ship body can be correspondingly adjusted. Optionally, a weight value corresponding to the change of the inclination angle of the ship body can be added, and a corresponding weight value range is set according to the corresponding relationship between the inclination angle of the ship body and time during loading or unloading.
Furthermore, it may further comprise: calculating a surge integral influence based on the ballast tank measurement value, the ballast tank body height value, the ship transverse sway angle and the ship longitudinal sway angle; and when the variance value is larger than a preset variance threshold, adjusting the influence weight value of the surge integral. In this embodiment, the variance represents an error in the extremum of the sequence, and as the ballast water increases, the water in the ballast tank gradually decreases with the amplitude of the hull sway, and thus it can be regarded as an integral problem. The influence trend gradually approaches 0 from 1, so that the weight of the ballast water can be adjusted according to the ballast water quantity corresponding to different time periods.
Step 290, receiving the simulated environment parameters and the simulated ballast control parameters input in the simulation system, generating simulated data by using the corrected ballast tank measured value time one-dimensional function based on the simulated environment parameters and the simulated ballast control parameters, and displaying the simulated data by adopting a display control.
The present embodiment is implemented by defining the ballast tank measurement time one-dimensional function as:wherein x is a time variable,
(x) As m-th one-dimensional influence factor function, +.>The weight value of the function of the m-th one-dimensional influence factor. Correspondingly, the method can further comprise the following steps: establishing an initial matrix according to the ballast tank measurement data, ballast tank valve opening degree change data, ship transverse shaking angle data and ship longitudinal shaking angle data of the whole period; wherein each column is one type of sequence data; carrying out dimensionless treatment on the sequence data of each column to obtain a dimensionless matrix; calculating the difference value between the first row and other rows of the dimensionless matrix to generate an absolute difference matrix; searching a maximum value and a minimum value in the absolute difference matrix, and calculating an association coefficient of each element in the absolute difference matrix based on the maximum value and the minimum value to generate an association coefficient matrix; and calculating the weight range of each data according to the association coefficient. Each influence factor and corresponding weight range in the ballast tank measurement value time one-dimensional function can be determined, after the factors are determined, the corresponding influence factors can be determined according to the difference relation between the fitted data sequences, and corresponding weight values can be correspondingly adjusted in the obtained weight ranges. Each influence factor and the corresponding weight range can be determined, and the weights of the corresponding influence factors can be adjusted according to different differences, so that the accuracy of prediction is further improved.
Example III
Fig. 3 is a schematic structural diagram of a semi-submersible vessel ballast system simulation apparatus according to a third embodiment of the present invention, as shown in fig. 3, the apparatus includes:
the acquisition module 310 is configured to determine an acquisition period according to a hull shake change, and acquire an environmental parameter and a ballast control parameter of one acquisition period in an actual ballasting process of the semi-submersible, where the environmental parameter includes: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data;
the creating module 320 is configured to create a ballast tank measurement time one-dimensional function, and perform fitting solution on the ballast tank measurement time one-dimensional function by using data acquired in one acquisition period and using a least square method;
a calculation module 330, configured to calculate a predicted sequence of the next period by using a one-dimensional function of the ballast tank measurement value time after the fitting solution;
the utilization module 340 is configured to perform three times of exponential smoothing calculation according to data acquired in an acquisition period by utilizing a Holt-windows algorithm, and obtain a prediction check sequence of a next period by utilizing the Holt-windows after the three times of exponential smoothing calculation;
the adjustment module 350 is configured to compare the predicted sequence of the next cycle with the predicted check sequence of the next cycle, and correct the weight value in the ballast tank measurement time one-dimensional function after the fitting solution when the difference is greater than a preset difference threshold, so as to avoid a prediction error caused by over-fitting;
The display module 360 is configured to receive the environmental parameter selected in the simulation system, generate simulation data according to the corrected ballast tank measurement time one-dimensional function based on the environmental parameter, and display the simulation data with a display control.
According to the semi-submersible vessel ballast system simulation device provided by the embodiment, the acquisition period is determined according to the shaking change of the hull, and the environmental parameters and the ballast control parameters of one acquisition period in the actual ballast process of the semi-submersible vessel are acquired, wherein the environmental parameters comprise: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data; creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method; calculating a predicted sequence of the next period by using a ballast tank measured value time one-dimensional function after fitting and solving; carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation; comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by over fitting; and receiving the selected environmental parameters in the simulation system, generating simulation data according to the corrected ballast tank measured value time one-dimensional function based on the environmental parameters, and displaying the simulation data by adopting a display control. The method comprises the steps of carrying out period division on the shaking period of a ship caused by the surge according to collected data, carrying out fitting by utilizing the complete data of one period, carrying out prediction on the data of the next period according to a curve obtained by fitting, simultaneously utilizing the characteristic that the data has periodicity, obtaining a second group of prediction data by utilizing a Holt-Winters method, calculating the difference between the two, collecting the physical quantity and the weight range corresponding to the fitting curve sub-term actually obtained according to different differences, adjusting the weight of the expression sub-term of the fitting curve, enabling the fitting curve to be more attached to the actual data, realizing more accurate data prediction, displaying a prediction result through a display control, enabling the simulation result to be more close to the actual situation, facilitating training of a semi-submersible advanced shipman through a simulation system, and improving the training effect.
On the basis of the embodiment, the ballast tank measurement time one-dimensional function is:wherein x is a time variable,
(x) As a function of the m-th one-dimensional influence factor,/>the weight value of the function of the m-th one-dimensional influence factor.
On the basis of the above embodiment, the apparatus further includes:
the initial matrix building module is used for building an initial matrix according to the ballast tank measurement data, the ballast tank valve opening degree data, the ship transverse shaking angle and the ship longitudinal shaking angle of one acquisition period, wherein each column is one type of sequence data;
the dimensionless processing module is used for carrying out dimensionless processing on the sequence data of each column to obtain a dimensionless matrix;
the absolute difference matrix generation module is used for calculating the difference value between the first row and the other rows of the dimensionless matrix to generate an absolute difference matrix;
the searching module is used for searching the maximum value and the minimum value in the absolute difference matrix, calculating the association coefficient of each element in the absolute difference matrix based on the maximum value and the minimum value and generating an association coefficient matrix;
and the weight range calculation module is used for calculating the weight range of each data according to the association coefficient.
On the basis of the above embodiment, the adjusting module includes:
the increasing unit is used for acquiring at least two acquisition cycle data of other ballast compartments when the difference value is an integral difference value; judging whether the integral difference value between the data of the second acquisition period and the data of the first acquisition period of the other ballast compartments is smaller than a preset integral difference value threshold; when the flow weight value is smaller than a preset integral difference threshold value, increasing the flow weight value of the opening degree of the ballast tank valve;
and the correction unit is used for acquiring the ship body inclination angle change sequence data in the at least two acquisition periods, and correcting the ship body inclination angle weight in the ballast tank measured value time one-dimensional function after fitting and solving according to the inclination angle change sequence data.
On the basis of the above embodiment, the correction unit is configured to:
and adding a weight value corresponding to the change of the inclination angle of the ship body, and setting a corresponding weight value range according to the corresponding relationship between the inclination angle of the ship body and time during loading or unloading.
On the basis of the foregoing embodiment, the adjustment module further includes:
the calculating unit is used for calculating the surge integral influence based on the ballast tank measured value, the ballast tank height value, the ship transverse shaking angle and the ship longitudinal shaking angle;
And the adjusting unit is used for adjusting the weight value of the influence of the surge integration when the variance value is larger than a preset variance threshold value.
The semi-submersible vessel ballast system simulation device provided by the embodiment of the invention can execute the semi-submersible vessel ballast system simulation method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
A fourth embodiment of the invention also provides a storage medium containing computer executable instructions which, when executed by a computer processor, are used to perform a semi-submersible vessel ballast system simulation method as provided in any of the above embodiments.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, 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), an optical fiber, 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 this document, 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.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. A method of simulating a semi-submersible ballast system, comprising:
determining a collection period according to the shaking change of the ship body, and collecting environmental parameters and ballast control parameters of one collection period in the actual ballasting process of the semi-submersible, wherein the environmental parameters comprise: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data;
creating a ballast tank measured value time one-dimensional function, and carrying out fitting solution on the ballast tank measured value time one-dimensional function by utilizing data acquired in one acquisition period and utilizing a least square method;
Calculating a predicted sequence of the next period by using a ballast tank measured value time one-dimensional function after fitting and solving;
carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation;
comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so as to avoid the prediction error caused by over fitting;
receiving simulation environment parameters and simulation ballast control parameters which are input in a simulation system, generating simulation data by using a corrected ballast tank measured value time one-dimensional function based on the simulation environment parameters and the simulation ballast control parameters, and displaying the simulation data by adopting a display control.
2. The method of claim 1 wherein the ballast tank measurement time one-dimensional function isWherein x is a time variable, +.>(x) As m-th one-dimensional influence factor function, +.>The weight value of the function of the m-th one-dimensional influence factor.
3. The method according to claim 2, wherein the method further comprises:
establishing an initial matrix according to the ballast tank measurement data, the ballast tank valve opening degree data, the ship transverse shaking angle and the ship longitudinal shaking angle of one acquisition period, wherein each column is one type of sequence data;
carrying out dimensionless treatment on the sequence data of each column to obtain a dimensionless matrix;
calculating the difference value between the first row and other rows of the dimensionless matrix to generate an absolute difference matrix;
searching a maximum value and a minimum value in the absolute difference matrix, and calculating an association coefficient of each element in the absolute difference matrix based on the maximum value and the minimum value to generate an association coefficient matrix;
and calculating the weight range of each data according to the association coefficient.
4. A method according to claim 3, wherein correcting the weight value in the one-dimensional function of ballast tank measurement time after the fitting solution when the difference is greater than a preset difference threshold comprises:
when the difference value is the integral difference value, acquiring at least two acquisition cycle data of other ballast compartments;
judging whether the integral difference value between the data of the second acquisition period and the data of the first acquisition period of the other ballast compartments is smaller than a preset integral difference value threshold;
When the flow weight value is smaller than a preset integral difference threshold value, increasing the flow weight value of the opening degree of the ballast tank valve; otherwise
And acquiring the ship body inclination angle change sequence data in the at least two acquisition periods, and correcting the ship body inclination angle weight in the ballast tank measured value time one-dimensional function after fitting and solving according to the inclination angle change sequence data.
5. The method of claim 4, wherein correcting hull inclination angle weights in a one-dimensional function of ballast tank measurement time fitted to the solution based on the inclination angle variation sequence data comprises:
and adding a weight value corresponding to the change of the inclination angle of the ship body, and setting a corresponding weight value range according to the corresponding relationship between the inclination angle of the ship body and time during loading or unloading.
6. The method of claim 4, wherein correcting the weight value in the one-dimensional function of ballast tank measurement time after the fitting solution when the difference is greater than a preset difference threshold comprises:
calculating a surge integral influence based on the ballast tank measurement value, the ballast tank body height value, the ship transverse sway angle and the ship longitudinal sway angle;
And when the variance value is larger than a preset variance threshold, adjusting the weight value of the influence of the surge integration.
7. A semi-submersible ballast system simulation apparatus, comprising:
the acquisition module is used for determining an acquisition period according to the shaking change of the ship body and acquiring an environmental parameter and a ballast control parameter of one acquisition period in the actual ballasting process of the semi-submersible ship, wherein the environmental parameter comprises: the ship lateral shaking angle and the ship longitudinal shaking angle, and the ballast control parameters comprise: ballast tank measurement data, ballast tank valve opening data;
the ballast tank measuring value time one-dimensional function is fitted and solved by utilizing a least square method;
the calculation module is used for calculating a predicted sequence of the next period by using a one-dimensional function of the ballast tank measured value time after fitting and solving;
the utilization module is used for carrying out three-time exponential smoothing calculation by utilizing a Holt-windows algorithm according to the data acquired in the acquisition period, and obtaining a prediction check sequence of the next period by utilizing the Holt-windows after the three-time exponential smoothing calculation;
The adjustment module is used for comparing the predicted sequence of the next period with the predicted check sequence of the next period, and correcting the weight value in the ballast tank measured value time one-dimensional function after the fitting solution when the difference value is larger than a preset difference value threshold value, so that the prediction error caused by the over fitting is avoided;
the display module is used for receiving the simulation environment parameters and the simulation ballast control parameters which are input in the simulation system, generating simulation data by utilizing the corrected ballast tank measured value time one-dimensional function based on the simulation environment parameters and the simulation ballast control parameters, and displaying the simulation data by adopting a display control.
8. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the semi-submersible ballast system simulation method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675587.1A CN117390895B (en) | 2023-12-08 | 2023-12-08 | Semi-submersible ship ballast system simulation method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675587.1A CN117390895B (en) | 2023-12-08 | 2023-12-08 | Semi-submersible ship ballast system simulation method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117390895A CN117390895A (en) | 2024-01-12 |
| CN117390895B true CN117390895B (en) | 2024-02-09 |
Family
ID=89437704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311675587.1A Active CN117390895B (en) | 2023-12-08 | 2023-12-08 | Semi-submersible ship ballast system simulation method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117390895B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537379A (en) * | 2018-04-04 | 2018-09-14 | 北京科东电力控制系统有限责任公司 | Adaptive variable weight combination load forecasting method and device |
| CN112105048A (en) * | 2020-07-27 | 2020-12-18 | 北京邮电大学 | Combined prediction method based on double-period Holt-Winters model and SARIMA model |
| CN112488396A (en) * | 2020-12-01 | 2021-03-12 | 国网福建省电力有限公司 | Wavelet transform-based electric power load prediction method of Holt-Winters and LSTM combined model |
| CN113065678A (en) * | 2019-12-13 | 2021-07-02 | 中兴通讯股份有限公司 | Performance index early warning method, device, equipment and storage medium |
| CN114638435A (en) * | 2022-03-29 | 2022-06-17 | 中国船舶重工集团公司第七一一研究所 | Diesel engine security parameter prediction method based on data driving |
| CN114647814A (en) * | 2022-05-23 | 2022-06-21 | 成都理工大学工程技术学院 | Nuclear signal correction method based on prediction model |
| CN114722619A (en) * | 2022-04-20 | 2022-07-08 | 集美大学 | Ship collision danger judgment threshold model construction method and system and storage medium |
| CN114840581A (en) * | 2022-05-20 | 2022-08-02 | 重庆云内核智能科技有限公司 | Method and device for generating dynamic threshold for equipment early warning based on statistical model |
| CN116805785A (en) * | 2023-08-17 | 2023-09-26 | 国网浙江省电力有限公司金华供电公司 | Power load hierarchy time sequence prediction method based on random clustering |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11341374B2 (en) * | 2018-05-29 | 2022-05-24 | Microsoft Technology Licensing, Llc | Data anomaly detection |
| US20210224833A1 (en) * | 2020-01-21 | 2021-07-22 | Oracle International Corporation | Seasonality Prediction Model |
-
2023
- 2023-12-08 CN CN202311675587.1A patent/CN117390895B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537379A (en) * | 2018-04-04 | 2018-09-14 | 北京科东电力控制系统有限责任公司 | Adaptive variable weight combination load forecasting method and device |
| CN113065678A (en) * | 2019-12-13 | 2021-07-02 | 中兴通讯股份有限公司 | Performance index early warning method, device, equipment and storage medium |
| CN112105048A (en) * | 2020-07-27 | 2020-12-18 | 北京邮电大学 | Combined prediction method based on double-period Holt-Winters model and SARIMA model |
| CN112488396A (en) * | 2020-12-01 | 2021-03-12 | 国网福建省电力有限公司 | Wavelet transform-based electric power load prediction method of Holt-Winters and LSTM combined model |
| CN114638435A (en) * | 2022-03-29 | 2022-06-17 | 中国船舶重工集团公司第七一一研究所 | Diesel engine security parameter prediction method based on data driving |
| CN114722619A (en) * | 2022-04-20 | 2022-07-08 | 集美大学 | Ship collision danger judgment threshold model construction method and system and storage medium |
| CN114840581A (en) * | 2022-05-20 | 2022-08-02 | 重庆云内核智能科技有限公司 | Method and device for generating dynamic threshold for equipment early warning based on statistical model |
| CN114647814A (en) * | 2022-05-23 | 2022-06-21 | 成都理工大学工程技术学院 | Nuclear signal correction method based on prediction model |
| CN116805785A (en) * | 2023-08-17 | 2023-09-26 | 国网浙江省电力有限公司金华供电公司 | Power load hierarchy time sequence prediction method based on random clustering |
Non-Patent Citations (3)
| Title |
|---|
| Photovoltaic modules degradation assessment using different statistical techniques;Ahmed Abdelouahed et al.;International Journal of Energy Research;论文全文 * |
| 基于Holt-Winters与最小二乘支持向量机的混合预测模型;刘宝成 等;洛阳理工学院学报（自然科学版）;第27卷(第4期);79-83页 * |
| 基于惩罚最小二乘估计的长期用电量半参数预测模型;邵臻;王晓佳;高飞;刘辉舟;杨露;;统计与决策(第24期);26-28页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117390895A (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944648B (en) | Large ship speed and oil consumption rate prediction method | |
| CN110163433B (en) | Ship flow prediction method | |
| US10769550B2 (en) | Ensemble learning prediction apparatus and method, and non-transitory computer-readable storage medium | |
| US20130204403A1 (en) | Apparatus and Methods for Non-Invasive Closed Loop Step Testing Using a Tunable Trade-Off Factor | |
| CN111199270A (en) | Regional wave height forecasting method and terminal based on deep learning | |
| CN113837493B (en) | Reservoir downstream TDG concentration generation prediction method and device | |
| Wang et al. | Verification and validation of CFD simulations for semi-submersible floating offshore wind turbine under pitch free-decay motion | |
| CN112180369B (en) | Depth learning-based sea surface wind speed inversion method for one-dimensional synthetic aperture radiometer | |
| Dai et al. | Optimization about the layout of IMUs in large ship based on fruit fly optimization algorithm | |
| Gaidai et al. | Floating wind turbines structural details fatigue life assessment | |
| CN117390895B (en) | Semi-submersible ship ballast system simulation method, device and storage medium | |
| Bisinotto et al. | Estimating wave spectra from the motions of dynamically positioned vessels: An assessment based on model tests | |
| CN117037450A (en) | Environment early warning method, device, equipment and medium of intelligent piling ship | |
| Mujeeb-Ahmed et al. | Effect of mooring line layout on the loads of ship-shaped offshore installations | |
| Tao et al. | Experimental and numerical investigation of the hydrodynamic response of an aquaculture vessel | |
| CN115410419B (en) | Ship mooring early warning method, system, electronic equipment and storage medium | |
| EP2587321A1 (en) | Wave filtering using differential evolution for dynamic positioning systems | |
| CN115062526B (en) | Three-dimensional ionosphere electron concentration distribution model training method based on deep learning | |
| Söding | Nonlinear seakeeping and hydroelasticity of ships using potential flow simulations | |
| CN114528638A (en) | Ship motion multi-step real-time prediction mixing method and system based on reinforcement learning | |
| CN112734125A (en) | Photovoltaic output prediction method and device and electronic equipment | |
| CN116432518B (en) | Rapid forecasting method, system, equipment and medium for occurrence probability of malformed wave | |
| US20230259769A1 (en) | Multi-stage training of machine learning models | |
| West | Optimization of Synthetic Mooring Systems for Floating Offshore Wind Turbines | |
| JP3245238U (en) | Prediction correction system equipped with a learning device and a prediction correction device |
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 |