CN114925886B - Ship bottom attachment cleaning prediction method for ship - Google Patents
Ship bottom attachment cleaning prediction method for ship Download PDFInfo
- Publication number
- CN114925886B CN114925886B CN202210472162.XA CN202210472162A CN114925886B CN 114925886 B CN114925886 B CN 114925886B CN 202210472162 A CN202210472162 A CN 202210472162A CN 114925886 B CN114925886 B CN 114925886B
- Authority
- CN
- China
- Prior art keywords
- draft
- ship
- sequence
- sampling period
- index
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000005070 sampling Methods 0.000 claims description 95
- 239000000446 fuel Substances 0.000 claims description 52
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000005259 measurement Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 4
- 241000238586 Cirripedia Species 0.000 description 9
- 238000001514 detection method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 241000251730 Chondrichthyes Species 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009182 swimming Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 239000000084 colloidal system Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 244000045947 parasite Species 0.000 description 1
- 230000003071 parasitic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B35/32—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for for collecting pollution from open water
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B59/00—Hull protection specially adapted for vessels; Cleaning devices specially adapted for vessels
- B63B59/04—Preventing hull fouling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Ocean & Marine Engineering (AREA)
- Mechanical Engineering (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of cleaning, in particular to a ship bottom attachment cleaning prediction method for ships.
Description
Technical Field
The invention relates to the technical field of cleaning, in particular to a ship bottom attachment cleaning prediction method for a ship.
Background
There are a large number of parasites in the water that can cling to the bottom of the ship, increasing the burden on the ship. A large amount of parasitic organisms adhere to the bottom of the ship, so that the weight of the ship body can be increased, the speed of the ship body is reduced, the fuel consumption is increased, and the material of the ship can be corroded. At present, ships are randomly cleaned through underwater detection, but the underwater detection method is inconvenient to operate and cannot be cleaned timely.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a ship bottom attachment cleaning and predicting method for a ship, which adopts the following technical scheme:
acquiring the oil consumption and the draft of the ship based on the set sampling frequency, obtaining an oil consumption sequence and a draft sequence in the current sampling period, and calculating abnormal oil consumption indexes of the ship in the current sampling period by combining the oil consumption sequence and the draft sequence; counting the berthing times of the ship in the current sampling period, and forming a berthing time sequence from each berthing time;
constructing a linear change function of the draft according to each draft in the draft sequence, and acquiring a measurement error value of the draft sequence by the linear change function; calculating a draft variance of the draft degree sequence, taking the product of the measurement error value and the draft variance as a misjudgment parameter of the oil consumption abnormality index, and acquiring a ship cleaning index of the current sampling period by combining the misjudgment parameter, the oil consumption abnormality index, the berthing times and the berthing duration sequence;
acquiring the ship cleaning indexes of a plurality of sampling periods to form a cleaning index sequence, and inputting the cleaning index sequence into a cleaning index prediction network to obtain a ship cleaning index predicted value of the next sampling period; and obtaining a prediction difference parameter of the cleaning index prediction network, optimizing the ship cleaning index prediction value by using the prediction difference parameter to obtain an actual ship cleaning index prediction value, and cleaning and early warning the ship according to the actual ship cleaning index prediction value.
Further, the method for calculating the abnormal fuel consumption index of the ship in the current sampling period by combining the fuel consumption sequence and the draft sequence comprises the following steps:
Obtaining the maximum draft, the minimum draft and the average draft in the draft sequence, and calculating a draft difference between the maximum draft and the minimum draft; calculating the average fuel consumption and the extremely poor fuel consumption of the fuel consumption sequence;
And calculating an abnormal fuel consumption index of the current sampling period by combining a first difference value of the average draft corresponding to the current sampling period and the last sampling period, a second difference value of the average fuel consumption corresponding to the current sampling period and the last sampling period, and the difference value of the draft of the current sampling period and the fuel consumption limit of the current sampling period, wherein the abnormal fuel consumption index is calculated according to the formula:
Wherein U i is the abnormal fuel consumption index of the ith sampling period; max (L i) is the maximum draft of the ith sample period; min (L i) is the minimum draft of the ith sample period; mean (L i) is the average draft of the ith sample period; mean (L i-1) is the average draft for the i-1 th sampling period; range (H i) is the fuel consumption of the ith sampling period; mean (H i) is the average fuel consumption for the ith sampling period; mean (H i-1) is the average fuel consumption for the i-1 th sampling period.
Further, the method for obtaining the measurement error value of the draft sequence by a linear variation function comprises the following steps:
substituting each draft in the draft sequence into a linear change function to obtain an ideal draft corresponding to each draft;
And respectively calculating the depth difference value between each draft and the corresponding ideal draft to obtain a depth difference value sequence, calculating an average depth difference value for the depth difference value sequence, and taking the average depth difference value as a measurement error value of the corresponding draft sequence.
Further, the calculation formula of the ship cleaning index includes:
wherein W is a ship cleaning index, mean (T) is the average berthing duration of berthing duration sequences, U is an abnormal oil consumption index, S is berthing times, and J is a misjudgment parameter.
Further, the method for obtaining the predicted difference parameter of the cleaning index prediction network comprises the following steps:
Forming a predicted value sequence by a plurality of known ship cleaning index predicted values, forming an actual value sequence by a plurality of corresponding ship cleaning indexes which are actually calculated, and calculating the similarity between the predicted value sequence and the actual value sequence to obtain a predicted difference parameter of the cleaning index predicted network, wherein the calculation formula of the predicted difference parameter is as follows: Wherein M is a predicted difference parameter, P is an actual value sequence, and P 0 is a predicted value sequence.
Further, the calculation formula of the actual ship cleaning index predicted value includes:
W0=W′*M
Wherein, W 0 is the predicted value of the actual ship cleaning index, W ′ is the predicted value of the ship cleaning index, and M is the predicted difference parameter.
The embodiment of the invention has at least the following beneficial effects: analyzing ship cleaning indexes of each sampling period according to the oil consumption, draft, berthing times and berthing duration of a ship, acquiring ship cleaning index predicted values of the next sampling period by using a cleaning index prediction network, optimizing the ship cleaning index predicted values by using prediction difference parameters of the cleaning index prediction network so as to obtain accurate actual ship cleaning index predicted values, further realizing timely cleaning and early warning, reducing the corrosion speed of ship materials, and solving the trouble of underwater detection.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart showing steps of a ship bottom attachment cleaning prediction method for a ship according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of the ship bottom attachment cleaning prediction method for the ship according to the invention in detail by combining the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all 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.
The following specifically describes a specific scheme of the ship bottom attachment cleaning prediction method for the ship provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for predicting cleaning attachments on a ship bottom of a ship according to an embodiment of the invention is shown, and the method includes the following steps:
Step S001, acquiring the oil consumption and the draft of the ship based on the set sampling frequency, obtaining an oil consumption sequence and a draft sequence in the current sampling period, and calculating abnormal oil consumption indexes of the ship in the current sampling period by combining the oil consumption sequence and the draft sequence; and counting the berthing times of the ship in the current sampling period, and forming a berthing time sequence from each berthing time.
Specifically, the ship power is realized by oil consumption, and the load capacity of the ship influences the oil consumption of the ship, and the larger the load capacity is, the larger the corresponding oil consumption is, so that the oil consumption of the ship is recorded.
When a large amount of attachments are on the bottom of the ship, the weight of the attachments can increase the self weight of the ship and further increase the draft of the ship, so that the distance between the water surface and the deck of the ship is measured through the distance sensor, the distance is taken as the draft of the ship, the draft L of the ship is recorded at the sampling frequency of 1 minute with one week as a sampling period, and a draft sequence l= { L 1,l2…ln }, wherein L 1 is the draft at the 1 st sampling, L 2 is the draft at the 2 nd sampling, and L n is the draft at the nth sampling.
The ship is driven at a higher speed, which is unfavorable for the adhesion of marine organisms like barnacles, but when the speed of the ship is reduced or the ship is moored, the marine organisms like barnacles are easy to secrete colloid to adhere, so that the more times the ship is moored, the longer the time of each mooring, and the more organisms like barnacles adhere. Therefore, in the embodiment of the invention, the number of times S of berthing the ship in one week and the berthing duration of each time are counted by taking one week as a sampling period, and the berthing duration is formed into a berthing duration sequence T= { T 1,t2,…tS }, wherein T 1 is the berthing duration of the 1 st sampling, T 2 is the berthing duration of the 2 nd sampling, and T S is the berthing duration of the S th sampling.
The oil consumption sequence H, the draft sequence L, the berthing times S and the berthing duration sequence T of the ship in one sampling period form the characteristic vector of the sampling period, so that the characteristic vector of a plurality of sampling periods can be obtained.
Further, under normal conditions, when the ship is fully loaded, the oil consumption and draft of the corresponding ship are not greatly changed due to the fact that the load of the ship is unchanged, when attachments such as barnacles are arranged on the bottom of the ship, the weight of the attachments can increase the dead weight of the ship, the draft of the ship is increased, and due to the attachment of the attachments, the resistance of the bottom of the ship is increased, the engine needs to output more power to enable the ship to be kept at a calibrated speed, the oil consumption is increased, and therefore the abnormal oil consumption index of the ship in the corresponding sampling period is calculated by combining a draft sequence and an oil consumption sequence, and the specific calculation method comprises the following steps: obtaining the maximum draft, the minimum draft and the average draft in the draft sequence, and calculating a draft difference between the maximum draft and the minimum draft; calculating the average fuel consumption and the fuel consumption of the fuel consumption sequence, and calculating the abnormal fuel consumption index of the current sampling period by combining the first difference value of the average draft corresponding to the current sampling period and the last sampling period, the second difference value of the average fuel consumption corresponding to the current sampling period and the last sampling period, and the draft difference value of the current sampling period and the fuel consumption of the current sampling period, wherein the abnormal fuel consumption index is calculated by the calculation formula:
Wherein U i is the abnormal fuel consumption index of the ith sampling period; max (L i) is the maximum draft of the ith sample period; min (L i) is the minimum draft of the ith sample period; mean (L i) is the average draft of the ith sample period; mean (L i-1) is the average draft for the i-1 th sampling period; range (H i) is the fuel consumption of the ith sampling period; mean (H i) is the average fuel consumption for the ith sampling period; mean (H i-1) is the average fuel consumption for the i-1 th sampling period.
According to the calculation formula of the abnormal fuel consumption index, the abnormal fuel consumption index of the ship corresponding to each sampling period can be obtained, and then the abnormal fuel consumption index is added into the feature vector to form a new feature vector.
Step S002, constructing a linear change function of the draft according to each draft in the draft sequence, and obtaining a measurement error value of the draft sequence by the linear change function; calculating the draft variance of the draft degree sequence, taking the product of the measurement error value and the draft variance as the misjudgment parameter of the abnormal fuel consumption index, and combining the misjudgment parameter, the abnormal fuel consumption index, the berthing times and the berthing duration sequence to obtain the ship cleaning index of the current sampling period.
Specifically, since the sea surface may have waves caused by blowing of wind, and if the distance sensor just detects the excited spray, the measurement of the draft will have a high or low floating error, so that the abnormal fuel consumption index calculated in step S001 will have an error, so that the erroneous judgment parameter corresponding to the abnormal fuel consumption index is obtained according to the draft sequence L in the new feature vector, and taking a sampling period as an example, the specific process is as follows:
(1) A linear variation function of draft is constructed from each draft in the draft sequence.
Specifically, each draft in the draft sequence and a corresponding sampling time point form a data set, a plurality of data sets are obtained, and the slope of a fitting straight line corresponding to the draft sequence is calculated for the data sets by using a least square method; and calculating the average draft of the draft sequence, correspondingly, calculating the average sampling time point of the sampling time points, and obtaining a linear change function of the draft by combining the slope, the average draft and the average sampling time point.
(2) Substituting each draft in the draft sequence into a linear change function to obtain an ideal draft corresponding to each draft, and calculating a measurement error value of the corresponding draft sequence by combining the ideal drafts.
Specifically, the linear change function is used for representing a draft change straight line of the ship in the sampling period, namely an ideal change straight line of the draft, so that each draft in the draft sequence is substituted into the linear change function to obtain the ideal draft corresponding to each draft. And respectively calculating the depth difference value between each draft and the corresponding ideal draft, further obtaining a depth difference value sequence, calculating an average depth difference value for the depth difference value sequence, and taking the average depth difference value as a measurement error value of the corresponding draft sequence.
(3) And calculating the draft variance of the draft degree sequence, and taking the product between the measurement error value and the draft variance as the erroneous judgment parameter of the abnormal fuel consumption index.
It should be noted that, the draft variance represents the fluctuation degree of the draft in the sampling period, and the larger the draft variance is, the larger the misjudgment parameter of the abnormal fuel consumption index is; the measurement error value is the error between the ideal and the actual measurement, and the larger the measurement error value is, the larger the erroneous judgment parameter of the abnormal fuel consumption index is.
Further, the oil consumption analysis alone cannot accurately indicate whether the attachments on the bottom of the ship need to be cleaned, and the investigation shows that the number of barnacles parasitized on marine organisms with larger body types and slower optimal speed is more, but the living organisms with faster swimming speed like sharks hardly find the parasitization of the barnacles, the reason is that the swimming speed of the sharks is fast, the attachment of the barnacles is not facilitated, and similarly, the ship is in navigation at a higher speed, the attachment of the living organisms like the barnacles is not facilitated, but the opportunity of the attachment of the living organisms like the barnacles is given when the ship stops, therefore, the ship cleaning index corresponding to the sampling period is obtained by combining the misjudgment parameters, the abnormal oil consumption index, the berthing times and the berthing duration sequence in the sampling period, and the calculation formula of the ship cleaning index is as follows:
Wherein W is a ship cleaning index, mean (T) is the average berthing duration of the berthing duration sequence, and U is an abnormal oil consumption index.
It should be noted that, when the number of times of berthing of the ship in the sampling period is greater, the longer the berthing time of each time is, the higher the abnormal fuel consumption index is, the lower the misjudgment parameter of the abnormal fuel consumption index is, and the higher the ship cleaning index corresponding to the sampling period is.
Step S003, acquiring ship cleaning indexes of a plurality of sampling periods to form a cleaning index sequence, and inputting the cleaning index sequence into a cleaning index prediction network to obtain a ship cleaning index predicted value of the next sampling period; and obtaining a predicted difference parameter of the cleaning index prediction network, optimizing a ship cleaning index predicted value by using the predicted difference parameter to obtain an actual ship cleaning index predicted value, and cleaning and early warning the ship according to the actual ship cleaning index predicted value.
Specifically, ship cleaning indexes corresponding to a plurality of continuous sampling periods are obtained through the methods of the step S001 and the step S002, a cleaning index sequence is formed by the ship cleaning indexes, the cleaning index sequence is input into a cleaning index prediction network to obtain a ship cleaning index predicted value of the next sampling period, wherein in the embodiment of the invention, the cleaning index prediction network is a TCN prediction network, the input of the TCN prediction network is the cleaning index sequence, the output is the ship cleaning index predicted value of the next sampling period, and the loss function of the TCN prediction network adopts a mean square error loss function.
Further, since the predicted value of the ship cleaning index is different from the actually calculated ship cleaning index, and in order to make the predicted result more accurate, a predicted value sequence is formed by a plurality of known predicted values of the ship cleaning index, an actual value sequence is formed by a plurality of actually calculated corresponding ship cleaning indexes, and the predicted difference parameter of the cleaning index prediction network is obtained by calculating the similarity between the predicted value sequence and the actual value sequence, the calculation formula of the predicted difference parameter is as follows: Wherein M is a predicted difference parameter, P is an actual value sequence, and P 0 is a predicted value sequence; and then optimizing the ship cleaning index predicted value by using the predicted difference parameter to obtain the actual ship cleaning index predicted value, wherein the optimization formula is as follows: w 0 = W '×m, where W 0 is an actual ship cleaning index prediction value, and W' is a ship cleaning index prediction value.
And setting a prediction threshold, and when the prediction value of the actual ship cleaning index is larger than the prediction threshold, confirming that the ship bottom of the ship needs to be cleaned, and further sending out cleaning early warning in time.
In summary, the embodiment of the invention provides a ship bottom attachment cleaning prediction method for a ship, which analyzes ship cleaning indexes of each sampling period according to the fuel consumption, draft, berthing times and berthing duration of the ship, acquires ship cleaning index predicted values of the next sampling period from the ship cleaning indexes of continuous multiple sampling periods through a cleaning index prediction network, optimizes the ship cleaning index predicted values by using prediction difference parameters of the cleaning index prediction network, so as to obtain accurate actual ship cleaning index predicted values, further achieve timely cleaning and early warning, reduce the corrosion speed of ship materials, and solve the trouble of underwater detection.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (4)
1. The ship bottom attachment cleaning prediction method for the ship is characterized by comprising the following steps of:
acquiring the oil consumption and the draft of the ship based on the set sampling frequency, obtaining an oil consumption sequence and a draft sequence in the current sampling period, and calculating abnormal oil consumption indexes of the ship in the current sampling period by combining the oil consumption sequence and the draft sequence; counting the berthing times of the ship in the current sampling period, and forming a berthing time sequence from each berthing time;
Constructing a linear change function of the draft according to each draft in the draft sequence, and acquiring a measurement error value of the draft sequence by the linear change function; calculating a draft variance of the draft sequence, taking the product of the measurement error value and the draft variance as a misjudgment parameter of the oil consumption abnormality index, and acquiring a ship cleaning index of the current sampling period by combining the misjudgment parameter, the oil consumption abnormality index, the berthing times and the berthing duration sequence;
Acquiring the ship cleaning indexes of a plurality of sampling periods to form a cleaning index sequence, and inputting the cleaning index sequence into a cleaning index prediction network to obtain a ship cleaning index predicted value of the next sampling period; obtaining a predicted difference parameter of the cleaning index prediction network, optimizing the ship cleaning index predicted value by using the predicted difference parameter to obtain an actual ship cleaning index predicted value, and cleaning and early warning the ship according to the actual ship cleaning index predicted value;
the calculation formula of the ship cleaning index comprises the following steps:
Wherein, Is a ship cleaning index,/>For the average duration of the duration sequence,/>Is an abnormal fuel consumption index,/>For the number of berths,/>Is a misjudgment parameter;
The method for obtaining the prediction difference parameter of the cleaning index prediction network comprises the following steps:
Forming a predicted value sequence by a plurality of known ship cleaning index predicted values, forming an actual value sequence by a plurality of corresponding ship cleaning indexes which are actually calculated, and calculating the similarity between the predicted value sequence and the actual value sequence to obtain a predicted difference parameter of the cleaning index predicted network, wherein the calculation formula of the predicted difference parameter is as follows: wherein/> To predict the discrepancy parameter,/>For actual value sequence,/>Is a sequence of predicted values.
2. The ship bottom attachment cleaning prediction method of the ship according to claim 1, wherein the method for calculating the abnormal fuel consumption index of the ship in the current sampling period by combining the fuel consumption sequence and the draft sequence comprises the following steps:
Obtaining the maximum draft, the minimum draft and the average draft in the draft sequence, and calculating a draft difference between the maximum draft and the minimum draft; calculating the average fuel consumption and the extremely poor fuel consumption of the fuel consumption sequence;
And calculating an abnormal fuel consumption index of the current sampling period by combining a first difference value of the average draft corresponding to the current sampling period and the last sampling period, a second difference value of the average fuel consumption corresponding to the current sampling period and the last sampling period, and the difference value of the draft of the current sampling period and the fuel consumption limit of the current sampling period, wherein the abnormal fuel consumption index is calculated according to the formula:
Wherein, For/>Abnormal fuel consumption indexes of a plurality of sampling periods; /(I)For/>Maximum draft for each sampling period; /(I)For/>A minimum draft of a sampling period; /(I)For/>Average draft for each sampling period; /(I)For/>Average draft for each sampling period; /(I)For/>The fuel consumption of each sampling period is extremely poor; /(I)For/>Average fuel consumption of each sampling period; /(I)For/>Average fuel consumption over a sampling period.
3. A method for predicting bilge removal of a vessel as claimed in claim 1, wherein said method for obtaining a measured error value of said draft sequence from a linear variation function comprises:
substituting each draft in the draft sequence into a linear change function to obtain an ideal draft corresponding to each draft;
And respectively calculating the depth difference value between each draft and the corresponding ideal draft to obtain a depth difference value sequence, calculating an average depth difference value for the depth difference value sequence, and taking the average depth difference value as a measurement error value of the corresponding draft sequence.
4. The ship bottom attachment cleaning prediction method of claim 1, wherein the calculation formula of the actual ship cleaning index prediction value comprises:
Wherein, Predicted value of actual ship cleaning index,/>Predicted value of ship cleaning index,/>To predict the discrepancy gauge.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210472162.XA CN114925886B (en) | 2022-04-29 | 2022-04-29 | Ship bottom attachment cleaning prediction method for ship |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210472162.XA CN114925886B (en) | 2022-04-29 | 2022-04-29 | Ship bottom attachment cleaning prediction method for ship |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114925886A CN114925886A (en) | 2022-08-19 |
CN114925886B true CN114925886B (en) | 2024-04-30 |
Family
ID=82806312
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210472162.XA Active CN114925886B (en) | 2022-04-29 | 2022-04-29 | Ship bottom attachment cleaning prediction method for ship |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114925886B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204355262U (en) * | 2014-10-21 | 2015-05-27 | 浙江海洋学院 | Bottom of ship marine attaching organism cleaning plant |
JP2017102565A (en) * | 2015-11-30 | 2017-06-08 | 株式会社Ihi | Anchorage vessel number prediction system, anchorage vessel number prediction method, and anchorage vessel number prediction program |
CN107933850A (en) * | 2017-11-28 | 2018-04-20 | 东台市海信船舶设备厂 | A kind of processing unit for lifesaving bottom of ship attachment |
CN107944648A (en) * | 2018-01-08 | 2018-04-20 | 中国船舶工业系统工程研究院 | A kind of accurate Forecasting Methodology of large ship speed of a ship or plane rate of fuel consumption |
CN110705797A (en) * | 2019-10-09 | 2020-01-17 | 浙江海洋大学 | Ship oil consumption data prediction method based on ship sensor network |
CN112836893A (en) * | 2021-02-26 | 2021-05-25 | 上海海事大学 | Method for predicting ship oil consumption under severe sea conditions based on sea condition and ship navigation conditions |
CN113668479A (en) * | 2021-10-22 | 2021-11-19 | 丹华海洋工程装备(南通)有限公司 | Method and system for adjusting filter screen for sea surface cleaning ship |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10984338B2 (en) * | 2015-05-28 | 2021-04-20 | Raytheon Technologies Corporation | Dynamically updated predictive modeling to predict operational outcomes of interest |
-
2022
- 2022-04-29 CN CN202210472162.XA patent/CN114925886B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204355262U (en) * | 2014-10-21 | 2015-05-27 | 浙江海洋学院 | Bottom of ship marine attaching organism cleaning plant |
JP2017102565A (en) * | 2015-11-30 | 2017-06-08 | 株式会社Ihi | Anchorage vessel number prediction system, anchorage vessel number prediction method, and anchorage vessel number prediction program |
CN107933850A (en) * | 2017-11-28 | 2018-04-20 | 东台市海信船舶设备厂 | A kind of processing unit for lifesaving bottom of ship attachment |
CN107944648A (en) * | 2018-01-08 | 2018-04-20 | 中国船舶工业系统工程研究院 | A kind of accurate Forecasting Methodology of large ship speed of a ship or plane rate of fuel consumption |
CN110705797A (en) * | 2019-10-09 | 2020-01-17 | 浙江海洋大学 | Ship oil consumption data prediction method based on ship sensor network |
CN112836893A (en) * | 2021-02-26 | 2021-05-25 | 上海海事大学 | Method for predicting ship oil consumption under severe sea conditions based on sea condition and ship navigation conditions |
CN113668479A (en) * | 2021-10-22 | 2021-11-19 | 丹华海洋工程装备(南通)有限公司 | Method and system for adjusting filter screen for sea surface cleaning ship |
Non-Patent Citations (1)
Title |
---|
基于数据驱动的船舶油耗预测模型研究;尹石军;林召凯;高海波;廖林豪;;江苏船舶(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114925886A (en) | 2022-08-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3825651A1 (en) | Apparatus for predicting a power consumption of a maritime vessel | |
JP6393940B2 (en) | Ship aging change estimation method, ship aging change estimation system, optimum route calculation system, and ship operation support system | |
Parunov et al. | Uncertainties in modelling the low-frequency wave-induced global loads in ships | |
Bitner-Gregerse et al. | Adverse weather conditions for ship manoeuvrability | |
CN112598113A (en) | Ocean sound velocity profile acquisition method based on self-organizing competitive neural network | |
JP6721455B2 (en) | Hull fouling evaluation device and hull fouling evaluation program | |
EP3464058B1 (en) | A method and a system for optimising operation of a vessel | |
CN110595472A (en) | Unmanned ship dual-target meteorological flight line optimization method and system | |
CN114925886B (en) | Ship bottom attachment cleaning prediction method for ship | |
Fonteinos et al. | Ship hull fouling estimation using shipboard measurements, models for resistance components, and shaft torque calculation using engine model | |
CN111597506B (en) | Prediction method for near-shore wave breaking parameters and wave height | |
CN112632868B (en) | Filling and correcting method and system for radial flow missing value observed by high-frequency ground wave radar | |
CN104443299B (en) | Inland navigation craft load measuring device based on pressure measurement technology and method | |
EP3362348B1 (en) | Method for applying a coating to an external surface of a man-made object to be at least partly immersed in water | |
CN112208728B (en) | Ship fouling monitoring and early warning method | |
CN113988548A (en) | Marine fishery assessment method based on sustainable development | |
CN113902327A (en) | Evaluation method and system for corrosion health state of offshore wind plant foundation structure | |
CN109373981B (en) | Method for accurately forecasting water increase and decrease of water area inside breakwater | |
CN111323081A (en) | Ship test voyage performance index correction method, correction system, storage medium and electronic terminal | |
CN117824995A (en) | Ship wave load characteristic value determination method under target sea condition | |
CN117963104A (en) | Method for judging ship bottom pollution state | |
CN112141293B (en) | Ship fouling monitoring and evaluating method based on fixed navigational speed fouling coefficient | |
CN117574099B (en) | Time-space correction deck upward wave time prediction method and system | |
CN116090745A (en) | Automatic operation method for solving inland container port refuting and shipping command | |
CN115081350A (en) | Mooring system safety prediction method, system and medium for ultra-large floating body |
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 |