CN115600746A - Convolutional neural network-based drag suction ship energy efficiency prediction method - Google Patents
Convolutional neural network-based drag suction ship energy efficiency prediction method Download PDFInfo
- Publication number
- CN115600746A CN115600746A CN202211300629.9A CN202211300629A CN115600746A CN 115600746 A CN115600746 A CN 115600746A CN 202211300629 A CN202211300629 A CN 202211300629A CN 115600746 A CN115600746 A CN 115600746A
- Authority
- CN
- China
- Prior art keywords
- data
- trailing suction
- energy efficiency
- working
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 36
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 239000002002 slurry Substances 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 16
- 230000004913 activation Effects 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a trailing suction ship energy efficiency prediction method based on a convolutional neural network, which comprises the following steps of: s1, dividing working conditions according to working data of a trailing suction ship; s2, filtering the working data of the trailing suction ship processed in the step S1 to eliminate the influence of environmental noise; and S3, constructing a training set of convolutional neural network energy efficiency data according to the work data of the trailing suction ship processed in the step S2, and establishing a convolutional neural network regression prediction model of the trailing suction ship energy efficiency. By adopting the method for predicting the energy efficiency of the trailing suction ship based on the convolutional neural network, the problem of inaccurate energy efficiency prediction can be solved.
Description
Technical Field
The invention relates to the technical field of energy efficiency prediction, in particular to a method for predicting the energy efficiency of a trailing suction vessel based on a convolutional neural network.
Background
The drag suction ship is used as a main construction ship type of the prior dredging engineering, and has irreplaceable functions in tasks such as port maintenance, excavation of a coastal harbor channel and the like due to the characteristics of flexibility, high efficiency, strong wind and wave resistance and the like. At present, the demand of domestic dredging engineering is huge, the fuel cost is continuously increased, and pollutant discharge regulations are increasingly strict, which have urgent requirements on improving the construction efficiency of the trailing suction vessel. The method can accurately predict the dredging efficiency of the trailing suction dredger, can conveniently determine the construction period, reduces the operation of constructors, and has important significance for improving the dredging operation efficiency.
Tang et al (j.z.tang, q.f.wang, t.y.zhong, automatic monitoring and control of the cutter suction dredger, autom.constr.18 (2) (2009) 194-203) designed an Automatic monitoring system for cutter suction vessels that improved the production efficiency of the dredging process by controlling the slurry concentration and slurry flow rate, focused on the dredging process closely based on computers and evaluated the system status accurately. However, since many factors affecting dredging productivity are dynamic and related to each other in a complex manner, and the working process of the drag suction vessel is a typical nonlinear process, the traditional energy efficiency prediction method cannot realize accurate energy efficiency prediction on the dredging process of the drag suction vessel under complex conditions.
Disclosure of Invention
The invention aims to provide a trailing suction vessel energy efficiency prediction method based on a convolutional neural network.
In order to achieve the purpose, the invention provides a method for predicting the energy efficiency of a trailing suction ship based on a convolutional neural network, which comprises the following steps:
s1, dividing working conditions according to working data of a trailing suction ship;
s2, filtering the working data of the trailing suction ship processed in the step S1;
and S3, constructing a training set of the convolutional neural network energy efficiency data according to the working data of the trailing suction ship processed in the step S2, and establishing a convolutional neural network regression prediction model of the trailing suction ship energy efficiency.
Further, the specific method of step S1 is:
according to the working principle of the trailing suction ship and the characteristics of real ship data, the rotating speed N of the dredge pump, the navigational speed V and the slurry concentration gamma are selected as judgment parameters for working condition division, and the rotating speed, the navigational speed and the slurry concentration threshold value N of the dredge pump are set thr ,V thr And gamma thr Will satisfy n > n simultaneously thr ,V＜V thr And gamma > gamma thr Judging the working data to be the dredging working condition data;
further, the specific method of step S2 is:
s21, mean value filtering: the mean value filtering method is adopted to replace all values in the original trailing suction boat data with the mean value so as to reduce the influence of environmental noise on the working data of the trailing suction boat, and the formula is as follows:
wherein i represents the operating parameter category of the trailing suction vessel (i =1, 2.., M); m is the number of working parameters, and the working parameters comprise slurry concentration, slurry density, mud pump flow rate, slurry flow rate, navigation speed, trailing suction ship power and the like; u. of i (j) J-th data (j =1, 2.., N) representing an i-th operating parameter of the trailing suction vessel; n is the number of data; u shape i (j) Is u i (j) Filtered working data; k is the step size of filtering;
wherein, the working parameter U of the trailing suction boat i Expressed as:
U i ＝(U i (1),U i (2),...,U i (N))
the filtered total working data set U of the trailing suction vessel is as follows:
U＝(U 1 ,U 2 ,...,U M ) T ；
S22、extracting work parameter X related to energy efficiency of drag suction ship i And energy efficiency data Y:
according to the type of the working parameters of the trailing suction hopper, the working data Z of the trailing suction hopper can be expressed as follows:
Z＝(X 1 ,X 2 ,...,X l ,Y 1 ,Y 2 ,Y 3 ,Y 4 ) T
wherein, X 1 ＝U 1 ,X 2 ＝U 2 ,...,X l ＝U l Representing working parameters related to the energy efficiency of the trailing suction vessel in the set U except the trailing suction vessel power P, the mud concentration gamma, the mud density rho and the mud flow Q (l = M-4); y is 1 ,Y 2 ,Y 3 ,Y 4 Representing the energy efficiency calculation parameters of the trailing suction dredger, namely the trailing suction dredger power P, the slurry concentration gamma, the slurry density rho and the slurry flow Q, energy efficiency data Y of the trailing suction dredger are calculated through the parameters, and the calculation formula is as follows:
Y＝P/γρQ
extracted operating parameter X i And energy efficiency data Y as an effective two-sided dataset, expressed as:
X i ＝(X i (1),X i (2),...,X i (N))
Y＝(Y(1),Y(2),...,Y(N))；
further, the specific method of step S3 is:
s31, selecting a sliding window data sequence: obtaining data of the current data point and the last p-1 data points from the effective measurement data set to form a sliding window data sequence, wherein p is the step length of the sliding window sequence, and the obtained sliding window data sequence is marked as
Y (j) ：
X (j) A sliding window sequence at the jth data point for all working data of the valid metrology data set:
combining the sliding window sequences of all data points to obtain a new data set X new ，Y new ：
X new ＝(X (1) ,X (2) ,...,X (N) ) T
Y new ＝(Y (1) ,Y (2) ,...,Y (N) ) T
Data set X new The method is a matrix with N multiplied by l rows and p columns, each l row of data represents the real-time values of l working parameters of the trailing suction ship on one data point and p-1 data points after the data point, and the data are used as the input of one sample of the neural network; data set Y new The method is a matrix with N rows and p columns, each row of data represents an effective value of the trailing suction boat on one data point and p-1 data points behind the data point, and the data are used as the output of one sample of the neural network;
s32, dividing the sample into a training set and a testing set; wherein the proportion of the training set and the test set in the total sample is respectively 80% and 20%, and the normalization processing is carried out on the training set and the test set;
s33, constructing a convolutional neural network model: the network structure of the model consists of an input layer, a convolution layer, an activation function layer and two full-connection layers, and learning rate, activation function type, iteration times and three hyper-parameters are set;
the size of the input data of the input layer is the product of the number of the filtered working parameters and the step length of the sliding window sequence, namely l x p;
the convolutional layer is provided with 16 filters with the size of 3 multiplied by 3 and used for extracting data characteristics of the drag suction ship;
the activation function of the activation function layer selects a Relu activation function, and the formula is as follows:
the full connection layer is used as an output layer, and the unit number of the full connection layer is equal to the step length p of the sliding window sequence;
s34, verifying the accuracy of the model: testing the convolutional neural network model by using samples of the test set, and verifying the accuracy of the model through Root Mean Square Error (RMSE);
wherein Y (i) is the true energy efficiency of the trailing suction vessel, E c And (x (i)) is an energy efficiency predicted value of the trailing suction ship.
The method for predicting the energy efficiency of the trailing suction ship based on the convolutional neural network has the advantages and positive effects that:
1. the working condition division and filtering method designed by the invention can effectively extract working data related to the energy efficiency of the trailing suction hopper, avoids the influence of environmental noise on energy efficiency prediction, and improves the accuracy of the energy efficiency prediction of the trailing suction hopper.
2. The method provided by the invention extracts the working data characteristics of the trailing suction vessel and establishes the energy efficiency prediction model by using the convolutional neural network, so that the problem of inaccurate energy efficiency prediction of the trailing suction vessel system is solved.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flowchart of an embodiment of a method for estimating the energy efficiency of a trailing suction vessel based on a convolutional neural network according to the present invention;
fig. 2 is a diagram of a drag suction ship energy efficiency value and a drag suction ship energy efficiency prediction value in an embodiment of the drag suction ship energy efficiency prediction method based on a convolutional neural network of the present invention;
fig. 3 is a root mean square error diagram of a model of an embodiment of the drag suction ship energy efficiency prediction method based on the convolutional neural network.
Detailed Description
The technical scheme of the invention is further explained by the attached drawings and the embodiment.
Examples
Fig. 1 is a flowchart of an embodiment of a method for estimating the energy efficiency of a trailing suction vessel based on a convolutional neural network according to the present invention. As shown in the figure, the trailing suction ship energy efficiency prediction method based on the convolutional neural network comprises the following steps:
s1, working condition division is carried out according to the working data of the trailing suction ship.
The specific method of the step S1 comprises the following steps:
s11, extracting dredging working condition data: according to the working principle of the trailing suction ship and the characteristics of real ship data, the rotating speed N of the dredge pump, the navigational speed V and the slurry concentration gamma are selected as judgment parameters for working condition division, and the rotating speed, the navigational speed and the slurry concentration threshold value N of the dredge pump are set thr ,V thr And gamma thr ，N thr ＝100r/min，V thr ＝4kn，γ thr =0.6%, n > n will be satisfied simultaneously thr ,V＜V thr And gamma > gamma thr The working data of (2) is judged as the dredging working condition data.
And S2, filtering the working data of the trailing suction vessel processed in the step S1 to eliminate environmental noise.
S21, mean filtering: the mean value filtering method is adopted to replace all values in the original trailing suction boat data with the mean value so as to reduce the influence of environmental noise on the working data of the trailing suction boat, and the formula is as follows:
wherein i represents the operating parameter category of the trailing suction vessel (i =1, 2.., M); m is the number of working parameters, and the working parameters comprise slurry concentration, slurry density, mud pump flow rate, slurry flow rate, navigation speed, trailing suction ship power and the like; u. u i (j) J data representing the ith working parameter of the trailing suction vessel (j =1, 2.., N); n is the number of data; u shape i (j) Is u i (j) Filtered working data; k is the step size of filtering;
wherein, the working parameter U of the trailing suction boat i Expressed as:
U i ＝(U i (1),U i (2),...,U i (N))
the filtered total working data set U of the trailing suction vessel is as follows:
U＝(U 1 ,U 2 ,...,U M ) T
the working parameters are respectively 9 groups of parameters including slurry concentration, slurry density, mud pump flow rate, mud pump vacuum, mud cabin capacity, wave compensator pressure, slurry flow, navigation speed and drag suction ship power, namely M is 9; the number N of the extracted working parameters is 1002; the filter step k is set to 10.
S22, extracting energy efficiency related working parameters X of the drag suction ship i And energy efficiency data Y:
according to the type of the working parameters of the trailing suction hopper, the working data Z of the trailing suction hopper can be expressed as follows:
Z＝(X 1 ,X 2 ,...,X l ,Y 1 ,Y 2 ,Y 3 ,Y 4 ) T
wherein, X 1 ＝U 1 ,X 2 ＝U 2 ,...,X l ＝U l Representing working parameters related to the energy efficiency of the trailing suction vessel in the set U except the trailing suction vessel power P, the mud concentration gamma, the mud density rho and the mud flow Q (l = M-4); y is 1 ,Y 2 ,Y 3 ,Y 4 Representing the energy efficiency calculation parameters of the drag suction ship, namely drag suction ship power P, slurry concentration gamma, slurry density rho and slurry flow Q, wherein the energy efficiency data Y of the drag suction ship is calculated through the parameters, and the calculation formula is as follows:
Y＝P/γρQ
extracted operating parameter X i And energy efficiency data Y is expressed as:
X i ＝(X i (1),X i (2),...,X i (N))
Y＝(Y(1),Y(2),...,Y(N))。
and S3, constructing a training set of the convolutional neural network energy efficiency data according to the working data of the trailing suction ship processed in the step S2, and establishing a convolutional neural network regression prediction model of the trailing suction ship energy efficiency.
The concrete construction method of the convolution neural network regression prediction model in the step S3 comprises the following steps:
s31, selecting a sliding window data sequence: from is provided withObtaining data of the current data point and the p-1 data points after the current data point by the data of the efficiency measurement data set to form a sliding window data sequence, wherein p is the step length of the sliding window sequence, and the obtained sliding window data sequence is recorded as
Y (j) ：
X (j) A sliding window sequence at the jth data point for all working data of the valid metrology data set:
combining the sliding window sequences of all data points to obtain a new data set X new ，Y new ：
X new ＝(X (1) ,X (2) ,...,X (N) ) T
Y new ＝(Y (1) ,Y (2) ,...,Y (N) ) T
Here, the step p of the sliding window sequence is set to 10, and the operating parameters extracted in step S2 are l =5 groups.
Data set X new The method is a matrix with N multiplied by l rows and p columns, each l row of data represents the real-time values of l working parameters of the trailing suction ship on one data point and p-1 data points after the data point, and the data are used as the input of one sample of the neural network; data set Y new The matrix is N rows and p columns, each row of data represents the effective value of the trailing suction boat on one data point and p-1 data points after the data point, and the data are output as one sample of the neural network.
S32, dividing the sample into a training set and a testing set; the proportion of the training set and the proportion of the testing set in the total sample are respectively 80% and 20%, and normalization processing is carried out on the training set and the testing set.
S33, constructing a convolutional neural network model: the network structure of the model consists of an input layer, a convolution layer, an activation function layer and two full-connection layers, and a learning rate, an activation function type, iteration times and three hyper-parameters are set;
the size of the input data of the input layer is the product of the number of the working parameters screened after the correlation analysis and the step length of the sliding window sequence, namely l × p, wherein the size of the input data is 5 × 10;
the convolutional layer is provided with 16 filters with the size of 3 multiplied by 3 and is used for extracting the characteristics of the working data of the trailing suction ship;
the activation function of the activation function layer selects a Relu activation function, and the formula is as follows:
the full connection layer is used as an output layer, and the unit number of the full connection layer is equal to the step length p of the sliding window sequence.
S34, verifying the accuracy of the model: testing the convolutional neural network model by using samples of the test set, and verifying the accuracy of the model through Root Mean Square Error (RMSE);
wherein Y (i) is the real energy efficiency of the trailing suction vessel, E c And (x (i)) is an energy efficiency predicted value of the trailing suction ship.
Fig. 2 is a diagram of a trailing suction ship energy efficiency value and a trailing suction ship energy efficiency prediction value in an embodiment of a trailing suction ship energy efficiency prediction method based on a convolutional neural network, and fig. 3 is a root mean square error diagram of a model in an embodiment of the trailing suction ship energy efficiency prediction method based on the convolutional neural network. As shown in the figure, the fit degree between the real energy efficiency and the energy efficiency prediction value of the trailing suction ship is very high, and the error is very small, which shows that the energy efficiency prediction method of the trailing suction ship is very high in accuracy.
Therefore, the method for predicting the energy efficiency of the trailing suction vessel based on the convolutional neural network can solve the problem of inaccurate energy efficiency prediction.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the invention without departing from the spirit and scope of the invention.
Claims (4)
1. A trailing suction ship energy efficiency prediction method based on a convolutional neural network is characterized by comprising the following steps:
s1, dividing working conditions according to working data of a trailing suction ship;
s2, filtering the working data of the trailing suction ship processed in the step S1;
and S3, constructing a training set of convolutional neural network energy efficiency data according to the work data of the trailing suction ship processed in the step S2, and establishing a convolutional neural network regression prediction model of the trailing suction ship energy efficiency.
2. The method for predicting the energy efficiency of the trailing suction vessel based on the convolutional neural network as claimed in claim 1, wherein the specific method in the step S1 is as follows:
according to the working principle of the trailing suction ship and the characteristics of real ship data, the rotating speed N of the dredge pump, the navigational speed V and the slurry concentration gamma are selected as judgment parameters for working condition division, and the rotating speed, the navigational speed and the slurry concentration threshold value N of the dredge pump are set thr ,V thr And gamma thr Will satisfy n > n simultaneously thr ,V＜V thr And gamma > gamma thr The working data of (2) is judged as the dredging working condition data.
3. The trailing suction vessel energy efficiency prediction method based on the convolutional neural network as claimed in claim 2, wherein the filtering method in step S2 is:
s21, replacing each value in the original trailing suction ship data with the measured mean value by adopting a mean value filtering method to reduce the influence of environmental noise on the working data of the trailing suction ship, wherein the formula is as follows:
wherein i represents the operating parameter category of the trailing suction vessel (i =1, 2.., M); m is the number of working parameters, and the working parameters comprise slurry concentration, slurry density, mud pump flow rate, slurry flow rate, navigational speed and trailing suction ship power; u. of i (j) J-th data (j =1, 2.., N) representing an i-th operating parameter of the trailing suction vessel; n is the number of data; u shape i (j) Is u i (j) Filtered working data; k is the step size of filtering;
wherein, the working parameter U of the trailing suction boat i Expressed as:
U i ＝(U i (1),U i (2),...,U i (N))
the filtered total working data set U of the trailing suction ship is as follows:
U＝(U 1 ,U 2 ,...,U M ) T ；
s22, extracting work parameters X related to energy efficiency of the trailing suction ship i And energy efficiency data Y:
according to the type of the working parameters of the trailing suction hopper, the working data Z of the trailing suction hopper can be expressed as follows:
Z＝(X 1 ,X 2 ,...,X l ,Y 1 ,Y 2 ,Y 3 ,Y 4 ) T
wherein X 1 ＝U 1 ,X 2 ＝U 2 ,...,X l ＝U l Representing working parameters related to the energy efficiency of the trailing suction vessel in the set U except the trailing suction vessel power P, the mud concentration gamma, the mud density rho and the mud flow Q (l = M-4); y is 1 ,Y 2 ,Y 3 ,Y 4 Representing the energy efficiency calculation parameters of the trailing suction dredger, namely the trailing suction dredger power P, the slurry concentration gamma, the slurry density rho and the slurry flow Q, energy efficiency data Y of the trailing suction dredger are calculated through the parameters, and the calculation formula is as follows:
Y＝P/γρQ
extractedOperating parameter X i And energy efficiency data Y as an effective two-sided dataset, expressed as:
X i ＝(X i (1),X i (2),...,X i (N))
Y＝(Y(1),Y(2),...,Y(N))。
4. the trailing suction vessel energy efficiency prediction method based on the convolutional neural network as claimed in claim 3, wherein the convolutional neural network regression prediction model in the step S3 is specifically constructed by the following method:
s31, selecting a sliding window data sequence: obtaining data of the current data point and the last p-1 data points from the effective measurement data set to form a sliding window data sequence, wherein p is the step length of the sliding window sequence, and the obtained sliding window data sequence is marked as
Y (j) ：
X (j) A sliding window sequence at the jth data point for all working data of the valid metrology data set:
combining the sliding window sequences of all data points to obtain a new data set X new ，Y new ：
X new ＝(X (1) ,X (2) ,...,X (N) ) T
Y new ＝(Y (1) ,Y (2) ,...,Y (N) ) T
Data set X new Is a matrix of N x l rows and p columns, each line of data represents the real-time values of l working parameters of the trailing suction boat on one data point and p-1 data points after the data point, and the data are taken asInputting a sample of a neural network; data set Y new The data is a matrix with N rows and p columns, each row of data represents the effective value of the trailing suction boat on one data point and p-1 data points behind the data point, and the data is used as the output of one sample of the neural network;
s32, dividing the sample into a training set and a testing set; wherein the proportion of the training set and the test set in the total sample is respectively 80% and 20%, and the normalization processing is carried out on the training set and the test set;
s33, constructing a convolutional neural network model: the network structure of the model consists of an input layer, a convolution layer, an activation function layer and two full-connection layers, and a learning rate, an activation function type, iteration times and three hyper-parameters are set;
the size of the input data of the input layer is the product of the number of the filtered working parameters and the step length of the sliding window sequence, namely l x p;
the convolutional layer is provided with 16 filters with the size of 3 multiplied by 3 and used for extracting the characteristics of the working data of the trailing suction ship;
the activation function of the activation function layer selects a Relu activation function, and the formula is as follows:
the full connection layer is used as an output layer, and the unit number of the full connection layer is equal to the step length p of the sliding window sequence;
s34, verifying the accuracy of the model: testing the convolutional neural network model by using samples of the test set, and verifying the accuracy of the model through Root Mean Square Error (RMSE);
wherein Y (i) is the true energy efficiency of the trailing suction vessel, E c And (x (i)) is an energy efficiency predicted value of the trailing suction ship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211300629.9A CN115600746A (en) | 2022-10-24 | 2022-10-24 | Convolutional neural network-based drag suction ship energy efficiency prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211300629.9A CN115600746A (en) | 2022-10-24 | 2022-10-24 | Convolutional neural network-based drag suction ship energy efficiency prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115600746A true CN115600746A (en) | 2023-01-13 |
Family
ID=84849192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211300629.9A Pending CN115600746A (en) | 2022-10-24 | 2022-10-24 | Convolutional neural network-based drag suction ship energy efficiency prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600746A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021878A (en) * | 2006-02-14 | 2007-08-22 | 中国交通建设集团有限公司 | Automatic computerized selecting optimized dredging method for cutter suction dredger |
| EP2535466A1 (en) * | 2011-06-16 | 2012-12-19 | IHC Systems B.V. | Position measurement for a suction tube of a dredger vessel |
| CN110782078A (en) * | 2019-10-18 | 2020-02-11 | 武汉科技大学 | Learning method for predicting mud discharging rate of trailing suction hopper dredger |
| CN112257929A (en) * | 2020-10-23 | 2021-01-22 | 广州中国科学院沈阳自动化研究所分所 | Cutter suction dredging auxiliary decision making system and method |
| CN113642801A (en) * | 2021-08-20 | 2021-11-12 | 江苏科技大学 | Cutter suction dredger yield prediction method based on LSTM |
| CN114091339A (en) * | 2021-11-24 | 2022-02-25 | 江苏科技大学 | Method for predicting bow blowing instantaneous yield of drag suction dredger based on GRU |
| CN114661006A (en) * | 2022-03-03 | 2022-06-24 | 江苏科技大学 | Optimized control system and method for cabin pumping and bank blowing process of trailing suction hopper dredger |
| CN114662782A (en) * | 2022-04-08 | 2022-06-24 | 江苏科技大学 | Method for predicting instantaneous yield of trailing suction hopper dredger based on LSTM neural network |
| CN115169644A (en) * | 2022-06-13 | 2022-10-11 | 中国船舶工业集团公司第七0八研究所 | Energy consumption prediction method and system for dredger |
-
2022
- 2022-10-24 CN CN202211300629.9A patent/CN115600746A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021878A (en) * | 2006-02-14 | 2007-08-22 | 中国交通建设集团有限公司 | Automatic computerized selecting optimized dredging method for cutter suction dredger |
| EP2535466A1 (en) * | 2011-06-16 | 2012-12-19 | IHC Systems B.V. | Position measurement for a suction tube of a dredger vessel |
| CN110782078A (en) * | 2019-10-18 | 2020-02-11 | 武汉科技大学 | Learning method for predicting mud discharging rate of trailing suction hopper dredger |
| CN112257929A (en) * | 2020-10-23 | 2021-01-22 | 广州中国科学院沈阳自动化研究所分所 | Cutter suction dredging auxiliary decision making system and method |
| CN113642801A (en) * | 2021-08-20 | 2021-11-12 | 江苏科技大学 | Cutter suction dredger yield prediction method based on LSTM |
| CN114091339A (en) * | 2021-11-24 | 2022-02-25 | 江苏科技大学 | Method for predicting bow blowing instantaneous yield of drag suction dredger based on GRU |
| CN114661006A (en) * | 2022-03-03 | 2022-06-24 | 江苏科技大学 | Optimized control system and method for cabin pumping and bank blowing process of trailing suction hopper dredger |
| CN114662782A (en) * | 2022-04-08 | 2022-06-24 | 江苏科技大学 | Method for predicting instantaneous yield of trailing suction hopper dredger based on LSTM neural network |
| CN115169644A (en) * | 2022-06-13 | 2022-10-11 | 中国船舶工业集团公司第七0八研究所 | Energy consumption prediction method and system for dredger |
Non-Patent Citations (1)
| Title |
|---|
| 朱大鹏等: "基于深度学习的耙吸挖泥船装舱产量预测研究", 《计算机与数字工程》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
| JP2886112B2 (en) | Process operation support method and system | |
| CN113006188B (en) | Excavator staged power matching method based on LSTM neural network | |
| CN109918364B (en) | Data cleaning method based on two-dimensional probability density estimation and quartile method | |
| CN114619292B (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
| CN110826790A (en) | Intelligent prediction method for construction productivity of cutter suction dredger | |
| CN113469951B (en) | Hub defect detection method based on cascade region convolutional neural network | |
| CN113780153A (en) | Cutter wear monitoring and predicting method | |
| CN105045091A (en) | Dredging process intelligent decision analysis method based on fuzzy neural control system | |
| CN114661006A (en) | Optimized control system and method for cabin pumping and bank blowing process of trailing suction hopper dredger | |
| CN115759409A (en) | Water gate deformation prediction method for optimizing LSTM (least Square TM) model by multi-time mode attention mechanism | |
| CN113157732B (en) | Underground scraper fault diagnosis method based on PSO-BP neural network | |
| CN115600746A (en) | Convolutional neural network-based drag suction ship energy efficiency prediction method | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN113374021A (en) | Excavator working condition identification method based on pilot control signal of operating handle | |
| CN112132324A (en) | Ultrasonic water meter data restoration method based on deep learning model | |
| CN113642801A (en) | Cutter suction dredger yield prediction method based on LSTM | |
| CN112307410A (en) | Seawater temperature and salinity information time sequence prediction method based on shipborne CTD measurement data | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| CN114091339A (en) | Method for predicting bow blowing instantaneous yield of drag suction dredger based on GRU | |
| CN114065639A (en) | Closed-loop real-time inversion method for construction parameters of dredger | |
| CN115169644A (en) | Energy consumption prediction method and system for dredger | |
| CN112179455A (en) | Ultrasonic water meter data restoration method based on bidirectional LSTM | |
| Zhang et al. | Energy Efficiency Prediction Model of Suction Hopper Dredger Based on Correlation Analysis and Convolutional Neural Network |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20230113 |
|
| WD01 | Invention patent application deemed withdrawn after publication |