CN116401501A - Dredging operation leakage quantity prediction method and device, electronic equipment and medium - Google Patents
Dredging operation leakage quantity prediction method and device, electronic equipment and medium Download PDFInfo
- Publication number
- CN116401501A CN116401501A CN202310349215.3A CN202310349215A CN116401501A CN 116401501 A CN116401501 A CN 116401501A CN 202310349215 A CN202310349215 A CN 202310349215A CN 116401501 A CN116401501 A CN 116401501A
- Authority
- CN
- China
- Prior art keywords
- leakage
- neural network
- working condition
- leakage quantity
- dredging operation
- 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 45
- 238000003062 neural network model Methods 0.000 claims abstract description 77
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000012795 verification Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- KJONHKAYOJNZEC-UHFFFAOYSA-N nitrazepam Chemical compound C12=CC([N+](=O)[O-])=CC=C2NC(=O)CN=C1C1=CC=CC=C1 KJONHKAYOJNZEC-UHFFFAOYSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004642 transportation engineering Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a dredging operation leakage quantity prediction method, a device, electronic equipment and a medium, wherein the method comprises the following steps: acquiring historical dredging operation data, and preprocessing the historical dredging operation data to obtain a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage quantity of a dredger; creating an initial leakage quantity prediction neural network model, taking working condition parameter data as input and leakage quantity as output, and performing iterative training to obtain a completely trained leakage quantity prediction neural network model; and acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity predicted value of the dredging operation. According to the invention, the neural network model with high fitting degree is obtained by creating the leakage quantity prediction neural network model and training by using the dredging operation data set, so that the technical problems of large error and low prediction accuracy of the theoretical calculation model in the prior art are solved.
Description
Technical Field
The present invention relates to the field of dredging operations, and in particular, to a method and apparatus for predicting leakage of a dredging operation, an electronic device, and a computer readable storage medium.
Background
In modern water conservancy and transportation engineering, dredging engineering is one of the important projects. Modern dredging industries mainly rely on dredgers, and leakage is one of the important criteria for measuring the efficiency of the operations during dredging operations with dredgers. At present, the problem of leakage quantity prediction of dredging engineering is often that constructors pass through a mode of a linear theoretical calculation model through working conditions, but the existing mode of the linear theoretical calculation model is not high enough in fitting degree of the theoretical calculation model, so that historical working condition parameter data cannot be reasonably utilized, the technical problems of large errors and low prediction precision exist, and practical application requirements cannot be met.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method, an apparatus, an electronic device and a computer readable storage medium for predicting the leakage of a dredging operation, so as to solve the technical problems of large error and low prediction accuracy caused by the failure to reasonably utilize the historical working condition parameter data when the leakage of the dredging operation is predicted by a linear theoretical calculation model in the prior art.
In order to solve the above problems, the present invention provides a dredging operation leakage amount prediction method, comprising:
acquiring historical dredging operation data, and preprocessing the historical dredging operation data to obtain a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage of a dredger;
creating an initial leakage quantity prediction neural network model, taking the working condition parameter data as input, taking the leakage quantity as output, and performing iterative training on the initial leakage quantity prediction neural network model to obtain a completely trained leakage quantity prediction neural network model;
and acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity predicted value of dredging operation.
Further, acquiring historical dredging operation data, preprocessing the historical dredging operation data to obtain a dredging operation data set, and comprising:
acquiring historical working condition parameter data and historical leakage affecting the leakage of the dredging operation;
taking the historical working condition parameter data affecting the leakage amount of the dredging operation as an input training sample, taking the historical leakage amount as an output sample, and constructing a dredging operation data set, wherein the dredging operation data set comprises a plurality of groups of training samples, each group of training samples comprises an input sample and an output sample, the input sample is working condition data of a first time period, the output sample is leakage amount of a second time period, and the ending time of the first time period is earlier than the starting time of the second time period;
eliminating training samples with missing data, and eliminating training samples with abnormal data based on Laida criteria;
and carrying out noise reduction operation and normalization processing on all the historical working condition parameter data in the training sample.
Further, the operating condition parameter data includes one or more of: drag head angle, flow, navigational speed, pre-dredging water depth, post-dredging water depth, water flow intensity, construction distance, drag suction power and construction time.
Further, noise reduction operation and normalization processing are performed on all the historical working condition parameter data in the training sample, including:
determining a correlation coefficient of historical working condition parameter data in the training sample based on a Pelson correlation coefficient principle, and eliminating working condition parameters of which the correlation coefficient is lower than a preset correlation threshold;
and converting values of all the historical working condition parameter data in the training sample into a preset range through a normalization function.
Further, creating an initial leakage amount prediction neural network model includes:
creating a network structure comprising an input layer, an hidden layer and an output layer;
the number of neurons of the input layer is the same as the dimension of the working condition parameter data, the number of neurons of the output layer is the same as the dimension of the leakage quantity, and the transfer function of neurons of the hidden layer is a tangent function.
Further, the working condition parameter data of the dredger is taken as input, the leakage amount is taken as output, and the initial leakage amount prediction neural network model is subjected to iterative training to obtain a completely trained leakage amount prediction neural network model, which comprises the following steps:
dividing a dredging operation data set into a training set and a verification set;
taking working condition parameter data of the training set as input, taking leakage quantity of the training set as output, and carrying out iterative training on an initial leakage quantity prediction neural network model;
determining at least one difference evaluation value of a leakage quantity predicted value and a true value of the leakage quantity predicted neural network model through a verification set;
and if the difference evaluation value is not within the preset accuracy threshold, repeating the iterative training process until the difference evaluation value reaches the accuracy threshold, and obtaining a completely trained leakage quantity prediction neural network model.
Further, determining, by the verification set, at least one difference evaluation value of the leakage amount predicted value and the true value of the leakage amount predicted neural network model, including:
obtaining a leakage quantity predicted value of a verification set sample according to the leakage quantity predicted neural network model and the verification set;
calculating according to the leakage quantity predicted value and the true value to obtain a relative error and a decision coefficient;
if the relative error is smaller than a preset relative error accuracy threshold and the decision coefficient is larger than a preset decision coefficient accuracy threshold, the prediction performance of the leakage quantity prediction neural network model meets the requirements.
The invention also provides a dredging operation leakage quantity prediction device, which comprises:
a data acquisition unit for acquiring a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage quantity of the dredger;
the model training unit is used for creating an initial leakage quantity prediction neural network model, taking working condition parameter data of the dredger as input, taking the leakage quantity as output, and carrying out iterative training on the initial leakage quantity prediction neural network model to obtain a completely trained leakage quantity prediction neural network model;
the leakage quantity prediction unit is used for acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity prediction value of the dredging operation.
The invention also provides an electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor is coupled with the memory and is used for executing the program stored in the memory so as to realize the steps in the dredging operation leakage prediction method.
The present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the dredging job leakage prediction method of any of the above.
Compared with the prior art, the invention has the beneficial effects that: firstly, acquiring a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage quantity of a dredger; then, an initial leakage quantity prediction neural network model is established, the working condition parameter data is taken as input, the leakage quantity is taken as output, and iterative training is carried out on the initial leakage quantity prediction neural network model, so that a completely trained leakage quantity prediction neural network model is obtained; and finally, acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity prediction value of dredging operation. According to the embodiment of the invention, the leakage quantity prediction neural network model is obtained by creating the leakage quantity prediction neural network model and training the obtained dredging operation data set, so that the technical problems of large error and low prediction precision caused by the fact that the theoretical calculation model in the prior art cannot reasonably utilize the historical working condition parameter data are solved.
Drawings
FIG. 1 is a flow chart of one embodiment of a dredging operation leakage prediction method provided by the present invention;
FIG. 2 is a flowchart illustrating an embodiment of the step S101;
FIG. 3 is a schematic view of an embodiment of a dredging operation leakage predicting device according to the present invention;
fig. 4 is a schematic structural diagram of an embodiment of an electronic device provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a schematic flow chart of a dredging operation leakage amount prediction method provided by the invention, and as shown in fig. 1, the dredging operation leakage amount prediction method includes:
s101, acquiring historical dredging operation data, and preprocessing the historical dredging operation data to obtain a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage of a dredger;
s102, creating an initial leakage quantity prediction neural network model, taking the working condition parameter data as input and the leakage quantity as output, and performing iterative training on the initial leakage quantity prediction neural network model to obtain a completely trained leakage quantity prediction neural network model;
s103, acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity prediction value of dredging operation.
In a specific embodiment, the working condition parameters are various parameters affecting the leakage amount of the dredging operation; the initial leakage amount neural network can be a BP neural network, a convolution neural network or other neural networks; the working condition data of the dredger can be obtained through on-line monitoring equipment, and also can be obtained through log files of the previous dredging operation; the leakage amount refers to the leakage amount of the dredging operation, and the leakage amount reflects the working efficiency of the dredging operation to a great extent.
Compared with the prior art, the method comprises the steps of firstly acquiring historical dredging operation data, and preprocessing the historical dredging operation data to obtain a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage of a dredger; then, an initial leakage quantity prediction neural network model is established, the working condition parameter data is taken as input, the leakage quantity is taken as output, and iterative training is carried out on the initial leakage quantity prediction neural network model, so that a completely trained leakage quantity prediction neural network model is obtained; and finally, acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity prediction value of dredging operation. According to the embodiment of the invention, the leakage quantity prediction neural network model is obtained by creating the leakage quantity prediction neural network model and training the obtained dredging operation data set, so that the technical problems of large error and low prediction precision caused by the fact that the theoretical calculation model in the prior art cannot reasonably utilize the historical working condition parameter data are solved.
In a specific embodiment of the present invention, step S101, as shown in fig. 2, includes:
s201, acquiring historical working condition parameter data affecting the leakage amount of the dredging operation;
s202, taking the historical working condition parameter data affecting the leakage amount of the dredging operation as an input training sample, taking the historical leakage amount as an output sample, and constructing a dredging operation data set, wherein the dredging operation data set comprises a plurality of groups of training samples, each group of training samples comprises the input sample and the output sample, the input sample is working condition data of a first time period, the output sample is leakage amount of a second time period, and the ending time of the first time period is earlier than the starting time of the second time period;
s203, eliminating training samples with missing data, and eliminating training samples with abnormal data based on Laida criteria;
s204, performing noise reduction operation and normalization processing on all the historical working condition parameter data in the training sample.
Specifically, in the process of acquiring historical dredging operation data and preprocessing the historical dredging operation data to obtain a dredging operation data set, detection data of working condition parameters affecting the leakage amount of the dredging operation, including the working condition parameters and the leakage amount, is collected through a detection device or a historical log file.
Grouping the acquired working condition parameters and leakage according to time periods, dividing the working condition data of each time period into the same group of training samples corresponding to the leakage of the next time period, and forming the working condition data into a data matrix X= (X) ij ) n×p ＝(x 1 ,x 2 ,…,x p ) i=1, 2 …, n; j=1, 2, …, p, where n is the number of samples and p is the leakage affecting the dredging operationNumber of operating parameters of quantity x ij Representing the j-th operating condition parameter in the i-th training sample.
The training samples are then subjected to data preprocessing, including: missing data processing, outlier processing, noise reduction processing, and normalization processing. In the case where missing data and abnormal data occur, the set of samples is directly removed. For the standard of the abnormal data, the abnormal data is rejected according to 3 sigma criterion (Laida criterion): that is, the random distribution can be regarded as normal or nearly normal sample data, and if only random errors are included, the mean μ and standard deviation σ are calculated, and a section (μ -3σ, μ+3σ) is determined, and errors exceeding this section are considered to be not random errors but coarse errors, and data including the errors should be eliminated.
In a specific embodiment of the invention, the operating parameters include one or more of the following: drag head angle, flow, navigational speed, pre-dredging water depth, post-dredging water depth, water flow intensity, construction distance, drag suction power and construction time.
Specifically, the working condition parameters are selected according to the specific construction condition of the dredger, not all the parameters listed above are of the same type, and more working condition parameters can be added according to the types of the dredger and the actual influencing factors of the construction site.
In a specific embodiment of the present invention, performing noise reduction operation and normalization processing on all the historical operating condition parameter data in the training sample includes:
determining a correlation coefficient of historical working condition parameter data in the training sample based on a Pelson correlation coefficient principle, and eliminating working condition parameters of which the correlation coefficient is lower than a preset correlation threshold;
and converting values of all the historical working condition parameter data in the data matrix into a preset range through a normalization function to obtain a dredging operation data set meeting the requirements.
Specifically, for the original data, because when the parameters are selected, data with excessive parameters and little effect on the prediction result may occur, it is necessary to calculate and obtain the correlation coefficient between each working condition parameter and the leakage amount in the training sample based on the pearson correlation coefficient principle, preset the correlation threshold value, and reject the parameters with low correlation coefficient in the working condition parameters.
It should be noted that, the pearson correlation coefficient principle is a method for measuring the strength of the correlation between two parameters, and judges whether there is positive or negative correlation and the magnitude of the correlation between the two parameters according to the calculated correlation coefficient value.
In addition, in order to eliminate the order-of-magnitude difference between the data of each parameter, the problem that the network prediction error is large because the order-of-magnitude difference between the input data and the output data is large is avoided, normalization processing is needed to be carried out on the working condition parameters, all parameter values are converted into the range of [0,1], a normalization function is established based on a maximum and minimum method, and the function is as follows:
X d ＝(X d -X min )/(X max -X min )
wherein X is d For normalized parameter values, X max 、X min Is the maximum and minimum value of the parameters.
In a specific embodiment of the present invention, creating an initial leakage amount prediction neural network model includes:
creating a network structure comprising an input layer, an hidden layer and an output layer;
the number of neurons of the input layer is the same as the dimension of the working condition parameter, the number of neurons of the output layer is the same as the dimension of the leakage quantity, and the neuron transfer function of the hidden layer is a tangent function.
Specifically, in the created three-layer network structure, the relationship between the number l of hidden layer neural networks, the number n of input layer neurons and the number m of output layer neurons is as follows:
wherein alpha is an adjustment constant between 1 and 10.
The number n of the neurons of the input layer is the same as the dimension of the input working condition parameters; the number m of the neurons of the output layer is the same as the dimension of the output leakage quantity; the neuron transfer function of the hidden layer is the sigmoid tangent function tansig ().
In a specific embodiment of the present invention, with working condition parameter data of a dredger as input and leakage amount as output, iterative training is performed on an initial leakage amount prediction neural network model to obtain a completely trained leakage amount prediction neural network model, including:
dividing a dredging operation data set into a training set and a verification set;
taking working condition parameter data of the training set as input, taking leakage quantity of the training set as output, and carrying out iterative training on an initial leakage quantity prediction neural network model;
determining at least one difference evaluation value of a leakage quantity predicted value and a true value of the leakage quantity predicted neural network model through a verification set;
and if the difference evaluation value is not within the preset accuracy threshold, repeating the iterative training process until the difference evaluation value reaches the accuracy threshold, and obtaining a completely trained leakage quantity prediction neural network model.
Specifically, in the iterative training process of the leakage quantity prediction neural network model, a dredging operation data set is firstly randomly divided into a training set and a verification set according to a certain proportion; the training set is used for training the leakage quantity prediction neural network model, and the verification set is used for verifying the performance of the trained network model.
Taking working condition parameter data of the training set as input and leakage quantity as output, and carrying out iterative training on an initial leakage quantity prediction neural network model; the accuracy threshold can be set according to the accuracy requirement of the operation process on the model, and the difference evaluation value of the predicted value and the true value is obtained through the verification set, so that the prediction performance of the leakage quantity prediction neural network model is judged; if the difference evaluation value is not within the predicted accuracy threshold, the predicted performance of the leakage quantity predicted neural network model is considered to fail to meet the requirement, and the iterative training process is continued until the difference evaluation value reaches the accuracy threshold, so that the completely trained leakage quantity predicted neural network model is obtained.
In a specific embodiment of the present invention, determining at least one difference evaluation value of the leakage amount predicted value and the true value of the leakage amount predicted neural network model by the verification set includes:
obtaining a leakage quantity predicted value of a verification set sample according to the leakage quantity predicted neural network model and the verification set;
calculating according to the leakage quantity predicted value and the true value to obtain a relative error and a decision coefficient;
if the relative error is smaller than a preset relative error accuracy threshold and the decision coefficient is larger than a preset decision coefficient accuracy threshold, the prediction performance of the leakage quantity prediction neural network model meets the requirements.
Specifically, the difference evaluation value for evaluating the prediction performance of the leakage amount prediction neural network model includes a relative error and a determination coefficient, and the calculation formulas are respectively:
wherein E is k As relative error, R 2 To determine the coefficients, q is the total number of samples,
is the predicted value of the kth sample, y k Is the true value of the kth sample.
In the process of judging the predicted performance of the model, the smaller the relative error is, the better the performance of the surface model is; the more the coefficient is determined to be within the range of [0,1], the better the surface model performance is as the coefficient is closer to 1; if the relative error is smaller than a preset relative error accuracy threshold and the decision coefficient is larger than a preset decision coefficient accuracy threshold, the prediction performance of the leakage quantity prediction neural network model is considered to be in accordance with the requirements, and the leakage quantity prediction neural network model can be used for carrying out leakage quantity prediction.
In order to better implement the dredging operation leakage amount prediction method according to the embodiment of the present invention, on the basis of the dredging operation leakage amount prediction method, the present invention further provides a dredging operation leakage amount prediction apparatus 300, as shown in the drawings, including:
a data acquisition unit 301 for acquiring a dredging operation data set including working condition parameter data and leakage amount of the dredger;
the model training unit 302 is configured to create an initial leakage amount prediction neural network model, take the working condition parameter data as input, and take the leakage amount as output, and perform iterative training on the initial leakage amount prediction neural network model to obtain a completely trained leakage amount prediction neural network model;
the leakage predicting unit 303 is configured to obtain real-time working condition parameter data of the dredger, and input the real-time working condition parameter data into a well-trained leakage predicting neural network model to obtain a leakage predicted value of the dredging operation.
The dredging operation leakage amount prediction apparatus 300 provided in the foregoing embodiment may implement the technical solution described in the foregoing dredging operation leakage amount prediction method embodiment, and the specific implementation principle of each module or unit may refer to the corresponding content in the foregoing dredging operation leakage amount prediction method embodiment, which is not described herein.
The present invention also provides an electronic device based on a dredging operation leakage amount prediction method, as shown in fig. 4, fig. 4 is a schematic structural diagram of an embodiment of the electronic device provided by the present invention, and the electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and capable of running on the processor 401, where the processor 401 executes the program to implement the dredging operation leakage amount prediction method as described above.
As a preferred embodiment, the above-mentioned electronic device further comprises a display 403 for displaying the execution of the dredging job leakage amount prediction method process described above by the processor 401.
The processor 401 may be an integrated circuit chip with signal processing capability. The processor 401 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC). The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may also be a microprocessor or the processor may be any conventional processor or the like.
The Memory 402 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a Secure Digital (SD Card), a Flash Card (Flash Card), etc. The memory 402 is configured to store a program, and the processor 401 executes the program after receiving an execution instruction, and the method for defining a flow disclosed in any one of the foregoing embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.
The display 403 may be an LED display, a liquid crystal display, a touch display, or the like. The display 403 is used to display various information on the electronic device 400.
It is to be appreciated that the configuration shown in fig. 4 is merely a schematic diagram of one configuration of the electronic device 400, and that the electronic device 400 may include more or fewer components than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a dredging job leakage amount prediction method as described above.
In general, the computer instructions for carrying out the methods of the present invention may be carried in any combination of one or more computer-readable storage media. The non-transitory computer-readable storage medium may include any computer-readable medium, except the signal itself in temporary propagation.
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 the context of 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 present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A method for predicting leakage of a dredging operation, comprising:
acquiring historical dredging operation data, and preprocessing the historical dredging operation data to obtain a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage of a dredger;
creating an initial leakage quantity prediction neural network model, taking the working condition parameter data as input, taking the leakage quantity as output, and performing iterative training on the initial leakage quantity prediction neural network model to obtain a completely trained leakage quantity prediction neural network model;
and acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity predicted value of dredging operation.
2. Dredging operation leakage prediction method according to claim 1, wherein the acquiring historical dredging operation data, preprocessing the historical dredging operation data to obtain a dredging operation data set, comprises:
acquiring historical working condition parameter data and historical leakage affecting the leakage of the dredging operation;
taking the historical working condition parameter data affecting the leakage quantity of the dredging operation as an input training sample, taking the historical leakage quantity as an output sample, and constructing a dredging operation data set, wherein the dredging operation data set comprises a plurality of groups of training samples, each group of training samples comprises an input sample and an output sample, the input sample is working condition data of a first time period, the output sample is leakage quantity of a second time period, and the ending time of the first time period is earlier than the starting time of the second time period;
eliminating training samples with missing data, and eliminating training samples with abnormal data based on Laida criteria;
and carrying out noise reduction operation and normalization processing on all the historical working condition parameter data in the training sample.
3. The dredging operation leakage prediction method according to claim 2, wherein the operating condition parameter data comprises one or more of the following: drag head angle, flow, navigational speed, pre-dredging water depth, post-dredging water depth, water flow intensity, construction distance, drag suction power and construction time.
4. The dredging job leakage prediction method according to claim 2, wherein the noise reduction and normalization process is performed on all the historical operating condition parameter data in the training samples, including:
determining a correlation coefficient of historical working condition parameter data in the training sample based on a Pelson correlation coefficient principle, and eliminating working condition parameters of which the correlation coefficient is lower than a preset correlation threshold;
and converting values of all the historical working condition parameter data in the training sample into a preset range through a normalization function.
5. The dredging job leakage prediction method according to claim 1, wherein the creating an initial leakage prediction neural network model comprises:
creating a network structure comprising an input layer, an hidden layer and an output layer;
the number of the neurons of the input layer is the same as the dimension of the working condition parameter data, the number of the neurons of the output layer is the same as the dimension of the leakage quantity, and the neuron transfer function of the hidden layer is a tangent function.
6. The dredging operation leakage amount prediction method according to claim 1, wherein the step of performing iterative training on the initial leakage amount prediction neural network model with the working condition parameter data of the dredger as input and the leakage amount as output to obtain a fully trained leakage amount prediction neural network model comprises:
dividing a dredging operation data set into a training set and a verification set;
taking working condition parameter data of the training set as input, taking leakage quantity of the training set as output, and carrying out iterative training on an initial leakage quantity prediction neural network model;
determining at least one difference evaluation value of a leakage quantity predicted value and a true value of the leakage quantity predicted neural network model through a verification set;
and if the difference evaluation value is not within the preset accuracy threshold, repeating the iterative training process until the difference evaluation value reaches the accuracy threshold, and obtaining a completely trained leakage quantity prediction neural network model.
7. The dredging operation leakage amount prediction method according to claim 6, wherein the determining, by the verification set, at least one difference evaluation value of a leakage amount prediction value and a true value of a leakage amount prediction neural network model includes:
obtaining a leakage quantity predicted value of a verification set sample according to the leakage quantity predicted neural network model and the verification set;
calculating according to the leakage quantity predicted value and the true value to obtain a relative error and a decision coefficient;
if the relative error is smaller than a preset relative error accuracy threshold and the decision coefficient is larger than a preset decision coefficient accuracy threshold, the prediction performance of the leakage quantity prediction neural network model meets the requirements.
8. A dredging operation leakage amount prediction apparatus, comprising:
a data acquisition unit for acquiring a dredging operation data set, wherein the dredging operation data set comprises working condition parameter data and leakage quantity of the dredger;
the model training unit is used for creating an initial leakage quantity prediction neural network model, taking the working condition parameter data as input and the leakage quantity as output, and carrying out iterative training on the initial leakage quantity prediction neural network model to obtain a completely trained leakage quantity prediction neural network model;
the leakage quantity prediction unit is used for acquiring real-time working condition parameter data of the dredger, and inputting the real-time working condition parameter data into a well-trained leakage quantity prediction neural network model to obtain a leakage quantity prediction value of the dredging operation.
9. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled to the memory, for executing the program stored in the memory to implement the steps in the dredging job leakage prediction method according to any one of the preceding claims 1 to 7.
10. A computer readable storage medium, having stored thereon a computer program which, when executed by a processor, implements a dredging job leakage amount prediction method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310349215.3A CN116401501A (en) | 2023-03-30 | 2023-03-30 | Dredging operation leakage quantity prediction method and device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310349215.3A CN116401501A (en) | 2023-03-30 | 2023-03-30 | Dredging operation leakage quantity prediction method and device, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116401501A true CN116401501A (en) | 2023-07-07 |
Family
ID=87017322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310349215.3A Pending CN116401501A (en) | 2023-03-30 | 2023-03-30 | Dredging operation leakage quantity prediction method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116401501A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236511A (en) * | 2023-09-26 | 2023-12-15 | 中交广州航道局有限公司 | Big data prediction method and device for vacuum degree of underwater pump of cutter suction dredger |
-
2023
- 2023-03-30 CN CN202310349215.3A patent/CN116401501A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236511A (en) * | 2023-09-26 | 2023-12-15 | 中交广州航道局有限公司 | Big data prediction method and device for vacuum degree of underwater pump of cutter suction dredger |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034244B (en) | Line loss abnormity diagnosis method and device based on electric quantity curve characteristic model | |
| CN105512799B (en) | Power system transient stability evaluation method based on mass online historical data | |
| US7593804B2 (en) | Fixed-point virtual sensor control system and method | |
| CN116401501A (en) | Dredging operation leakage quantity prediction method and device, electronic equipment and medium | |
| CN111241755A (en) | Power load prediction method | |
| WO2021104216A1 (en) | Method and device for evaluating device model trend similarity | |
| CN113742993A (en) | Method, device, equipment and storage medium for predicting life loss of dry-type transformer | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN112215398A (en) | Power consumer load prediction model establishing method, device, equipment and storage medium | |
| CN115099135A (en) | Improved artificial neural network multi-type operation power consumption prediction method | |
| CN111047476A (en) | Dam structure safety monitoring accurate prediction method and system based on RBF neural network | |
| CN112949697A (en) | Method and device for confirming pipeline abnormity and computer readable storage medium | |
| CN115841343B (en) | Sales limit determining method and device | |
| CN112199850A (en) | Method for researching system elastic distribution rule based on process characteristics | |
| CN111062133A (en) | Wind turbine generator performance analysis method and system | |
| CN116247655A (en) | Wind power output prediction method, system, storage medium and equipment | |
| CN115438312A (en) | Probability distribution model establishment and application method and medium for new energy output | |
| CN115564410A (en) | State monitoring method and device for relay protection equipment | |
| CN113762795A (en) | Industrial chain diagnosis method and system based on hierarchical analysis | |
| CN114399371A (en) | Method and device for detecting behavior of surrounding string label, computer equipment and storage medium | |
| CN105809304A (en) | Method for analyzing correlation of production and operation parameters of power plant and pollution treatment facility | |
| CN117850403B (en) | Dynamic detection method for initiating and controlling system | |
| CN113878613B (en) | Industrial robot harmonic reducer early fault detection method based on WLCTD and OMA-VMD | |
| CN113610333A (en) | Hydraulic engineering construction quality inspection method and device, electronic equipment and storage medium | |
| CN115545191B (en) | Current noise reduction network model training method and fault current limiter current noise reduction method |
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 |