CN114037551A - Pond culture pH value missing data interpolation method - Google Patents

Pond culture pH value missing data interpolation method Download PDF

Info

Publication number
CN114037551A
CN114037551A CN202111347638.9A CN202111347638A CN114037551A CN 114037551 A CN114037551 A CN 114037551A CN 202111347638 A CN202111347638 A CN 202111347638A CN 114037551 A CN114037551 A CN 114037551A
Authority
CN
China
Prior art keywords
data
representing
lstm
model
improved lstm
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
Application number
CN202111347638.9A
Other languages
Chinese (zh)
Inventor
刘世晶
钱程
涂雪滢
李国栋
汤涛林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fishery Machinery and Instrument Research Institute of CAFS
Original Assignee
Fishery Machinery and Instrument Research Institute of CAFS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fishery Machinery and Instrument Research Institute of CAFS filed Critical Fishery Machinery and Instrument Research Institute of CAFS
Priority to CN202111347638.9A priority Critical patent/CN114037551A/en
Publication of CN114037551A publication Critical patent/CN114037551A/en
Pending legal-status Critical Current

Links

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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/048—Activation functions
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Agronomy & Crop Science (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Animal Husbandry (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Complex Calculations (AREA)

Abstract

The invention provides a pond culture pH value missing data interpolation method, which comprises the following steps: s1: preprocessing data; s2: establishing an improved LSTM model; s3: establishing a pH value interpolation model based on the improved LSTM by using the improved LSTM model; s4: and evaluating the pH value interpolation model based on the improved LSTM. The invention discloses a pond culture pH value missing data interpolation method, which utilizes the existing water quality data and meteorological data and utilizes an improved LSTM method to construct a pond pH value interpolation model so as to realize the interpolation of pH value missing data.

Description

Pond culture pH value missing data interpolation method
Technical Field
The invention relates to the field of data interpolation methods, in particular to a pond culture pH value missing data interpolation method.
Background
At present, a method for realizing interpolation of pH value missing data by using the existing water quality data and meteorological data is lacked.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a pond culture pH value missing data interpolation method, which utilizes the existing water quality data and meteorological data and utilizes an improved LSTM method to construct a pond pH value interpolation model so as to realize the interpolation of the pH value missing data.
In order to achieve the aim, the invention provides a pond culture pH value missing data interpolation method, which comprises the following steps:
s1: preprocessing data;
s2: establishing an improved LSTM model;
s3: establishing a pH value interpolation model based on the improved LSTM by using the improved LSTM model;
s4: and evaluating the pH value interpolation model based on the improved LSTM.
Preferably, the step of S1 further comprises the steps of:
s11: fixing the sampling frequency of at least one water quality sensor, and acquiring meteorological data of a meteorological station and water quality data of the water quality sensor by constructing a pond culture internet of things system;
s12: repairing the meteorological data and the water quality data with missing values less than or equal to 2 sampling time intervals by adopting a linear interpolation method;
s13: detecting and repairing abnormal values;
s14: and carrying out normalization processing on the meteorological data and the water quality data.
Preferably, in the step S14, the data is normalized by formula (1):
Figure BDA0003354592980000021
wherein x isiDenotes the feature vector at a particular time length index i, min denotes the minimum value in the data, and max denotes the maximum value in the data.
Preferably, the input to the improved LSTM model is a variable length sequence x ═ xiIn which xiIndexing at i for a particular length of timeFeature vector, then the hidden state at time index t is updated as follows:
int＝σ(Wxinxt+Whinht-1+bin)
ft＝σ(Wxfxt+Whfht-1+bf)
Figure BDA0003354592980000022
ot＝σ(Wxoxt+Whoht-1+bo)
Figure BDA0003354592980000023
therein, intRepresenting the input gate at time index t, ftIndicating a forgetting gate at time index t, otRepresents the output gate at time index t; c. CtRepresents the unit vector at time index t; sigma represents a sigmoid function;
Figure BDA0003354592980000024
representing element multiplication; the first parameter W and the second parameter b map the cascade to the size of the hidden state; h istRepresenting hidden states of the model output; wxinRepresenting an input gate input weight; x is the number oftRepresenting input gate input at time t; whinRepresenting input layer hidden state weights; binRepresenting input gate bias; wxfRepresenting forgetting layer input weights; whfRepresenting a forgotten door hidden state weight; bfThe representation represents a forgetting gate bias; wxcRepresenting hidden state weights at the time index; whcRepresenting a time indexed hidden state weight; bcRepresents a bias at the time index; wxoRepresenting output gate input weights; whoRepresenting an output gate hidden state weight; boRepresents the output gate offset;
the decoder of the improved LSTM model is responsible for deliveryGenerating an output sequence y ═ y1, y2m-adding a fully connected layer with a linear activation function on top of the LSTM layer to generate a prediction with continuous values; for the decoder, the estimate y at time index ttThe calculation is as follows:
yt＝Linear(W[st，ct]+b)
st＝LSTM(yt-1，st-1，ct)
wherein s istIs the hidden state of the decoder at time index t, ct is the weighted sum of the hidden states passed by the encoder, [ st, ct]Is a concatenation of decoder hidden state and context vector; LSTM (Long ShortTerm memory) means that decoding operation is performed by using an LSTM network; linear denotes a recursion-based fully-connected operation.
Preferably, the step of S3 further comprises the steps of:
s31: acquiring meteorological data of a meteorological station and water quality data of a water quality sensor by constructing a pond culture internet of things system;
s32: carrying out standardization and normalization pretreatment on the meteorological data and the water quality data according to the time series analysis requirements;
s33: constructing a training set and a testing set by using the current meteorological data and the water quality data;
s34: training the improved LSTM model by using the training set until the output of the improved LSTM model reaches the target accuracy, and obtaining the pH value interpolation model based on the improved LSTM;
s35: and verifying the precision of the pH value interpolation model based on the improved LSTM by using the test set, and verifying the effectiveness of the pH value interpolation model based on the improved LSTM.
Preferably, in the step S4, the modified LSTM-based pH interpolation model is evaluated by using a root mean square error, an average absolute error and an average absolute percentage error.
Preferably, the root mean square error RMSE, the mean absolute error MAE, and the mean absolute percentage error MAPE satisfy the formula:
Figure BDA0003354592980000031
Figure BDA0003354592980000032
Figure BDA0003354592980000041
wherein, yiIn order to measure the dissolved oxygen content,
Figure BDA0003354592980000042
for prediction, N is the number of missing samples.
Preferably, the improved LSTM model uses a pytouch neural network framework;
the number of the encoder hidden layers of the improved LSTM model is 1;
the number of decoder hidden layers of the improved LSTM model is 2;
the number of LSTM hidden units in each layer of the improved LSTM model is 20;
the loss rate of the improved LSTM model is 0.2;
the optimizer of the improved LSTM model adopts Adam;
the loss function of the improved LSTM model adopts MSE;
the skin size of the modified LSTM model was 60.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
the invention realizes the interpolation of pH value missing data by establishing a pH value interpolation model based on the improved LSTM and utilizing the existing water quality data and meteorological data.
Drawings
FIG. 1 is a flow chart of a method for interpolating missing pH data in pond culture according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a network structure of an improved LSTM model according to an embodiment of the present invention;
FIG. 3 is a flow chart of establishing a pH interpolation model based on modified LSTM according to an embodiment of the present invention.
Detailed Description
The following description of the preferred embodiments of the present invention will be provided in conjunction with the accompanying drawings, which are set forth in detail below to provide a better understanding of the function and features of the invention.
Referring to fig. 1 to 3, a method for interpolating missing pH data of pond culture according to an embodiment of the present invention includes:
s1: preprocessing data;
the step of S1 further includes the steps of:
s11: fixing the sampling frequency of at least one water quality sensor, and acquiring meteorological data of a meteorological station and water quality data of the water quality sensor by constructing a pond culture internet of things system;
s12: repairing meteorological data and water quality data with missing values less than or equal to 2 sampling time intervals by adopting a linear interpolation method;
s13: detecting and repairing abnormal values;
s14: and carrying out normalization processing on the meteorological data and the water quality data.
In the step S14, the data is normalized by the formula (1):
Figure BDA0003354592980000051
wherein x isiDenotes the feature vector at a particular time length index i, min denotes the minimum value in the data, and max denotes the maximum value in the data.
In the actual sampling process, the sampling frequency of the sensor is fixed, and the collected water quality data and the collected meteorological data have the same distribution characteristics; aiming at the conditions that a sensor network is influenced by signal interference, network delay and human factors and random data is missing, abnormal and the like, the data with missing values less than or equal to 2 sampling time intervals is repaired by adopting a linear interpolation method in order to ensure the integrity of a data repair time sequence, and abnormal values are detected and repaired. And finally, carrying out normalization processing on the data by adopting a formula (1).
S2: establishing an improved LSTM model;
the input to the improved LSTM model is the variable length sequence x ═ xiIn which xiFor a feature vector at a specific time length index i, the hidden state at time index t is updated as follows:
int＝σ(Wxinxt+Whinht-1+bin)
ft＝σ(Wxfxt+Whfht-1+bf)
Figure BDA0003354592980000052
ot＝σ(Wxoxt+Whoht-1+bo)
Figure BDA0003354592980000053
wherein itRepresenting the input gate at time index t, ftIndicating a forgetting gate at time index t, otRepresents the output gate at time index t; c. CtRepresents the unit vector at time index t; sigma represents a sigmoid function;
Figure BDA0003354592980000054
representing element multiplication; the first parameter W and the second parameter b map the cascade to the size of the hidden state; h istRepresenting hidden states representing model outputs; wxinRepresenting an input gate input weight; x is the number oftRepresenting input gate input at time t; whinRepresenting input layer hidden state weights; binRepresenting input gate bias; wxfRepresenting forgetting layer input weights; whfRepresenting a forgotten door hidden state weight; bfThe representation represents a forgetting gate bias; wxcRepresenting hidden state weights at the time index; whcRepresenting a time indexed hidden state weight; bcRepresents a bias at the time index; wxoRepresenting output gate input weights; whoRepresenting an output gate hidden state weight; boRepresents the output gate offset;
the decoder that improves the LSTM model is responsible for recursively generating the output sequence y ═ { y1, y2m-adding a fully connected layer with a linear activation function on top of the LSTM layer to generate a prediction with continuous values; for the decoder, the estimate yt at time index t is calculated as follows:
yt＝Linear(W[st，ct]+b)
st＝LSTM(yt-1，st-1，ct)
wherein s istIs the hidden state of the decoder at time index t, ct is the weighted sum of the hidden states passed by the encoder, [ st, ct]Is a concatenation of decoder hidden state and context vector; LSTM (Long ShortTerm memory) means that decoding operation is performed by using an LSTM network; linear denotes a recursion-based fully-connected operation.
S3: establishing a pH value interpolation model based on the improved LSTM by using the improved LSTM model;
the step of S3 further includes the steps of:
s31: acquiring meteorological data of a meteorological station and water quality data of a water quality sensor by constructing a pond culture internet of things system;
s32: carrying out standardization and normalization pretreatment on meteorological data and water quality data according to the time series analysis requirements;
s33: constructing a training set and a testing set by using the current meteorological data and water quality data;
s34: training the improved LSTM model by using a training set until the output of the improved LSTM model reaches a target accuracy rate, and obtaining a pH value interpolation model based on the improved LSTM;
s35: and verifying the precision of the pH value interpolation model based on the improved LSTM by using the test set, and verifying the effectiveness of the pH value interpolation model based on the improved LSTM.
S4: the pH interpolation model based on modified LSTM was evaluated.
And in the step S4, the pH value interpolation model based on the improved LSTM is evaluated by adopting the root mean square error, the average absolute error and the average absolute percentage error.
The root mean square error RMSE, the mean absolute error MAE, and the mean absolute percentage error MAPE satisfy the formula:
Figure BDA0003354592980000071
Figure BDA0003354592980000072
Figure BDA0003354592980000073
wherein yi is the measured dissolved oxygen content,
Figure BDA0003354592980000074
for prediction, N is the number of missing samples.
Improving LSTM model parameters
The structure of the improved LSTM model also needs to be determined. The hyper-parameters include the number of hidden layers, the number of hidden LSTM units in each layer, loss rate, loss function, etc.
In the embodiment, the improved LSTM model is realized and optimized by using a pytouch neural network framework;
the number of the encoder hidden layers of the improved LSTM model is 1;
the number of decoder hidden layers of the improved LSTM model is 2;
the number of LSTM hidden units of each layer of the improved LSTM model is 20;
the loss rate of the improved LSTM model is 0.2;
adam is adopted as an optimizer for improving the LSTM model;
MSE is adopted to improve the loss function of the LSTM model;
the skin size of the modified LSTM model was 60.
The mean square error is a mathematically well-behaved function, allows smooth differentiation and allows easy calculation of the gradient. Therefore, MSE is chosen as a loss function for training SSIM.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.

Claims (8)

1. A pond culture pH value missing data interpolation method comprises the following steps:
s1: preprocessing data;
s2: establishing an improved LSTM model;
s3: establishing a pH value interpolation model based on the improved LSTM by using the improved LSTM model;
s4: and evaluating the pH value interpolation model based on the improved LSTM.
2. The method for interpolating pH missing data in pond culture according to claim 1, wherein the step of S1 further comprises the steps of:
s11: fixing the sampling frequency of at least one water quality sensor, and acquiring meteorological data of a meteorological station and water quality data of the water quality sensor by constructing a pond culture internet of things system;
s12: repairing the meteorological data and the water quality data with missing values less than or equal to 2 sampling time intervals by adopting a linear interpolation method;
s13: detecting and repairing abnormal values;
s14: and carrying out normalization processing on the meteorological data and the water quality data.
3. The method for interpolating pH missing data in pond culture according to claim 2, wherein in the step S14, the data is normalized by the formula (1):
Figure FDA0003354592970000011
wherein x isiDenotes the feature vector at a particular time length index i, min denotes the minimum value in the data, and max denotes the maximum value in the data.
4. The method for interpolating pH value missing data in pond culture according to claim 3, wherein the input of the improved LSTM model is a variable length sequence x ═ xiIn which xiFor a feature vector at a specific time length index i, the hidden state at time index t is updated as follows:
int＝σ(Wxinxt+Whinht-1+bin)
ft＝σ(Wxfxt+Whfht-1+bf)
Figure FDA0003354592970000012
ot＝σ(Wxoxt+Whoht-1+bo)
Figure FDA0003354592970000021
therein, intRepresenting the input gate at time index t, ftIndicating a forgetting gate at time index t, otRepresents the output gate at time index t; c. CtRepresents the unit vector at time index t; sigma represents a sigmoid function;
Figure FDA0003354592970000022
representing element multiplication; the first parameter W and the second parameter b map the cascade to the size of the hidden state, wherein; h istRepresenting hidden states of the model output; wxinRepresenting an input gate input weight; x is the number oftRepresenting input gate input at time t; whinRepresenting input layer hidden state weights; binRepresenting input gate bias; wxfRepresenting forgetting layer input weights; whfRepresenting a forgotten door hidden state weight; bfThe representation represents a forgetting gate bias; wxcRepresenting hidden state weights at the time index; whcRepresenting a time indexed hidden state weight; bcRepresents a bias at the time index; wxoRepresenting output gate input weights; whoRepresenting an output gate hidden state weight; boRepresents the output gate offset;
the decoder of the improved LSTM model is responsible for recursively generating the output sequence y ═ { y1, y2m-adding a fully connected layer with a linear activation function on top of the LSTM layer to generate a prediction with continuous values; for the decoder, the estimate y at time index ttThe calculation is as follows:
yt＝Linear(W[st，ct]+b)
st＝LSTM(yt-1，st-1，ct)
wherein s istIs the hidden state of the decoder at time index t, ct is the weighted sum of the hidden states passed by the encoder, [ st, ct]Is a concatenation of decoder hidden state and context vector; LSTM represents decoding operation by using LSTM network; linear denotes a recursion-based fully-connected operation.
5. The method for interpolating pH missing data in pond culture according to claim 1, wherein the step of S3 further comprises the steps of:
s31: acquiring meteorological data of a meteorological station and water quality data of a water quality sensor by constructing a pond culture internet of things system;
s32: carrying out standardization and normalization pretreatment on the meteorological data and the water quality data according to the time series analysis requirements;
s33: constructing a training set and a testing set by using the current meteorological data and the water quality data;
s34: training the improved LSTM model by using the training set until the output of the improved LSTM model reaches the target accuracy, and obtaining the pH value interpolation model based on the improved LSTM;
s35: and verifying the precision of the pH value interpolation model based on the improved LSTM by using the test set, and verifying the effectiveness of the pH value interpolation model based on the improved LSTM.
6. The pond culture pH missing data interpolation method according to claim 1, wherein in the step S4, the pH interpolation model based on the improved LSTM is evaluated by using a root mean square error, an average absolute error and an average absolute percentage error.
7. The method for interpolating pH missing data in pond culture according to claim 6, wherein the root mean square error RMSE, the mean absolute error MAE and the mean absolute percentage error MAPE satisfy the following formula:
Figure FDA0003354592970000031
Figure FDA0003354592970000032
Figure FDA0003354592970000033
wherein, yiIn order to measure the dissolved oxygen content,
Figure FDA0003354592970000034
for prediction, N is the number of missing samples.
8. The pond culture pH missing data interpolation method according to claim 1, wherein the modified LSTM model uses a pytouch neural network framework;
the number of the encoder hidden layers of the improved LSTM model is 1;
the number of decoder hidden layers of the improved LSTM model is 2;
the number of LSTM hidden units in each layer of the improved LSTM model is 20;
the loss rate of the improved LSTM model is 0.2;
the optimizer of the improved LSTM model adopts Adam;
the loss function of the improved LSTM model adopts MSE;
the skin size of the modified LSTM model was 60.
CN202111347638.9A 2021-11-15 2021-11-15 Pond culture pH value missing data interpolation method Pending CN114037551A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111347638.9A CN114037551A (en) 2021-11-15 2021-11-15 Pond culture pH value missing data interpolation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111347638.9A CN114037551A (en) 2021-11-15 2021-11-15 Pond culture pH value missing data interpolation method

Publications (1)

Publication Number Publication Date
CN114037551A true CN114037551A (en) 2022-02-11

Family

ID=80144385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111347638.9A Pending CN114037551A (en) 2021-11-15 2021-11-15 Pond culture pH value missing data interpolation method

Country Status (1)

Country Link
CN (1) CN114037551A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090558A (en) * 2018-01-03 2018-05-29 华南理工大学 A kind of automatic complementing method of time series missing values based on shot and long term memory network
US20190129819A1 (en) * 2017-10-26 2019-05-02 International Business Machines Corporation Missing Values Imputation of Sequential Data
WO2019208998A1 (en) * 2018-04-27 2019-10-31 한국과학기술원 Gru-based cell structure design robust to missing data and noise in time series data in recurrent neural network
CN111131424A (en) * 2019-12-18 2020-05-08 武汉大学 Service quality prediction method based on combination of EMD and multivariate LSTM
CN112215422A (en) * 2020-10-13 2021-01-12 北京工业大学 Long-time memory network water quality dynamic early warning method based on seasonal decomposition
CN112418406A (en) * 2020-12-09 2021-02-26 甘肃靖远航天风力发电有限公司 Wind power tower inclination angle missing data supplementing method based on SSA-LSTM model
CN112687349A (en) * 2020-12-25 2021-04-20 广东海洋大学 Construction method of model for reducing octane number loss

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190129819A1 (en) * 2017-10-26 2019-05-02 International Business Machines Corporation Missing Values Imputation of Sequential Data
CN108090558A (en) * 2018-01-03 2018-05-29 华南理工大学 A kind of automatic complementing method of time series missing values based on shot and long term memory network
WO2019208998A1 (en) * 2018-04-27 2019-10-31 한국과학기술원 Gru-based cell structure design robust to missing data and noise in time series data in recurrent neural network
CN111131424A (en) * 2019-12-18 2020-05-08 武汉大学 Service quality prediction method based on combination of EMD and multivariate LSTM
CN112215422A (en) * 2020-10-13 2021-01-12 北京工业大学 Long-time memory network water quality dynamic early warning method based on seasonal decomposition
CN112418406A (en) * 2020-12-09 2021-02-26 甘肃靖远航天风力发电有限公司 Wind power tower inclination angle missing data supplementing method based on SSA-LSTM model
CN112687349A (en) * 2020-12-25 2021-04-20 广东海洋大学 Construction method of model for reducing octane number loss

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈英义;程倩倩;方晓敏;于辉辉;李道亮;: "主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧", 农业工程学报, no. 17, 31 August 2018 (2018-08-31), pages 16 - 18 *

Similar Documents

Publication Publication Date Title
CN110852515B (en) Water quality index prediction method based on mixed long-time and short-time memory neural network
CN108876021B (en) Medium-and-long-term runoff forecasting method and system
CN113609955B (en) Three-phase inverter parameter identification method based on deep learning and digital twin
CN111967688A (en) Power load prediction method based on Kalman filter and convolutional neural network
CN111931983B (en) Precipitation prediction method and system
CN113554466B (en) Short-term electricity consumption prediction model construction method, prediction method and device
CN114358435A (en) Pollution source-water quality prediction model weight influence calculation method of two-stage space-time attention mechanism
CN112086100B (en) Quantization error entropy based urban noise identification method of multilayer random neural network
CN113447879A (en) Electric energy meter metering error prediction method, system and device based on multi-stress influence
CN113850320A (en) Transformer fault detection method based on improved support vector machine regression algorithm
CN112215495B (en) Pollution source contribution calculation method based on long-time and short-time memory neural network
CN116303786B (en) Block chain financial big data management system based on multidimensional data fusion algorithm
CN112132324A (en) Ultrasonic water meter data restoration method based on deep learning model
CN114037551A (en) Pond culture pH value missing data interpolation method
CN115907204A (en) Forest transpiration water consumption prediction method for optimizing BP neural network by sparrow search algorithm
CN112329535B (en) CNN-based quick identification method for low-frequency oscillation modal characteristics of power system
CN113919388A (en) Electromechanical equipment fault diagnosis method and device integrating signal frequency spectrum amplitude modulation and deep learning
CN114036846A (en) Pond culture dissolved oxygen deficiency data interpolation method
CN113159395A (en) Deep learning-based sewage treatment plant water inflow prediction method and system
CN112307918A (en) Diagnosis method for transformer direct-current magnetic biasing based on fuzzy neural network
CN111126659A (en) Power load prediction method and system
CN117974736B (en) Underwater sensor output signal noise reduction method and system based on machine learning
CN117473275B (en) Energy consumption detection method for data center
CN115828719A (en) Power system subsynchronous oscillation data generation method based on generation countermeasure network
CN117408129A (en) Power distribution network state estimation method based on CNN-LSTM pseudo measurement model

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