CN112446098A - Extreme performance simulation method for propeller in marine equipment - Google Patents

Extreme performance simulation method for propeller in marine equipment Download PDF

Info

Publication number
CN112446098A
CN112446098A CN202011414100.0A CN202011414100A CN112446098A CN 112446098 A CN112446098 A CN 112446098A CN 202011414100 A CN202011414100 A CN 202011414100A CN 112446098 A CN112446098 A CN 112446098A
Authority
CN
China
Prior art keywords
propeller
performance
parameter
parameters
function
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.)
Granted
Application number
CN202011414100.0A
Other languages
Chinese (zh)
Other versions
CN112446098B (en
Inventor
蔡如桦
陈刚
邹遂丰
刘建阁
闻心怡
彭晓钧
贺梦豪
刘婷
陈梦珂
谢敏灵
周跃
李天鹞
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.)
Wuhan No 2 Ship Design Institute No 719 Research Institute of China Shipbuilding Industry Corp
Original Assignee
Wuhan No 2 Ship Design Institute No 719 Research Institute of China Shipbuilding Industry Corp
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 Wuhan No 2 Ship Design Institute No 719 Research Institute of China Shipbuilding Industry Corp filed Critical Wuhan No 2 Ship Design Institute No 719 Research Institute of China Shipbuilding Industry Corp
Priority to CN202011414100.0A priority Critical patent/CN112446098B/en
Publication of CN112446098A publication Critical patent/CN112446098A/en
Application granted granted Critical
Publication of CN112446098B publication Critical patent/CN112446098B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Abstract

The invention relates to a limit performance simulation method of a propeller in marine equipment, which comprises the following steps: collecting environmental parameters, material parameters and performance parameters of a propeller; establishing a neural network model for simulating the limit performance of the propeller, and obtaining a limit performance simulation coefficient of the propeller through the neural network; the neural network takes the relevant parameters of the environmental parameters and the performance parameters of the propeller and the relevant parameters of the material parameters and the performance parameters as input vectors and outputs a performance parameter change function of the propeller; and performing linear fitting on the performance parameter change function of the output propeller to obtain the corresponding relation between the material parameters and the performance parameters in the extreme environment. The simulation method can simulate the structure and the performance coefficient of the propeller in the extreme environment, thereby being beneficial to improving the propeller, avoiding potential safety hazards in the actual extreme environment and providing data basis for the design of the propeller.

Description

Extreme performance simulation method for propeller in marine equipment
Technical Field
The invention relates to a propeller in marine equipment, in particular to a limit performance simulation method of the propeller in the marine equipment.
Background
Marine equipment, such as marine nuclear power platforms, are required to face various harsh environments in the marine environment, and therefore, the performance requirements for the components in the marine equipment are relatively high. The propeller in the ship is used as power equipment and is important equipment of an ocean nuclear power platform, the performances of thrust, power, rotating speed, navigational speed and the like and the durability of the propeller in various environments play an important role, and particularly in extremely cold environments, whether the performance of the propeller can be kept in a normal environment or not has a very important influence on running and safety.
Therefore, in order to avoid the propeller from being out of order in the extreme environment, it is necessary to perform simulation calculation on the performance of the propeller in the extreme environment so as to solve the possible problems of the propeller according to the calculated condition of the propeller.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a limit performance simulation method of a propeller in marine equipment, which can simulate the structure and the performance coefficient of the propeller in a limit environment, thereby being beneficial to improving the propeller and avoiding potential safety hazards in the actual limit environment.
The technical scheme adopted for realizing the aim of the invention is as follows: a method of simulating limit performance of a propeller in marine equipment, the method comprising:
collecting environmental parameters, material parameters and performance parameters of a propeller;
establishing a neural network model for simulating the limit performance of the propeller, and obtaining a limit performance simulation coefficient of the propeller through the neural network; the neural network takes a relevant parameter gamma of the environmental parameter and the performance parameter of the propeller and a relevant parameter xi of the material parameter and the performance parameter as input vectors and outputs a performance parameter change function of the propeller;
and performing linear fitting on the performance parameter change function of the output propeller to obtain the corresponding relation between the material parameters and the performance parameters in the extreme environment.
In the above technical solution, the network output expression of the neural network model is as follows:
Y＝f2[W2·f1(W1·X-B1)-B2]
W1、B1weight matrix and deviation matrix from input layer to hidden layer, W2、B2Weight matrix and deviation matrix from hidden layer to output layer, respectively, f1、f2Neuron transfer functions of a hidden layer and an output layer respectively, an output vector Y is a limit performance function of the propeller, and an input vector X is a function of an environmental parameter, a material parameter and a performance parameter, wherein:
X＝f(A，V，C，K)
wherein A is an environmental parameter function, V is a material parameter function, and C isA performance parameter function, K being a correlation function; wherein A ═ K1(Loc，T1，T2，S)，Loc，T1，T2S is respectively represented as geographical location, ambient temperature, air humidity, wind speed; v is K2(L, M, N, O), wherein L, M, N and O are respectively hardness, strength, brittleness and plasticity of components in the propeller; c ═ K3(F，P，S1，S2)，F，P，S1，S2The four parameters of the thrust, the power, the rotating speed and the navigational speed of the propeller are respectively set; k is { gamma, xi }, gamma is the correlation coefficient of the environmental parameter a and the performance parameter C, xi is the correlation coefficient of the material parameter V and the performance parameter C, wherein,
Figure BDA0002815588490000021
Figure BDA0002815588490000022
represents the conjugation of C;
Figure BDA0002815588490000023
Figure BDA0002815588490000024
represents the conjugation of C.
The method takes the relevant parameter gamma of the performance parameter of the propeller and the relevant parameter xi of the material parameter and the performance parameter as input vectors, calculates the propeller performance change function of the material parameter of each component in the propeller and the performance parameter of the propeller under different environmental parameters through a neural network, and obtains the corresponding relation of the material parameter and the performance parameter under the extreme environment through linear fitting of the performance parameter change function of the output propeller, thereby simulating the parameters of the materials required by each component in the propeller under the extreme environment, whether the working performance of the propeller meets the standard or not, whether potential safety hazards exist or not and the like, and providing reliable data basis for the improvement and optimization of the materials, the process and the performance of the propeller operating under the extreme environment.
Drawings
FIG. 1 is a flow chart of a method for simulating limit performance of a propeller in marine equipment according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the specific embodiments.
As shown in FIG. 1, the method for simulating the limit performance of the propeller in the marine equipment comprises the following steps:
s1, collecting environmental parameters, material parameters and performance parameters of the propeller;
s2, establishing a neural network model for simulating the limit performance of the propeller, and obtaining a limit performance simulation coefficient of the propeller through the neural network; the neural network takes the relevant parameter gamma of the environmental parameter and the performance parameter of the propeller and the relevant parameter xi of the material parameter and the performance parameter as input vectors and outputs a performance parameter change function of the propeller.
Specifically, the network output expression of the neural network established in this embodiment is:
Y＝f2[W2·f1(W1·X-B1)-B2]
W1、B1weight matrix and deviation matrix from input layer to hidden layer, W2、B2Weight matrix and deviation matrix from hidden layer to output layer, respectively, f1、f2Neuron transfer functions of a hidden layer and an output layer respectively, an output vector Y is a limit performance function of the propeller, and an input vector X is a function of an environmental parameter, a material parameter and a performance parameter, wherein:
X＝f(A，V，C，K)
in the formula, A is an environmental parameter function, V is a material parameter function, C is a performance parameter function, and K is a correlation function; wherein A ═ K1(Loc，T1，T2，S)，Loc，T1，T2S is respectively represented as geographical location, ambient temperature, air humidity, wind speed; v is K2(L, M, N, O), wherein L, M, N and O are respectively hardness, strength, brittleness and plasticity of components in the propeller; c ═ K3(F，P，S1，S2)，F，P，S1，S2The four parameters of the thrust, the power, the rotating speed and the navigational speed of the propeller are respectively set; k is { gamma, xi }, gamma is the correlation coefficient of the environmental parameter a and the performance parameter C, xi is the correlation coefficient of the material parameter V and the performance parameter C, wherein,
Figure BDA0002815588490000041
Figure BDA0002815588490000042
represents the conjugation of C;
Figure BDA0002815588490000043
Figure BDA0002815588490000044
represents the conjugation of C.
The output vector Y is the limit performance function of the propeller.
In the embodiment, the state parameters of the propeller under the previous normal working condition are used for network training of the established neural network, and the hidden layer function, the number of neurons and the weight are continuously adjusted according to the error between the output value and the output value under the normal working condition until the error meets the requirement; the normal working condition is an environment under which the state parameters of the propeller meet the standard conditions.
In this embodiment, the network training of the neural network by the BP algorithm specifically includes:
the BP algorithm is divided into a forward propagation stage and a backward propagation stage, in the forward propagation stage, information is converted from an input layer step by step and transmitted to an output layer, and the process is also a process executed when the network normally runs after training is completed; adjusting the weight matrix stage according to the performance error in the backward propagation stage;
taking the error measure of the network with respect to the p-th sample:
Figure BDA0002815588490000045
in the formula: m is the number of neurons of the output layer; y ispjIdeal output vector, Y, representing the jth element of the p-th samplepjFor the output value of the net for the jth element of the pth sample, the net error with respect to the entire sample set is finally determined as:
E＝∑Ep
the error calculated according to the above equation to this entire sample set is within a specified threshold range, i.e., the performance index of the propeller under normal circumstances.
And S3, obtaining the corresponding relation between the material parameters and the performance parameters under the limit environment by linear fitting of the performance parameter change function of the output propeller.
Calculated by the following formula:
Figure BDA0002815588490000051
in the formula, anAs a function of an environmental parameter, xiAs a function of the material parameter of the component i, y, in the propelleriAs a function of the performance parameter, Σ x, of component i in the propelleriyiIs a corresponding relation formula of the component i in the propeller to the material parameter and the performance parameter under different environmental parameters.
The corresponding relation function of the material parameters and the performance parameters under the extreme environment is obtained through the above-mentioned formulaic fitting, so that the parameters of the materials required by all parts in the propeller under the extreme environment and whether the working performance of the propeller meets the standard or not can be simulated. For example, in an extremely cold environment (temperature of-40 ℃), whether the parameters of the hardness, strength, brittleness and plasticity of the material parameters of each component in the propeller are within a normal standard data range or not is calculated through the corresponding relation function, if the parameters exceed the range, potential safety hazards exist, the materials of the propeller need to be tested and improved, meanwhile, whether the thrust, power, rotating speed and navigational speed of the propeller are influenced or not is calculated through the performance change function of the propeller, and data support is provided for the optimal design and improvement of the propeller.

Claims (5)

1. A method for simulating limit performance of a propeller in marine equipment is characterized by comprising the following steps:
collecting environmental parameters, material parameters and performance parameters of a propeller;
establishing a neural network model for simulating the limit performance of the propeller, and obtaining a limit performance simulation coefficient of the propeller through the neural network; the neural network takes a relevant parameter gamma of the environmental parameter and the performance parameter of the propeller and a relevant parameter xi of the material parameter and the performance parameter as input vectors and outputs a performance parameter change function of the propeller;
and performing linear fitting on the performance parameter change function of the output propeller to obtain the corresponding relation between the material parameters and the performance parameters in the extreme environment.
2. The method for simulating the limit performance of a propeller in marine equipment according to claim 1, wherein: the network output expression of the neural network model is as follows:
Y＝f2[W2·f1(W1·X-B1)-B2]
W1、B1weight matrix and deviation matrix from input layer to hidden layer, W2、B2Weight matrix and deviation matrix from hidden layer to output layer, respectively, f1、f2Neuron transfer functions of a hidden layer and an output layer respectively, an output vector Y is a limit performance function of the propeller, and an input vector X is a function of an environmental parameter, a material parameter and a performance parameter, wherein:
X＝f(A，V，C，K)
in the formula, A is an environmental parameter function, V is a material parameter function, C is a performance parameter function, and K is a correlation function; wherein A ═ K1(Loc，T1，T2，S)，Loc，T1，T2S is respectively represented as geographical location, ambient temperature, air humidity, wind speed; v is K2(L, M, N, O), L, M, N and O being parts of propellers, respectivelyHardness, strength, brittleness and plasticity; c ═ K3(F，P，S1，S2)，F，P，S1，S2The four parameters of the thrust, the power, the rotating speed and the navigational speed of the propeller are respectively set; k is { gamma, xi }, gamma is the correlation coefficient of the environmental parameter a and the performance parameter C, xi is the correlation coefficient of the material parameter V and the performance parameter C, wherein,
Figure FDA0002815588480000011
Figure FDA0002815588480000012
represents the conjugation of C;
Figure FDA0002815588480000013
Figure FDA0002815588480000014
represents the conjugation of C.
3. The method for simulating the limit performance of a propeller in marine equipment according to claim 2, wherein: network training is carried out on the established neural network by using the state parameters of the propeller under the previous normal working condition, and hidden layer functions, the number of neurons and weights are continuously adjusted according to the error between the output value and the output value under the normal working condition until the error meets the requirement; the normal working condition is an environment under which the state parameters of the propeller meet the standard conditions.
4. The method for simulating the limit performance of a propeller in marine equipment according to claim 3, wherein: carrying out network training on the neural network through a BP algorithm, wherein the BP algorithm is divided into a forward propagation stage and a backward propagation stage, and in the forward propagation stage, information is transmitted to an output layer from an input layer through gradual conversion; adjusting the weight matrix stage according to the performance error in the backward propagation stage;
taking the error measure of the network with respect to the p-th sample:
Figure FDA0002815588480000021
in the formula: m is the number of neurons of the output layer; y ispjIdeal output vector, Y, representing the jth element of the p-th samplepjFor the output value of the net for the jth element of the pth sample, the net error with respect to the entire sample set is finally determined as:
E＝∑Ep
the error to the entire sample set is calculated according to the above formula to be within a specified threshold.
5. The method for simulating the limit performance of a propeller in marine equipment according to any one of claims 2 to 4, wherein the corresponding relationship between the material parameter and the performance parameter under different environmental parameters obtained by linear fitting the performance parameter variation function of the output propeller is calculated by the following formula:
Figure FDA0002815588480000022
in the formula, anAs a function of an environmental parameter, xiAs a function of the material parameter of the component i, y, in the propelleriAs a function of the performance parameter, Σ x, of component i in the propelleriyiIs a corresponding relation formula of the component i in the propeller to the material parameter and the performance parameter under different environmental parameters.
CN202011414100.0A 2020-12-03 2020-12-03 Method for simulating ultimate performance of propeller in marine equipment Active CN112446098B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011414100.0A CN112446098B (en) 2020-12-03 2020-12-03 Method for simulating ultimate performance of propeller in marine equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011414100.0A CN112446098B (en) 2020-12-03 2020-12-03 Method for simulating ultimate performance of propeller in marine equipment

Publications (2)

Publication Number Publication Date
CN112446098A true CN112446098A (en) 2021-03-05
CN112446098B CN112446098B (en) 2023-08-25

Family

ID=74739671

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011414100.0A Active CN112446098B (en) 2020-12-03 2020-12-03 Method for simulating ultimate performance of propeller in marine equipment

Country Status (1)

Country Link
CN (1) CN112446098B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2791446A1 (en) * 1999-03-26 2000-09-29 Renault METHOD OF INITIALIZING A NETWORK OF NEURONS
US6574613B1 (en) * 1998-02-27 2003-06-03 Jorge Moreno-Barragan System and method for diagnosing jet engine conditions
US20030163436A1 (en) * 2002-01-11 2003-08-28 Jost Seifert Neuronal network for modeling a physical system, and a method for forming such a neuronal network
US20170161606A1 (en) * 2015-12-06 2017-06-08 Beijing University Of Technology Clustering method based on iterations of neural networks
CN107609647A (en) * 2017-10-16 2018-01-19 安徽工业大学 One kind is based on BP neural network roll alloy mechanical property Forecasting Methodology
CN108090658A (en) * 2017-12-06 2018-05-29 河北工业大学 Arc fault diagnostic method based on time domain charactreristic parameter fusion
CN110077525A (en) * 2019-05-08 2019-08-02 河海大学 A kind of double paddle propulsive performance discrimination methods of ship
CN110910531A (en) * 2019-10-21 2020-03-24 同济大学 Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information
CN111144001A (en) * 2019-12-26 2020-05-12 湖南科技大学 Mine shaft engineering TBM control method based on BP neural network
CN111985725A (en) * 2020-08-30 2020-11-24 浙江工业大学 Centrifugal pump performance parameter prediction method based on improved BP neural network

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6574613B1 (en) * 1998-02-27 2003-06-03 Jorge Moreno-Barragan System and method for diagnosing jet engine conditions
FR2791446A1 (en) * 1999-03-26 2000-09-29 Renault METHOD OF INITIALIZING A NETWORK OF NEURONS
US20030163436A1 (en) * 2002-01-11 2003-08-28 Jost Seifert Neuronal network for modeling a physical system, and a method for forming such a neuronal network
US20170161606A1 (en) * 2015-12-06 2017-06-08 Beijing University Of Technology Clustering method based on iterations of neural networks
CN107609647A (en) * 2017-10-16 2018-01-19 安徽工业大学 One kind is based on BP neural network roll alloy mechanical property Forecasting Methodology
CN108090658A (en) * 2017-12-06 2018-05-29 河北工业大学 Arc fault diagnostic method based on time domain charactreristic parameter fusion
CN110077525A (en) * 2019-05-08 2019-08-02 河海大学 A kind of double paddle propulsive performance discrimination methods of ship
CN110910531A (en) * 2019-10-21 2020-03-24 同济大学 Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information
CN111144001A (en) * 2019-12-26 2020-05-12 湖南科技大学 Mine shaft engineering TBM control method based on BP neural network
CN111985725A (en) * 2020-08-30 2020-11-24 浙江工业大学 Centrifugal pump performance parameter prediction method based on improved BP neural network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
谭美等: "海洋核动力平台大破口事故下安全壳压力控制与影响", 船舶工程, no. 11, pages 29 - 33 *

Also Published As

Publication number Publication date
CN112446098B (en) 2023-08-25

Similar Documents

Publication Publication Date Title
CN111199270B (en) Regional wave height forecasting method and terminal based on deep learning
CN112131760A (en) CBAM model-based prediction method for residual life of aircraft engine
CN111444760A (en) Traffic sign detection and identification method based on pruning and knowledge distillation
CN110222828B (en) Unsteady flow field prediction method based on hybrid deep neural network
CN110000787A (en) A kind of control method of super redundant mechanical arm
CN107045575A (en) Aero-engine performance model modelling approach based on self-adjusting Wiener model
CN106597852A (en) MEMS gyroscope temperature compensation method based on RBF neural network
CN114004023A (en) Aircraft pneumatic parameter identification method based on recurrent neural network
CN115688288B (en) Aircraft pneumatic parameter identification method and device, computer equipment and storage medium
CN114842681A (en) Airport scene flight path prediction method based on multi-head attention mechanism
CN116341358A (en) Large buoy motion response and anchoring tension prediction method combined with deep learning
CN113221237B (en) Large attack angle flutter analysis method based on reduced order modeling
CN114357872A (en) Ship motion black box identification modeling and motion prediction method based on stacking model fusion
CN112446098A (en) Extreme performance simulation method for propeller in marine equipment
CN114030008B (en) Industrial robot practical training energy consumption measurement method based on data driving
CN116202492A (en) Ship-following wave measurement method based on high-low frequency separation
CN113219841B (en) Nonlinear control method for underwater multi-joint hydraulic mechanical arm based on adaptive robustness
CN116304587A (en) Rolling bearing degradation trend prediction method based on CAE and AGRU
CN115206455A (en) Deep neural network-based rare earth element component content prediction method and system
CN107292015B (en) Neural network algorithm-based underwater vehicle equilibrium submerged model evaluation method
CN113108949A (en) Model fusion-based sonde temperature sensor error prediction method
CN111506959A (en) Universal flight control system and method for flight simulation training
CN117010179B (en) Unsupervised depth adaptation parameter correction method based on deep learning
CN116562186B (en) Underwater gas transmission pipeline leakage parameter inversion method and system based on simulation-optimization
Wang et al. Research on Hovercraft Motion Prediction Based on Compound prediction

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant