CN113536682B - Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism - Google Patents

Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism Download PDF

Info

Publication number
CN113536682B
CN113536682B CN202110824289.9A CN202110824289A CN113536682B CN 113536682 B CN113536682 B CN 113536682B CN 202110824289 A CN202110824289 A CN 202110824289A CN 113536682 B CN113536682 B CN 113536682B
Authority
CN
China
Prior art keywords
data
model
time series
extrapolation
autoencoder
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110824289.9A
Other languages
Chinese (zh)
Other versions
CN113536682A (en
Inventor
马剑
邹新宇
周安
张聪
张统
丁宇
吕琛
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.)
Beihang University
Original Assignee
Beihang University
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 Beihang University filed Critical Beihang University
Priority to CN202110824289.9A priority Critical patent/CN113536682B/en
Publication of CN113536682A publication Critical patent/CN113536682A/en
Application granted granted Critical
Publication of CN113536682B publication Critical patent/CN113536682B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/27Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/25Fusion techniques
    • G06F18/253Fusion techniques of extracted features
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/047Probabilistic or stochastic networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/084Backpropagation, e.g. using gradient descent
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)

Abstract

本发明提供一种基于二次自编码融合机制的电动液压舵机参数退化时序外推预测方法,所述方法包括:获取电动液压舵机的故障预测数据;对所述故障数据进行综合预处理,以得到训练数据集和测试数据集;构建时序外推预测器:所述时序外推预测器包括卷积神经网络一次自编码器、基于专家知识的人工时域特征提取器,以及基于SAE的二次自编码器;所述时序外推预测器将所述训练数据集进行融合得到融合特征,而且所述二次自编码器对所述融合特征进行二次编码,而后再将二次编码特征与标签数据建立映射关系;综合训练所述卷积神经网络一次自编码器和所述时序外推预测器,得到训练好的时序外推预测器;以及利用训练好的时序外推预测模型对对已有数据进行预测。

The present invention provides a time series extrapolation prediction method for electro-hydraulic steering gear parameter degradation based on a secondary self-encoding fusion mechanism. The method includes: obtaining fault prediction data of the electro-hydraulic steering gear; comprehensively preprocessing the fault data, To obtain the training data set and the test data set; construct a time series extrapolation predictor: the time series extrapolation predictor includes a convolutional neural network autoencoder, an artificial time domain feature extractor based on expert knowledge, and a binary SAE-based Secondary autoencoder; the temporal extrapolation predictor fuses the training data set to obtain fusion features, and the secondary autoencoder performs secondary coding on the fused features, and then combines the secondary coding features with Label data establishes a mapping relationship; comprehensively trains the convolutional neural network primary autoencoder and the temporal extrapolation predictor to obtain a trained temporal extrapolation predictor; and uses the trained temporal extrapolation prediction model to There is data to predict.

Description

一种基于二次自编码融合机制的电动液压舵机参数退化时序 外推预测方法A kind of electro-hydraulic steering gear parameter degradation timing sequence based on quadratic self-encoding fusion mechanism extrapolation forecasting method

技术领域Technical field

本发明涉及电动液压舵机的退化趋势预测,特别是涉及一种电动液压舵机参数退化时序外推预测。The present invention relates to the prediction of the degradation trend of electro-hydraulic steering gear, and in particular to a time series extrapolation prediction of the degradation of electro-hydraulic steering gear parameters.

背景技术Background technique

电动液压舵机系统是一种复杂的机电一体化系统,同时也是一种高精度的位置伺服系统,对飞行器的姿态控制具有重要影响。随着科学技术的不断发展,先进航空器广泛采用速度快、精度高、功率重量比大的全数字化伺服舵机系统。当代工程应用对舵机的可靠性提出了更高的要求。舵机关键参数退化过程预测是舵机可靠性研究的一个重要方面。精准预测舵机关键参数未来时间序列,把握参数变化趋势规律,对于合理安排维修计划、提高飞行品质、保障飞行安全、降低全寿命周期费用等具有重要意义。传统的时序外推预测方法通常采用时间序列分解的策略,通过将时间序列分解为趋势项、季节项、残差项等分别进行预测,最后融合各项预测结果得到参数的时序外推预测序列。然而,对于电动液压舵机这样的复杂机电系统,其退化过程往往表现出非线性,导致其退化参数的时间序列往往难以依照传统方法进行有效分解,给舵机关键参数未来时序预测问题带来了很大困难。The electro-hydraulic steering gear system is a complex electromechanical integration system and a high-precision position servo system, which has an important impact on the attitude control of the aircraft. With the continuous development of science and technology, advanced aircraft widely adopt fully digital servo steering systems with fast speed, high precision and large power-to-weight ratio. Contemporary engineering applications place higher requirements on the reliability of steering gears. The prediction of the degradation process of key parameters of the steering gear is an important aspect of the reliability research of the steering gear. Accurately predicting the future time series of key parameters of the steering gear and grasping the trend of parameter changes are of great significance for rationally arranging maintenance plans, improving flight quality, ensuring flight safety, and reducing life cycle costs. Traditional time series extrapolation forecasting methods usually use the time series decomposition strategy to forecast separately by decomposing the time series into trend items, seasonal items, residual items, etc., and finally fuse the forecast results to obtain the time series extrapolation forecast sequence of parameters. However, for complex electromechanical systems such as electro-hydraulic steering gear, the degradation process often exhibits nonlinearity, which makes the time series of its degradation parameters often difficult to effectively decompose according to traditional methods, which brings problems to the future timing prediction of key parameters of the steering gear. Very difficult.

为了解决该问题,提出了一种基于人工特征与卷积特征二次自编码融合机制的电动液压舵机参数退化时序外推预测方法。该方法结合人工时域特征与卷积深度特征,通过二次自编码机制实现特征融合,可以将原始参数的时序依赖关系与变化趋势直接映射到隐层深度特点当中,避免了传统方法中序列分解的问题,为电动液压舵机关键参数退化时序的外推预测问题提供了更实用的方法。In order to solve this problem, a time series extrapolation prediction method for electro-hydraulic steering gear parameter degradation based on the secondary autoencoding fusion mechanism of artificial features and convolutional features is proposed. This method combines artificial time domain features and convolutional depth features, and achieves feature fusion through a secondary autoencoding mechanism. It can directly map the temporal dependencies and changing trends of the original parameters to the hidden layer depth features, avoiding the sequence decomposition in traditional methods. The problem provides a more practical method for the extrapolation prediction problem of the degradation time series of key parameters of electro-hydraulic steering gear.

发明内容Contents of the invention

为了解决现有技术所存在的问题,本发明提出一种基于二次自编码融合机制的电动液压舵机参数退化时序外推预测方法。In order to solve the problems existing in the existing technology, the present invention proposes a time series extrapolation prediction method for electro-hydraulic steering gear parameter degradation based on a secondary autoencoding fusion mechanism.

根据本发明的一个方面,提供一种基于二次自编码融合机制的电动液压舵机参数退化时序外推预测方法,所述方法包括:获取电动液压舵机的故障预测数据;对所述故障数据进行综合预处理,以得到训练数据集和测试数据集;构建时序外推预测器:所述时序外推预测器包括卷积神经网络一次自编码器、基于专家知识的人工时域特征提取器,以及基于SAE的二次自编码器;所述时序外推预测器将所述训练数据集进行融合得到融合特征,而且所述二次自编码器对所述融合特征进行二次编码,而后再将二次编码特征与标签数据建立映射关系;综合训练所述卷积神经网络一次自编码器和所述时序外推预测器,得到训练好的时序外推预测器;以及利用训练好的时序外推预测模型对对已有数据进行预测。According to one aspect of the present invention, a time series extrapolation prediction method for electro-hydraulic steering gear parameter degradation based on a quadratic auto-encoding fusion mechanism is provided. The method includes: obtaining fault prediction data of the electro-hydraulic steering gear; Perform comprehensive preprocessing to obtain training data sets and test data sets; construct a time series extrapolation predictor: the time series extrapolation predictor includes a convolutional neural network one-time autoencoder and an artificial time domain feature extractor based on expert knowledge, And a quadratic autoencoder based on SAE; the temporal extrapolation predictor fuses the training data set to obtain fusion features, and the quadratic autoencoder performs secondary encoding on the fusion features, and then Establish a mapping relationship between the secondary encoding features and the label data; comprehensively train the convolutional neural network primary autoencoder and the temporal extrapolation predictor to obtain a trained temporal extrapolation predictor; and utilize the trained temporal extrapolation Predictive models make predictions on existing data.

优选地是,所述时序外推预测模型以原始的训练数据集作为输入,首先基于人工时域特征提取器进行人工特征提取,利用经过预训练的卷积神经网络特征提取模型对原始的训练数据集进行卷积特征提取,然后对卷积特征与人工时域特征进行特征融合,并将训练数据标签Strainy作为时序外推预测模型输出,以此完成外推预测器模型的训练。Preferably, the time series extrapolation prediction model takes the original training data set as input, first performs manual feature extraction based on an artificial time domain feature extractor, and uses a pre-trained convolutional neural network feature extraction model to extract the original training data Convolutional feature extraction is performed on the set, and then the convolutional features and artificial time domain features are feature fused, and the training data label S trainy is output as the time series extrapolation prediction model to complete the training of the extrapolation predictor model.

优选地是,对所述已有数据进行预测时,对于长度为w的输入数据,其预测数据长度为W-w,截取已有数据中长度为2w-W的数据段与预测数据进行拼接,以此作为新一轮预测的输入,不断往复迭代知道达到人为预设的预测长度Lp,则预测结束。Preferably, when predicting the existing data, for the input data with length w, the predicted data length is Ww, and the data segments with length 2w-W in the existing data are intercepted and spliced with the predicted data, so as to As the input of a new round of prediction, the prediction is completed by continuously iterating until the artificially preset prediction length L p is reached.

优选地是,将经过综合预处理得到的验证集数据送入所述时序外推预测模型,结合相应的预测指标,完成模型的预测性能评估。Preferably, the verification set data obtained through comprehensive preprocessing is sent to the time series extrapolation prediction model, and combined with the corresponding prediction indicators, the prediction performance evaluation of the model is completed.

优选地是,所述综合预处理步骤包括对关键参数时序数据进行滑窗切割,所述关键参数时序数据为X,X={x1,x2,...xN},对X进行滑窗切割从而生成相应的样本数据集,当窗口宽度为W,步长为s时,切割生成的样本数量为:Preferably, the comprehensive preprocessing step includes performing sliding window cutting on key parameter time series data. The key parameter time series data is X, X={x 1 , x 2 , ... Window cutting generates the corresponding sample data set. When the window width is W and the step size is s, the number of samples generated by cutting is:

则生成相应的数据集为{S1,S2,...Ssn},对{S1,nor,S2,nor,...Ssn,nor}中的每个样本Si,nor取长度为w的数据作为训练数据,取W-w长度的数据作为这段训练数据对应的预测数据。Then the corresponding data set is generated as {S 1 , S 2 ,...S sn }, for each sample Si, nor in {S 1, nor , S 2, nor ,...S sn, nor } Take the data of length w as the training data, and take the data of length Ww as the prediction data corresponding to this training data.

优选地是,所述卷积神经网络一次自编码器的构建包括基于所述训练数据集Strain={S1,nor,S2,nor,...Sn,nor},将其数据格式转化为三维数据格式(sn,w,1),将所构建好的三维训练数据集输入一次自编码器反复执行前向传播和反向传播迭代计算过程,以对所构建的一次自编码模型的卷积层、池化层、全连接层的模型参数不断进行调整,以完成模型的预训练,其中{S1,nor,S2,nor,...Ssn,nor}为经过归一化处理的样本数据集,sn为样本数量,w为每个样本的数据长度,1为通道数。Preferably , the construction of the convolutional neural network primary autoencoder includes converting its data format into Convert it into a three-dimensional data format (sn, w, 1), input the constructed three-dimensional training data set into the primary autoencoder and repeatedly perform the forward propagation and back propagation iterative calculation processes to evaluate the constructed primary autoencoder model. The model parameters of the convolution layer, pooling layer, and fully connected layer are continuously adjusted to complete the pre-training of the model, where {S 1, nor , S 2, nor ,...S sn, nor } are normalized Processed sample data set, sn is the number of samples, w is the data length of each sample, and 1 is the number of channels.

优选地是,所述一次自编码模型包括多个卷积层、多个池化层和一个Flatten全连接层,所述全连接层利用多层堆叠的卷积层和池化提取的特征进行特征识别,在所述全连接层上使用sofimax回归,所述sofimax函数的输出为Preferably, the one-shot autoencoding model includes multiple convolutional layers, multiple pooling layers and a Flatten fully connected layer. The fully connected layer uses features extracted from multiple layers of stacked convolutional layers and pooling to perform feature extraction. Recognition, using sofimax regression on the fully connected layer, the output of the sofimax function is

其中k表示输出层网络节点数。where k represents the number of output layer network nodes.

优选地是,在所述基于SAE的二次自编码器中进一步以二维融合特征矩阵所述二次编码器和解码器进行预训练;以二维融合特征矩阵作为所述堆叠二次自编码的输入和输出,选择合适的损失函数和迭代次数,完成前向传播和反向传播迭代计算过程,使模型不断重构自身输入,最终从完成预训练的堆叠二次自编码器模型中提取其中的编码层作为可用的二次自编码模型。Preferably, in the SAE-based secondary autoencoder, the secondary encoder and decoder are further pre-trained with a two-dimensional fusion feature matrix; a two-dimensional fusion feature matrix is used as the stacked secondary autoencoder. input and output, select the appropriate loss function and number of iterations, complete the iterative calculation process of forward propagation and back propagation, so that the model continuously reconstructs its own input, and finally extracts it from the stacked quadratic autoencoder model that has completed pre-training. The encoding layer serves as an available quadratic autoencoding model.

优选地是,基于预训练得到的二次自编码器模型对深度融合特征进行二次自编码,从而得到二次编码特征集{F′1,F′2,..,F′sn}。Preferably, the deep fusion features are subjected to secondary auto-encoding based on the pre-trained secondary autoencoder model, thereby obtaining the secondary encoding feature set {F′ 1 , F′ 2 , .., F′ sn }.

本发明内容仅作为在具体实施方式和附图中完全描述的主题的介绍。不应将发明内容认定为描述了必要技术特征,也不应当用来确定权利要求的范围。此外,应该理解的是,上述发明内容和以下具体实施方式仅仅是示例性的和解释性的,并且不作为所要求保护的主题的必要限制。This summary merely serves as an introduction to the subject matter fully described in the detailed description and drawings. The Summary of the Invention should not be deemed to describe necessary technical features, nor should it be used to determine the scope of the claims. Furthermore, it is to be understood that the foregoing summary and the following detailed description are exemplary and explanatory only and are not necessarily limiting of claimed subject matter.

附图说明Description of the drawings

本公开的各种实施例或样例(“示例”)在以下的具体实施方式和附图中得以公开。没必要将附图按比例绘制。一般而言,除非在权利要求中另有规定,否则可以任意顺序执行所公开方法的操作。附图中:Various embodiments or examples ("examples") of the present disclosure are disclosed in the following detailed description and accompanying drawings. It is not necessary that the drawings be drawn to scale. In general, the operations of the disclosed methods may be performed in any order, unless otherwise specified in the claims. In the attached picture:

图1示出了根据本发明的基于深度神经网络的人工特征与卷积特征融合的特征提取方法流程图;Figure 1 shows a flow chart of a feature extraction method based on the fusion of artificial features and convolutional features based on deep neural networks according to the present invention;

图1A示出了基于图1所示方法输出的融合特征的时序外推预测方法;Figure 1A shows a time series extrapolation prediction method based on the fusion features output by the method shown in Figure 1;

图2示出了根据本发明的获取电动液压舵机故障预测数据的方法示意图;Figure 2 shows a schematic diagram of a method for obtaining electro-hydraulic steering gear failure prediction data according to the present invention;

图3示出了根据本发明的基于卷积神经网络的一次自编码模型结构图;Figure 3 shows a structural diagram of a one-time autoencoding model based on a convolutional neural network according to the present invention;

图4示出了图1所示的一次自编码和人工时域特征提取的的操作流程图;Figure 4 shows the operation flow chart of the one-time autoencoding and artificial time domain feature extraction shown in Figure 1;

图5示出了图1所示的基于SAE的二次自编码器的结构示意图;Figure 5 shows a schematic structural diagram of the SAE-based quadratic autoencoder shown in Figure 1;

图6示出了反馈角度原始数据示意图;Figure 6 shows a schematic diagram of the raw data of the feedback angle;

图7A示出了基于图4所示流程图获取的人工时域特征的最大值;Figure 7A shows the maximum value of the artificial time domain feature obtained based on the flowchart shown in Figure 4;

图7B示出了基于图4所示流程图获取的人工时域特征的标准差;Figure 7B shows the standard deviation of the artificial time domain features obtained based on the flowchart shown in Figure 4;

图8为根据本发明的时序外推预测方法得到的预测结果;Figure 8 shows the prediction results obtained according to the time series extrapolation prediction method of the present invention;

图9A为全部预测数据;Figure 9A shows all prediction data;

图9B为部分预测数据的局部放大图。Figure 9B is a partially enlarged view of part of the prediction data.

具体实施方式Detailed ways

在详细解释本公开的一个或多个实施例之前,应当理解,实施例不限于它们具体应用中的构造细节,以及下文实施方式或附图所提出步骤或方法。Before one or more embodiments of the present disclosure are explained in detail, it is to be understood that the embodiments are not limited to the construction details of their specific applications, steps or methods set forth in the following embodiments or drawings.

本发明所公开的时序外推预测方法图示在图1和图1A所示的方法流程图中,图1示出了根据本发明的基于深度神经网络的人工特征与卷积特征融合的特征提取方法流程图,图1A示出了基于图1所示方法输出的融合特征的时序外推预测方法。如图1所示的特征提取方法,其包括多个步骤:步骤1:获取电动液压舵机的故障预测数据;步骤2:对故障数据进行综合预处理;步骤3:进行基于卷积神经网络的特征提取;步骤4:对训练数据集进行基于专家知识的人工时域特征提取;步骤5:对基于经验知识提取的人工特征和基于CNN特征提取模型提取的高维隐含层特征进行特征拼接;步骤6:进行基于堆叠自编码器的深度特征融合,从而得到二次编码特征值。在步骤6中得到的二次编码特征值送入图1A所示的时序外推预测模型训练模块,执行步骤7:时序外推预测模型训练,所述步骤7具体包括:构建时序外推预测模型;训练时序外推预测器模型;以及使用外推预测期进行预测。下面将结合图1和图1A对基于二次自编码融合机制的电动液压舵机参数退化时序外推预测方法进行详细的说明。The time series extrapolation prediction method disclosed by the present invention is illustrated in the method flow chart shown in Figure 1 and Figure 1A. Figure 1 shows feature extraction based on the fusion of artificial features and convolutional features based on deep neural networks according to the present invention. Method flow chart, Figure 1A shows the temporal extrapolation prediction method based on the fused features output by the method shown in Figure 1 . The feature extraction method shown in Figure 1 includes multiple steps: Step 1: Obtain the fault prediction data of the electro-hydraulic steering gear; Step 2: Comprehensive preprocessing of the fault data; Step 3: Perform convolutional neural network-based Feature extraction; Step 4: Perform artificial time domain feature extraction based on expert knowledge from the training data set; Step 5: Feature splicing of artificial features extracted based on empirical knowledge and high-dimensional hidden layer features extracted based on the CNN feature extraction model; Step 6 : Perform deep feature fusion based on stacked autoencoders to obtain secondary encoding feature values. The secondary encoding feature values obtained in step 6 are sent to the time series extrapolation prediction model training module shown in Figure 1A, and step 7 is performed: time series extrapolation prediction model training. The step 7 specifically includes: constructing a time series extrapolation prediction model ;train a time series extrapolation predictor model; and make forecasts using the extrapolation forecast period. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method based on the quadratic autoencoding fusion mechanism will be described in detail below with reference to Figure 1 and Figure 1A.

一、获取电动液压舵机的故障预测数据1. Obtain fault prediction data of electro-hydraulic steering gear

受限于现实试验条件与实际使用环境,产品真实故障数据获取困难这一情况广泛存在。仿真分析是国内外解决数据匮乏问题的主要手段之一,广泛的研究结果都是基于仿真模型进行故障注入、获取相应的故障数据。因此,本发明为了获取电动液压舵机的故障预测数据,需要使用Simulink软件对电动液压舵机进行结构化建模并进行故障模拟。在操作中,使用该Simulink模型进行故障注入,可以最大限度获取接近真实故障情况的数据,实现故障预测模型验证。Limited by the actual test conditions and actual use environment, it is widely difficult to obtain real product failure data. Simulation analysis is one of the main means to solve the problem of data shortage at home and abroad. Extensive research results are based on simulation models to inject faults and obtain corresponding fault data. Therefore, in order to obtain the fault prediction data of the electro-hydraulic steering gear, the present invention needs to use Simulink software to conduct structured modeling of the electro-hydraulic steering gear and perform fault simulation. In operation, using this Simulink model for fault injection can maximize the acquisition of data close to the real fault situation and achieve fault prediction model verification.

针对舵机系统故障预测要求,首先对舵机系统结构进行了模型化处理,然后利用Simulink仿真软件搭建舵机控制系统仿真模型,用于生成仿真数据。在舵机控制系统仿真模型的基础上,选取适当的舵机系统仿真模型故障注入点进行故障注入并采集仿真信号,用于舵机控制系统故障预测模型的开发和验证。获取电动液压舵机故障预测数据的方法如图2所示。In response to the steering gear system fault prediction requirements, the steering gear system structure was first modeled, and then Simulink simulation software was used to build a steering gear control system simulation model for generating simulation data. Based on the steering gear control system simulation model, appropriate fault injection points of the steering gear system simulation model are selected for fault injection and simulation signals are collected for the development and verification of the steering gear control system fault prediction model. The method of obtaining electro-hydraulic steering gear failure prediction data is shown in Figure 2.

首先,针对舵机系统故障预测要求,对舵机控制系统模型进行结构化处理。结构化处理的舵机系统主要包含能源系统和位置伺服系统,如图2中的舵机系统结构分析模块所示,其关键组成部件主要包括:功放组合、直流电机、电液伺服阀、液压变量泵、作动筒、操纵机构、反馈电位器、高压安全阀、低压安全阀、油滤、邮箱等部件。First, according to the steering gear system fault prediction requirements, the steering gear control system model is structured. The structured steering gear system mainly includes the energy system and the position servo system, as shown in the steering gear system structure analysis module in Figure 2. Its key components mainly include: power amplifier combination, DC motor, electro-hydraulic servo valve, hydraulic variable Pump, actuator, control mechanism, feedback potentiometer, high-pressure safety valve, low-pressure safety valve, oil filter, mailbox and other components.

在对舵机控制系统模型进行结构化处理的基础上,利用Simulink模拟软件,搭建舵机控制系统仿真模型,在此仿真模型的基础上确定故障注入点。故障注入点可根据故障预测需要和历史故障数据来选取,其通常在舵机的各个组成部件上注入。在本申请中,例如可以选取反馈放大系数作为故障注入点,并在反馈电位器上进行故障注入。最后,进行故障仿真模拟与信号采集。信号采集的数据可以是舵机控制系统的各种控制指令和状态信号,其是本申请的电动舵机关键参数时序数据,例如包括:控制指令、统一时钟、位移信号、反馈角度。这些选取的关键参数时序数据就构成了待预测参数的历史时序数据。其中反馈角度可以有效地表征舵机系统的健康状态,因此,可以选择反馈角度作为后续的被预测参数。Based on the structured processing of the steering gear control system model, Simulink simulation software is used to build a steering gear control system simulation model, and the fault injection point is determined based on this simulation model. The fault injection point can be selected based on fault prediction needs and historical fault data. It is usually injected on each component of the steering gear. In this application, for example, the feedback amplification coefficient can be selected as the fault injection point, and fault injection can be performed on the feedback potentiometer. Finally, fault simulation and signal collection are performed. The data collected by the signal can be various control instructions and status signals of the steering gear control system, which are the key parameter timing data of the electric steering gear in this application, including, for example: control instructions, unified clock, displacement signal, and feedback angle. These selected key parameter time series data constitute the historical time series data of the parameters to be predicted. The feedback angle can effectively characterize the health status of the steering gear system. Therefore, the feedback angle can be selected as the subsequent predicted parameter.

二、对故障数据进行综合预处理2. Comprehensive preprocessing of fault data

舵机故障预测数据获取单元获得的数据,例如是反馈角度信号,送入故障数据预处理单元进行综合处理,以得到训练数据集和测试数据集,具体参照图1所示的综合数据预处理模块,其包括:The data obtained by the steering gear fault prediction data acquisition unit, such as the feedback angle signal, is sent to the fault data preprocessing unit for comprehensive processing to obtain a training data set and a test data set. For details, refer to the comprehensive data preprocessing module shown in Figure 1 , which includes:

步骤1、对关键参数时序数据进行滑窗切割,构造样本数据集;Step 1. Perform sliding window cutting on the key parameter time series data to construct a sample data set;

对传感器采集到的任一电动舵机关键参数时序数据为X,X={x1,x2,...xN},对X进行滑窗切割从而生成相应的样本数据集。当窗口宽度为W步长为s时,切割生成的样本数量为:The time series data of any key parameter of the electric steering gear collected by the sensor is X, X = {x 1 , x 2 , ... When the window width is W and the step size is s, the number of samples generated by cutting is:

则生成相应的数据集为{S1,S2,...Ssn},对{S1,nor,S2,nor,...Ssn,nor}中的每个样本Si,nor取长度为w的数据作为训练数据,取W-w长度的数据作为这段训练数据对应的预测数据。Then the corresponding data set is generated as {S 1 , S 2 ,...S sn }, for each sample Si, nor in {S 1, nor , S 2, nor ,...S sn, nor } Take the data of length w as the training data, and take the data of length Ww as the prediction data corresponding to this training data.

步骤2、对训练数据集进行极大极小值归一化处理;Step 2. Perform maximum and minimum normalization processing on the training data set;

为了提高数据表达能力,加快后续模型的训练的收敛速度,需要对训练数据集进行归一化处理,主要是通过极大极小值归一法对原始参数的幅值进行缩放,完成数据的线性变换。对于单个样本数据Si={x1,x2,...xw},通过公式:In order to improve the data expression ability and speed up the convergence speed of subsequent model training, the training data set needs to be normalized, mainly by scaling the amplitude of the original parameters through the maximum and minimum value normalization method to complete the linearization of the data. Transform. For a single sample data S i ={x 1 , x 2 ,...x w }, through the formula:

实现归一化处理,从而得到归一化的样本数据集{S1,nor,S2,nor,...Ssn,nor}。Implement normalization processing to obtain a normalized sample data set {S 1, nor , S 2, nor ,...S sn, nor }.

步骤3、构造训练数据集和测试数据集;Step 3. Construct training data set and test data set;

从所有数据中选取前r%的数据作为训练数据集,剩下的数据作为测试数据集,用于验证模型预测性能。通常而言,r一般取60-80,优选地取70。Select the first r% of all data as the training data set, and the remaining data as the test data set to verify the model prediction performance. Generally speaking, r generally takes 60-80, preferably 70.

三、进行基于卷积神经网络的特征提取3. Feature extraction based on convolutional neural network

经过综合数据预处理模块处理后得到的训练数据集,分别送入卷积神经网络一次自编码器和基于专家知识的人工时域特征提取模块,以得到卷积特征和人工特时域征。该特征提取步骤具体包括:基于卷积神经网络的一次自编码模型构建,如图3所示;以及如图4所示的卷积一次自编码器模型的预训练和使用卷积编码器进行卷积特征提取。The training data set obtained after processing by the comprehensive data preprocessing module is sent to the convolutional neural network primary autoencoder and the artificial time domain feature extraction module based on expert knowledge to obtain convolutional features and artificial special time domain features. The feature extraction step specifically includes: the construction of a one-shot autoencoder model based on a convolutional neural network, as shown in Figure 3; and the pre-training of the convolutional one-shot autoencoder model as shown in Figure 4 and the use of a convolutional encoder for convolution. Product feature extraction.

首先,利用训练数据集,构建基于卷积神经网络(CNN)的一次自编码模型,并利用训练数据集进行模型的预训练。由于二维卷积神经网络对输入数据的格式要求为三维数据,因此需要构造训练数据集。构造训练集是为了满足二维的一次自编码模型的输入要求,其方法是将训练数据集Strain={S1,nor,S2,nor,...Sn,nor}的数据格式转化为(sn,w,1),其中sn为样本数量,w为每个样本的数据长度,1为通道数。将构建好的训练样本数据集输入图3所示的基于卷积神经网络(CNN)的一次自编码模型。First, a training data set is used to construct a one-pass autoencoding model based on a convolutional neural network (CNN), and the training data set is used to pre-train the model. Since the two-dimensional convolutional neural network requires the format of the input data to be three-dimensional data, a training data set needs to be constructed. The training set is constructed to meet the input requirements of the two-dimensional one-shot autoencoding model. The method is to convert the data format of the training data set S train = {S 1, nor , S 2, nor ,...S n, nor }. is (sn, w, 1), where sn is the number of samples, w is the data length of each sample, and 1 is the number of channels. Input the constructed training sample data set into the one-pass autoencoding model based on the convolutional neural network (CNN) shown in Figure 3.

卷积神经网络(Convolutional Neural Network)是一种多层的监督学习神经网络,隐含层的卷积层和池采样层是实现卷积神经网络特征提取功能的核心部分。CNN是一种专门用来处理具有类似网络结构数据的神经网络,通过模仿生物视觉运行机制对原始数据进行特征提取,不同CNN层之间具有权值共享的特点,有效降低了网络的复杂度,避免因数据量过少而引起的过拟合问题和避免多维数据特征提取时数据重建的复杂度。如图3所示,本发明的深度卷积神经网络包括多个卷积层、多个池化层和一个Flatten全连接层。Convolutional Neural Network is a multi-layer supervised learning neural network. The convolution layer and pool sampling layer of the hidden layer are the core parts of realizing the feature extraction function of the convolutional neural network. CNN is a neural network specially designed to process data with similar network structure. It extracts features from original data by imitating the operating mechanism of biological vision. Different CNN layers have the characteristics of weight sharing, which effectively reduces the complexity of the network. Avoid over-fitting problems caused by too little data and avoid the complexity of data reconstruction when extracting multi-dimensional data features. As shown in Figure 3, the deep convolutional neural network of the present invention includes multiple convolutional layers, multiple pooling layers and a Flatten fully connected layer.

卷积层:具有非线性激活的卷积过程可描述为:Convolution layer: The convolution process with nonlinear activation can be described as:

其中,是第r个卷积层中第n个卷积核的输出,/>是第r-1个卷积层中第m个输出特征向量,*代表卷积操作,/>分别表示第r个卷积层中第n个卷积核的权重和偏置,ReLU表示非线性激活函数。in, is the output of the nth convolution kernel in the rth convolutional layer,/> is the m-th output feature vector in the r-1th convolution layer, * represents the convolution operation,/> Represents the weight and bias of the n-th convolution kernel in the r-th convolution layer respectively, and ReLU represents the nonlinear activation function.

池化层:通过加入池化层能够减少卷积特征的空间维数,避免过拟合。最大池化层是最常用的池化层,它只取输入中最重要的部分(最高的值),可以表示为Pooling layer: By adding a pooling layer, the spatial dimension of the convolutional features can be reduced and overfitting can be avoided. The max pooling layer is the most commonly used pooling layer. It only takes the most important part of the input (the highest value), which can be expressed as

其中是卷积层得到的特征,/>是池化层的输出,l表示池化操作区域的长度。in is the feature obtained by the convolutional layer,/> is the output of the pooling layer, and l represents the length of the pooling operation area.

全连接层:利用多层堆叠的卷积层和池化提取的特征,最终输入全连接层进行特征识别,通常在顶层全连接层上使用softmax回归。定义softmax函数的输出为Fully connected layer: Features extracted using multi-layer stacked convolutional layers and pooling are finally input into the fully connected layer for feature recognition. Softmax regression is usually used on the top fully connected layer. Define the output of the softmax function as

其中k表示输出层网络节点数。where k represents the number of output layer network nodes.

其中卷积层通过使用一定数量的卷积核来提取输入数据在时域上的不同特征,通过池化层可以有效的缩小参数矩阵的尺寸,从而减少最后连接层的中的参数数量,加入池化层可以加快计算速度以及防止模型过拟合,最后利用全连接层将高维隐含层中的特征参数映射至原始的输入数据,从而训练模型的特征提取能力。The convolution layer uses a certain number of convolution kernels to extract different features of the input data in the time domain. The pooling layer can effectively reduce the size of the parameter matrix, thereby reducing the number of parameters in the final connection layer and adding the pool The fully connected layer can speed up the calculation and prevent the model from over-fitting. Finally, the fully connected layer is used to map the feature parameters in the high-dimensional hidden layer to the original input data, thereby training the feature extraction capability of the model.

其次,选择合适的迭代次数和损失函数,将所构建好的三维训练数据集输入特征提取模型反复执行前向传播和反向传播迭代计算过程;在此过程中,对卷积层、池化层、全连接层的模型参数不断进行调整,以完成模型的预训练。Secondly, select the appropriate number of iterations and loss function, and input the constructed three-dimensional training data set into the feature extraction model to repeatedly perform the forward propagation and back propagation iterative calculation processes; during this process, the convolution layer and the pooling layer are , The model parameters of the fully connected layer are continuously adjusted to complete the pre-training of the model.

再次,取出预训练模型的两层卷积层和两层池化层以及一层全连接层,并保留其权重参数,将其构建为训练后的深度卷积神经网络一次自编码模型。Third, take out the two convolutional layers, two pooling layers and one fully connected layer of the pre-trained model, retain their weight parameters, and build them into a trained deep convolutional neural network one-pass autoencoding model.

最后,基于完成预训练的卷积神经网络一次自编码模型对训练数据集{S1,nor,S2,nor,...Ssn,nor}进行卷积特征提取,从而得到卷积特征集{F1,CNN,F2,CNN,...,Fsn,CNN}。Finally, based on the pre-trained convolutional neural network one-time autoencoding model, the convolution feature extraction is performed on the training data set {S 1, nor , S 2, nor ,...S sn, nor } to obtain the convolution feature set. {F 1,CNN ,F 2,CNN ,...,F sn,CNN }.

四、对训练数据集进行基于专家知识的人工时域特征提取4. Extract artificial time domain features based on expert knowledge from the training data set

如图4的右侧图所示,对切割出的训练数据集Strain={S1,nor,S2,nor,...Sn,nor}进行基于专家知识的时域特征提取。具体包括对归一化训练数据进行滑窗切割,对切割出的每个样本提取不同的时域数据以及时域特征的归一化处理。As shown in the right diagram of Figure 4, time domain feature extraction based on expert knowledge is performed on the cut training data set S train ={S 1, nor , S 2, nor ,...S n, nor }. Specifically, it includes sliding window cutting of the normalized training data, extracting different time domain data for each cut sample, and normalizing the time domain features.

对归一化的样本数据进行滑窗切割:窗口长度为w′,步长为1,对于样本Si={x1,x2,...xw}可切割出w-w′+1个样本,每个样本长度为w′,即得到{S′1,S′2,...S′w-w′+1}。Perform sliding window cutting on the normalized sample data: the window length is w′, the step size is 1, and for the sample Si = {x 1 , x 2 ,...x w }, ww′+1 samples can be cut , the length of each sample is w′, that is, {S′ 1 , S′ 2 ,...S′ ww′+1 }.

对每个样本S′i分别提取最大值、标准差、方差、波形因子、均方根、脉冲指数、裕度因子、峰值因子八个时域特征:对于窗口数据S′i提取的时域特征为Fi={f1,f2,...,f8},因此对于样本Si提取的人工特征为{F1,F2,...Fw-w′+1},利用极大极小值归一方法对人工特征进行归一化处理,具体可参考综合数据预处理中的步骤2。For each sample S′ i , eight time domain features are extracted: maximum value, standard deviation, variance, waveform factor, root mean square, impulse index, margin factor, and peak factor: for the time domain features extracted from window data S′ i is F i ={f 1 , f 2 ,..., f 8 }, so the artificial features extracted for sample S i are {F 1 , F 2 ,...F ww′+1 }, using the maximum polar The small value normalization method normalizes artificial features. For details, please refer to step 2 in comprehensive data preprocessing.

五、对基于专家知识提取的人工特征和基于CNN特征提取模型提取的高维隐含层特征进行特征拼接5. Feature splicing of artificial features extracted based on expert knowledge and high-dimensional hidden layer features extracted based on CNN feature extraction model

继续参考图1和图4,在CNN特征提取模型提取高维隐含层特征和人工特征提取模块提取人工时域特征之后,对所述高维隐含层特征和人工时域特征进行特征拼接。CNN特征提取模型提取的特征矩阵为MCNN,其形状尺寸为其中nf为卷积核个数,sf为卷积核步长,f为卷积核尺寸。人工特征提取模块提取的人工时域特征矩阵为Mmanual,其形状尺寸为(w-w′+1,8)。分别将两个特征尺寸MCNN,Mmanual进行Flatten展平,并沿列方向进行拼接,得到的融合特征的尺寸为:Continuing to refer to Figures 1 and 4, after the CNN feature extraction model extracts high-dimensional hidden layer features and the artificial feature extraction module extracts artificial time-domain features, the high-dimensional hidden layer features and artificial time-domain features are feature spliced. The feature matrix extracted by the CNN feature extraction model is M CNN , and its shape and size are Where n f is the number of convolution kernels, s f is the convolution kernel step size, and f is the convolution kernel size. The artificial time domain feature matrix extracted by the artificial feature extraction module is M manual , and its shape and size are (ww′+1, 8). Flatten the two feature sizes M CNN and M manual respectively, and splice them along the column direction. The size of the resulting fused feature is:

对训练数据集Strain={S1,nor,S2,nor,...Sn,nor}中每个样本Si,nor进行CNN特征提取和人工特征提取并进行特征融合。令融合特征的维度为nmerge,则可将训练数据集重新组织为(n,nmerge)的二维融合特征矩阵,并把此融合特征矩阵作为后续SAE编码模型的输入。Perform CNN feature extraction and artificial feature extraction and perform feature fusion for each sample S i, nor in the training data set S train = {S 1, nor , S 2, nor ,...S n, nor }. Let the dimension of the fusion feature be n merge , then the training data set can be reorganized into a two-dimensional fusion feature matrix of (n, n merge ), and this fusion feature matrix can be used as the input of the subsequent SAE coding model.

六、进行基于堆叠自编码器(SAE)的深度特征融合6. Perform deep feature fusion based on stacked autoencoders (SAE)

参考图5,图5为图1所示的基于SAE的二次自编码器的结构示意图。在此二次自编码器种,进行基于堆叠自编码器的深度特征融合,具体包括构建二次自编码器和解码器,训练二次编码器和解码器以及使用堆叠的二次自编码器进行深度特征融合。Refer to Figure 5, which is a schematic structural diagram of the SAE-based quadratic autoencoder shown in Figure 1. In this quadratic autoencoder, deep feature fusion based on stacked autoencoders is performed, which specifically includes building quadratic autoencoders and decoders, training quadratic autoencoders and decoders, and using stacked quadratic autoencoders. Deep feature fusion.

首先,构建堆叠二次自编码器和解码器模型,其模型结构如图5所示,编码层数与解码层数相同,能够使得模型对深度特征具有更好的二次编码能力。First, a stacked quadratic autoencoder and decoder model is constructed. The model structure is shown in Figure 5. The number of encoding layers is the same as the number of decoding layers, which enables the model to have better secondary encoding capabilities for deep features.

其次,利用步骤(五)中得到的二维融合特征矩阵进行二次自编码器模型的预训练,以二维融合特征矩阵作为堆叠二次自编码模型的输入和输出,选择合适的损失函数和迭代次数,完成前向传播和反向传播迭代计算过程,使模型不断重构自身输入,最终从完成预训练的堆叠二次自编码器模型中提取其中的编码层作为可用的二次自编码模型。Secondly, use the two-dimensional fusion feature matrix obtained in step (5) to pre-train the quadratic autoencoder model, use the two-dimensional fusion feature matrix as the input and output of the stacked quadratic autoencoder model, and select the appropriate loss function and The number of iterations, completes the iterative calculation process of forward propagation and back propagation, so that the model continuously reconstructs its own input, and finally extracts the coding layer from the stacked quadratic autoencoder model that has completed pre-training as a usable quadratic autoencoder model. .

最后,基于预训练得到的二次自编码器模型对深度融合特征进行二次自编码,从而得到二次编码特征集{F′1,F′2,..,F′sn}。Finally, secondary autoencoding is performed on the deep fusion features based on the pre-trained secondary autoencoder model, thereby obtaining the secondary encoding feature set {F′ 1 , F′ 2 , .., F′ sn }.

七、进行时序外推预测模型训练7. Carry out time series extrapolation prediction model training

图1A所示的框图示出了时序外推预测模型训练的执行步骤和方法,其具体包括构建时序外推预测模型,训练外推预测器模型以及使用外推预测期进行预测。The block diagram shown in Figure 1A shows the execution steps and methods of time series extrapolation prediction model training, which specifically include building a time series extrapolation prediction model, training the extrapolation predictor model and using the extrapolation prediction period for prediction.

步骤7.1:利用在进行基于卷积神经网络的特征提取过程中得到的卷积神经网络一次自编码器和基于SAE的二次自编码过程中得到的堆叠二次自编码器模型,构建时序外推预测器,该外推预测器将CNN特征与人工特征进行了融合而且对深度特征进行了二次编码,再将二次编码特征与标签数据建立映射关系从而完成外推预测。Step 7.1: Use the convolutional neural network primary autoencoder obtained during the feature extraction process based on the convolutional neural network and the stacked quadratic autoencoder model obtained during the SAE-based secondary autoencoder process to construct the time series extrapolation Predictor, this extrapolation predictor fuses CNN features and artificial features and performs secondary coding on the depth features, and then establishes a mapping relationship between the secondary coding features and the label data to complete the extrapolation prediction.

步骤7.2:综合训练CNN卷积特征提取器和时序外推预测器。时序外推预测模型以原始输入数据作为输入,首先进行人工特征提取,利用经过预训练的CNN特征提取模型对原始数据进行CNN卷积特征提取,然后对CNN卷积特征与人工时域特征进行特征融合,并将训练数据标签Strainy作为时序外推预测模型输出,以此完成外推预测器模型的训练。Step 7.2: Comprehensive training of CNN convolutional feature extractor and temporal extrapolation predictor. The time series extrapolation prediction model takes the original input data as input, first performs manual feature extraction, uses the pre-trained CNN feature extraction model to perform CNN convolution feature extraction on the original data, and then characterizes the CNN convolution features and artificial time domain features. Fusion, and the training data label S trainy is used as the output of the time series extrapolation prediction model to complete the training of the extrapolation predictor model.

步骤7.3、利用训练好的时序外推预测模型对已有数据进行预测,对于长度为w的输入数据,其预测数据长度为W-w,截取已有数据中长度为2w-W的数据段与预测数据进行拼接,以此作为新一轮预测的输入,不断往复迭代知道达到人为预设的预测长度Lp,则预测结束。Step 7.3. Use the trained time series extrapolation prediction model to predict the existing data. For the input data with length w, the predicted data length is Ww. Intercept the data segment with length 2w-W in the existing data and the predicted data. Carry out splicing and use this as the input for a new round of prediction, and continue to iterate until the artificially preset prediction length L p is reached, then the prediction ends.

步骤7.4、将综合数据预处理单元得到的验证集数据送入时序外推预测模型,结合相应的预测指标,可完成模型的预测性能评估。Step 7.4: Send the verification set data obtained by the comprehensive data preprocessing unit into the time series extrapolation prediction model, and combine it with the corresponding prediction indicators to complete the prediction performance evaluation of the model.

【基于特征融合的特征提取示例】[Example of feature extraction based on feature fusion]

本发明的一个重要工作在于创新地设计了基于深度神经网络的人工特征与卷积特征融合的特征提取方法,该方法直接影响外推预测模型的液压作动系统退化趋势预测及健康评估。基于此,我们以舵机系统“作动筒内漏”故障,选取“流量注入点”测点采集的反馈角度数据进行示例说明。An important work of the present invention is to innovatively design a feature extraction method based on the fusion of artificial features and convolutional features based on deep neural networks. This method directly affects the degradation trend prediction and health assessment of the hydraulic actuator system of the extrapolation prediction model. Based on this, we use the "actuator internal leakage" fault of the steering gear system and select the feedback angle data collected at the "flow injection point" measuring point as an example.

电动液压舵机的结构化模型如图2所示,其故障预测设定为“作动筒内漏”故障,其数据为反馈角度时域数据。在获取反馈角度数据后,对此数据进行预处理。在本案例中,选择窗口长度为9000,步长为1,对于每个窗口的数据,前6000长度的数据作为基于卷积神经网络序列外推预测模型的输入,后3000长度的数据作为该窗口的标签数据,即为预测数据。对于全部归一化的反馈角度数据,选取前70%的数据作为训练数据集,剩下的30%数据作为验证数据集,用于验证模型预测性能。The structured model of the electro-hydraulic steering gear is shown in Figure 2. Its fault prediction is set to the "actuator internal leakage" fault, and its data is feedback angle time domain data. After obtaining the feedback angle data, preprocess the data. In this case, the window length is selected as 9000 and the step size is 1. For the data of each window, the first 6000 length of data is used as the input of the sequence extrapolation prediction model based on the convolutional neural network, and the last 3000 length of data is used as the window. The label data is the prediction data. For all normalized feedback angle data, the first 70% of the data is selected as the training data set, and the remaining 30% of the data is used as the verification data set to verify the model prediction performance.

1、得到训练数据后,进行基于卷积神经网络的特征提取1. After obtaining the training data, perform feature extraction based on convolutional neural network

考虑舵机反馈角度数据的参数特性,利用卷积神经网络对归一化样本数据进行样本特征提取。继续参考图1、图3和图4,卷积层通过使用一定数量的卷积核来提取输入数据在时域上的不同特征,通过池化层可以有效的缩小参数矩阵的尺寸,从而减少最后连接层的中的参数数量,加入池化层可以加快计算速度以及防止模型过拟合,利用两层卷积层将原式数据映射至高维隐含空间以此学习数据的非线性特征,再结合展平层和全连接层将高维样本特征重映射至原始的输入数据从而学习原始样本的关键特征,选取将原始数据样本映射到低维特征空间的模块作为模型的编码器,选取提取筛选后的特征重构样本的模块作为模型的解码器。本发明选择的模型结构参数如表1所示Considering the parameter characteristics of the steering gear feedback angle data, the convolutional neural network is used to extract sample features from the normalized sample data. Continuing to refer to Figure 1, Figure 3 and Figure 4, the convolution layer uses a certain number of convolution kernels to extract different features of the input data in the time domain. The pooling layer can effectively reduce the size of the parameter matrix, thereby reducing the final The number of parameters in the connection layer. Adding a pooling layer can speed up calculations and prevent model overfitting. Use two layers of convolutional layers to map the original data to a high-dimensional implicit space to learn the nonlinear characteristics of the data, and then combine The flattening layer and the fully connected layer remap the high-dimensional sample features to the original input data to learn the key features of the original samples. The module that maps the original data samples to the low-dimensional feature space is selected as the encoder of the model. After extraction and screening, The module of the feature reconstruction sample serves as the decoder of the model. The model structure parameters selected by this invention are shown in Table 1

表1 基于卷积神经网络的一次自编码器模型参数Table 1 Parameters of linear autoencoder model based on convolutional neural network

选择合适的迭代次数和损失函数,将所构建好的三维训练数据集输入特征提取模型反复执行前向传播和反向传播迭代计算过程,对卷积层、池化层、全连接层的模型参数不断进行调整完成模型的预训练,取出预训练模型的两层卷积层和两层池化层以及一层全连接层,并保留其权重参数,将其构建为CNN特征提取模型。Select the appropriate number of iterations and loss function, input the constructed three-dimensional training data set into the feature extraction model, and repeatedly perform the forward propagation and back propagation iterative calculation processes to calculate the model parameters of the convolution layer, pooling layer, and fully connected layer. Continuously adjust and complete the pre-training of the model. Take out the two convolutional layers, two pooling layers and one fully connected layer of the pre-trained model, retain their weight parameters, and construct it as a CNN feature extraction model.

2、对切割出的训练数据集进行基于专家知识的时域特征提取2. Extract time domain features based on expert knowledge from the cut training data set.

具体地,以窗口长度为3000,步长为3000再对每个窗口的训练数据进行切割并对每个子窗口的数据进行人工特征提取,特征提取结果如图7A和图7B所示。Specifically, the window length is 3000 and the step size is 3000, then the training data of each window is cut and manual feature extraction is performed on the data of each sub-window. The feature extraction results are shown in Figure 7A and Figure 7B.

3、对基于专家知识提取的人工特征和基于CNN特征提取模型提取的高维隐含层特征进行特征拼接3. Feature splicing of artificial features extracted based on expert knowledge and high-dimensional hidden layer features extracted based on CNN feature extraction model

4、进行基于堆叠自编码器的深度特征融合4. Perform deep feature fusion based on stacked autoencoders

利用二维融合特征矩阵进行二次自编码器模型的预训练,以二维融合特征矩阵作为堆叠二次自编码模型的输入和输出,选择合适的损失函数和迭代次数,完成前向传播和反向传播迭代计算过程,使模型不断重构自身输入,最终从完成预训练的堆叠二次自编码器模型中提取其中的编码层作为可用的二次自编码模型。Use the two-dimensional fusion feature matrix to pre-train the quadratic autoencoder model, use the two-dimensional fusion feature matrix as the input and output of the stacked quadratic autoencoder model, select the appropriate loss function and number of iterations, and complete the forward propagation and inverse The iterative calculation process of forward propagation enables the model to continuously reconstruct its own input, and finally extract the coding layer from the stacked quadratic autoencoder model that has completed pre-training as a usable quadratic autoencoder model.

5、时序外推预测模型训练5. Time series extrapolation prediction model training

利用预训练得到的卷积神经网络一次自编码器和堆叠二次自编码器模型构建时序外推预测器,该外推预测器将CNN特征与人工特征进行了融合而且对深度特征进行了二次编码,再将二次编码特征与标签数据建立映射关系从而完成外推预测,该时序外推预测模型以原始输入数据作为输入,首先进行人工特征提取,利用经过预训练的CNN提特模型对原始数据进行CNN提特,然后对CNN特征与人工特征进行特征融合,并将训练数据标签作为模型输出以此完成模型训练。利用训练好的预测模型对已有数据进行预测,将外推数据与原始数据进行拼接以此作为新一轮预测的输入,不断往复迭代知道达到人为预设的预测长度,则预测结束,预测结果如图8所示,预测结果与真实标签对比结果如图9A和图9B所示。The pre-trained convolutional neural network first-order autoencoder and stacked quadratic autoencoder models are used to construct a temporal extrapolation predictor. The extrapolation predictor fuses CNN features with artificial features and performs a second step on deep features. coding, and then establish a mapping relationship between the secondary coding features and the label data to complete the extrapolation prediction. The time series extrapolation prediction model takes the original input data as input, first performs manual feature extraction, and uses the pre-trained CNN Tit model to predict the original The data is extracted by CNN, and then the CNN features and artificial features are feature fused, and the training data labels are used as model output to complete the model training. Use the trained prediction model to predict the existing data, splice the extrapolated data with the original data as the input for a new round of prediction, and continue iterating until the preset prediction length is reached, then the prediction ends and the prediction result As shown in Figure 8, the comparison results between the prediction results and the real labels are shown in Figure 9A and Figure 9B.

尽管已经参考附图所示的实施例描述了本发明,但是可在不脱离权利要求范围的情况下使用等同或替代手段。本发明所描述和图示的组件仅仅是可以用于实现本公开的实施例的系统/设备和方法的示例,并且可以在不脱离权利要求范围的情况下用其他设备和组件进行替换。Although the invention has been described with reference to the embodiments shown in the drawings, equivalent or alternative means may be used without departing from the scope of the claims. The components described and illustrated herein are merely examples of systems/devices and methods that may be used to implement embodiments of the present disclosure, and may be substituted with other devices and components without departing from the scope of the claims.

Claims (9)

1.一种基于二次自编码融合机制的电动液压舵机参数退化时序外推预测方法,包括:1. A time series extrapolation prediction method for electro-hydraulic steering gear parameter degradation based on the quadratic auto-encoding fusion mechanism, including: 获取电动液压舵机的故障预测数据;Obtain failure prediction data of electro-hydraulic steering gear; 对所述故障数据进行综合预处理,以得到训练数据集和测试数据集;Perform comprehensive preprocessing on the fault data to obtain a training data set and a test data set; 构建时序外推预测器,其特征在于:Construct a time series extrapolation predictor characterized by: 所述时序外推预测器包括卷积神经网络一次自编码器、基于专家知识的人工时域特征提取器,以及基于SAE的二次自编码器;The time series extrapolation predictor includes a convolutional neural network primary autoencoder, an artificial time domain feature extractor based on expert knowledge, and a secondary autoencoder based on SAE; 所述时序外推预测器将所述训练数据集进行融合得到融合特征,而且所述二次自编码器对所述融合特征进行二次编码,而后再将二次编码特征与标签数据建立映射关系;The time series extrapolation predictor fuses the training data set to obtain fusion features, and the secondary autoencoder performs secondary coding on the fused features, and then establishes a mapping relationship between the secondary coding features and the label data. ; 综合训练所述卷积神经网络一次自编码器和所述时序外推预测器,得到训练好的时序外推预测器;以及Comprehensive training of the convolutional neural network primary autoencoder and the temporal extrapolation predictor to obtain a trained temporal extrapolation predictor; and 利用训练好的时序外推预测模型对对已有数据进行预测。Use the trained time series extrapolation prediction model to predict existing data. 2.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,所述时序外推预测模型以原始的训练数据集作为输入,首先基于人工时域特征提取器进行人工特征提取,利用经过预训练的卷积神经网络特征提取模型对原始的训练数据集进行卷积特征提取,然后对卷积特征与人工时域特征进行特征融合,并将训练数据标签Strainy作为时序外推预测模型输出,以此完成外推预测器模型的训练。2. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method according to claim 1, characterized in that the time series extrapolation prediction model takes the original training data set as input and is first based on an artificial time domain feature extractor. Manual feature extraction, using the pre-trained convolutional neural network feature extraction model to extract convolutional features from the original training data set, and then feature fusion of the convolutional features and artificial time domain features, and use the training data label S trainy as The time series extrapolation prediction model output is used to complete the training of the extrapolation predictor model. 3.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,对所述已有数据进行预测时,对于长度为w的输入数据,其预测数据长度为W-w,截取已有数据中长度为2w-W的数据段与预测数据进行拼接,以此作为新一轮预测的输入,不断往复迭代知道达到人为预设的预测长度Lp,则预测结束。3. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method according to claim 1, characterized in that when predicting the existing data, for the input data with a length of w, the predicted data length is Ww, Intercept the data segment with a length of 2w-W in the existing data and splice it with the prediction data, and use this as the input of a new round of prediction. Iterate continuously until the artificially preset prediction length L p is reached, then the prediction ends. 4.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,将经过综合预处理得到的验证集数据送入所述时序外推预测模型,结合相应的预测指标,完成模型的预测性能评估。4. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method according to claim 1, characterized in that the verification set data obtained through comprehensive preprocessing is sent to the time series extrapolation prediction model, combined with the corresponding prediction indicators. , complete the prediction performance evaluation of the model. 5.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,所述综合预处理步骤包括对关键参数时序数据进行滑窗切割,所述关键参数时序数据为X,X={x1,x2,...xN},对X进行滑窗切割从而生成相应的样本数据集,当窗口宽度为W,步长为s时,切割生成的样本数量为:5. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method according to claim 1, characterized in that the comprehensive preprocessing step includes sliding window cutting of key parameter time series data, and the key parameter time series data is X , X={x 1 , x 2 ,...x N }, perform sliding window cutting on 则生成相应的数据集为{S1,S2,...Ssn},对{S1,nor,S2,nor,...Ssn,nor}中的每个样本Si,nor取长度为w的数据作为训练数据,取W-w长度的数据作为这段训练数据对应的预测数据。Then the corresponding data set is generated as {S 1 , S 2 ,...S sn }, for each sample Si, nor in {S 1, nor , S 2, nor ,...S sn, nor } Take the data of length w as the training data, and take the data of length Ww as the prediction data corresponding to this training data. 6.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,所述卷积神经网络一次自编码器的构建包括基于所述训练数据集Strain={S1,nor,S2,nor,...Sn,nor},将其数据格式转化为三维数据格式(sn,w,1),将所构建好的三维训练数据集输入一次自编码器反复执行前向传播和反向传播迭代计算过程,以对所构建的一次自编码模型的卷积层、池化层、全连接层的模型参数不断进行调整,以完成模型的预训练,其中{S1,nor,S2,or,...Ssn,nor}为经过归一化处理的样本数据集,sn为样本数量,w为每个样本的数据长度,1为通道数。6. The electro-hydraulic steering gear parameter degradation time series extrapolation prediction method according to claim 1, characterized in that the construction of the convolutional neural network one-time autoencoder includes based on the training data set S train = {S 1 ,nor ,S 2,nor ,...S n,nor }, convert its data format into a three-dimensional data format (sn, w, 1), input the constructed three-dimensional training data set once and execute the autoencoder repeatedly. The iterative calculation process of forward propagation and back propagation is used to continuously adjust the model parameters of the convolution layer, pooling layer, and fully connected layer of the constructed primary autoencoding model to complete the pre-training of the model, where {S 1 , nor , S 2, or ,...S sn, nor } is the normalized sample data set, sn is the number of samples, w is the data length of each sample, and 1 is the number of channels. 7.根据权利要求6所述的电动液压舵机参数退化时序外推预测方法,其特征在于,所述一次自编码模型包括多个卷积层、多个池化层和一个Flatten全连接层,所述全连接层利用多层堆叠的卷积层和池化提取的特征进行特征识别,在所述全连接层上使用softmax回归,所述softmax函数的输出为7. The electro-hydraulic steering gear parameter degradation timing extrapolation prediction method according to claim 6, characterized in that the one-time autoencoding model includes multiple convolutional layers, multiple pooling layers and a Flatten fully connected layer, The fully connected layer uses features extracted by multi-layer stacked convolutional layers and pooling for feature recognition. Softmax regression is used on the fully connected layer. The output of the softmax function is 其中k表示输出层网络节点数。where k represents the number of output layer network nodes. 8.根据权利要求1所述的电动液压舵机参数退化时序外推预测方法,其特征在于,在所述基于SAE的二次自编码器中进一步以二维融合特征矩阵对所述二次编码器和解码器进行预训练;以二维融合特征矩阵作为所述二次自编码的输入和输出,选择合适的损失函数和迭代次数,完成前向传播和反向传播迭代计算过程,使模型不断重构自身输入,最终从完成预训练的二次自编码器模型中提取其中的编码层作为可用的二次自编码模型。8. The electro-hydraulic steering gear parameter degradation timing extrapolation prediction method according to claim 1, characterized in that in the SAE-based secondary autoencoder, the secondary encoding is further performed with a two-dimensional fusion feature matrix. The decoder and decoder are pre-trained; the two-dimensional fusion feature matrix is used as the input and output of the secondary autoencoder, the appropriate loss function and the number of iterations are selected, and the forward propagation and back propagation iterative calculation processes are completed to make the model continuously Reconstruct its own input, and finally extract the coding layer from the pre-trained quadratic autoencoder model as a usable quadratic autoencoder model. 9.根据权利要求8所述的电动液压舵机参数退化时序外推预测方法,其特征在于,基于预训练得到的二次自编码器模型对深度融合特征进行二次自编码,从而得到二次编码特征集{F′1,F′2,...,F′sn}。9. The electro-hydraulic steering gear parameter degradation timing extrapolation prediction method according to claim 8, characterized in that, based on the quadratic autoencoder model obtained by pre-training, the deep fusion features are quadratic auto-encoded to obtain the quadratic autoencoder. Encoding feature set {F′ 1 , F′ 2 , ..., F′ sn }.
CN202110824289.9A 2021-07-21 2021-07-21 Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism Active CN113536682B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110824289.9A CN113536682B (en) 2021-07-21 2021-07-21 Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110824289.9A CN113536682B (en) 2021-07-21 2021-07-21 Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism

Publications (2)

Publication Number Publication Date
CN113536682A CN113536682A (en) 2021-10-22
CN113536682B true CN113536682B (en) 2024-01-23

Family

ID=78100684

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110824289.9A Active CN113536682B (en) 2021-07-21 2021-07-21 Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism

Country Status (1)

Country Link
CN (1) CN113536682B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114063601A (en) * 2021-11-12 2022-02-18 江苏核电有限公司 Equipment state diagnosis system and method based on artificial intelligence
CN114399066B (en) * 2022-01-15 2023-04-18 中国矿业大学(北京) Mechanical equipment predictability maintenance system and maintenance method based on weak supervision learning
CN116753471A (en) * 2023-06-15 2023-09-15 重庆中法环保研发中心有限公司 Water supply pipeline leakage multi-domain feature extraction and fusion identification method
CN116776228B (en) * 2023-08-17 2023-10-20 合肥工业大学 A decoupled self-supervised pre-training method and system for power grid time series data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109634139A (en) * 2018-12-10 2019-04-16 中国航天空气动力技术研究院 Hypersonic aircraft navigation and control system semi-matter simulating system and method
CN112257760A (en) * 2020-09-30 2021-01-22 北京航空航天大学 A method for abnormal detection of host network communication behavior based on timing motif
CN113035280A (en) * 2021-03-02 2021-06-25 四川大学 RBP binding site prediction algorithm based on deep learning

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11531802B2 (en) * 2019-10-18 2022-12-20 Taiwan Semiconductor Manufacturing Company Ltd. Layout context-based cell timing characterization

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109634139A (en) * 2018-12-10 2019-04-16 中国航天空气动力技术研究院 Hypersonic aircraft navigation and control system semi-matter simulating system and method
CN112257760A (en) * 2020-09-30 2021-01-22 北京航空航天大学 A method for abnormal detection of host network communication behavior based on timing motif
CN113035280A (en) * 2021-03-02 2021-06-25 四川大学 RBP binding site prediction algorithm based on deep learning

Also Published As

Publication number Publication date
CN113536682A (en) 2021-10-22

Similar Documents

Publication Publication Date Title
CN113536682B (en) Electric hydraulic steering engine parameter degradation time sequence extrapolation prediction method based on secondary self-coding fusion mechanism
CN113536681B (en) Electric steering engine health assessment method based on time sequence extrapolation prediction
CN112100865B (en) Method for predicting remaining life of aircraft engine based on parallel CNN model
Ke et al. Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network
Xu et al. RUL prediction for rolling bearings based on Convolutional Autoencoder and status degradation model
CN109214575A (en) A kind of super short-period wind power prediction technique based on small wavelength short-term memory network
CN113536683B (en) A feature extraction method based on the fusion of artificial features and convolution features based on deep neural networks
CN116679211B (en) Lithium battery health state prediction method
CN102562239A (en) Method for monitoring exhaust temperature of aircraft engine
CN105760961A (en) Photovoltaic output power prediction method and system
CN116957698A (en) Electricity price prediction method based on improved time sequence mode attention mechanism
CN113988449A (en) Wind power prediction method based on Transformer model
CN113627093A (en) Underwater mechanism cross-scale flow field characteristic prediction method based on improved Unet network
CN115795683A (en) An airfoil optimization method combining CNN and Swin Transformer network
CN117852686A (en) Power load prediction method based on multi-element self-encoder
CN114819386A (en) Conv-Transformer-based flood forecasting method
CN115017826A (en) A method for predicting the remaining service life of equipment
CN116843057A (en) Wind power ultra-short-term prediction method based on LSTM-ViT
CN114334041A (en) A Transformer-based high-precision prediction method for complex spectra of electromagnetic metamaterials
CN117350554A (en) A general prediction method taking into account the output of scenery and solar energy
WO2025040160A1 (en) Method, system and apparatus for temporarily replacing faulty wind lidar
CN117353286A (en) A short-term load forecasting method based on multiple similar days and stacking learning
CN116483036A (en) A Transformer-based Autoencoder Soft Sensor Modeling Method
CN118194139B (en) Spatio-temporal data prediction method based on adaptive graph learning and nerve controlled differential equation
CN114444790A (en) Time series prediction method of various measuring points on gas turbine based on steady state feature composition

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