CN115048959A - RMSD-DS-based gun recoil prevention device fault diagnosis method - Google Patents

RMSD-DS-based gun recoil prevention device fault diagnosis method Download PDF

Info

Publication number
CN115048959A
CN115048959A CN202210649020.6A CN202210649020A CN115048959A CN 115048959 A CN115048959 A CN 115048959A CN 202210649020 A CN202210649020 A CN 202210649020A CN 115048959 A CN115048959 A CN 115048959A
Authority
CN
China
Prior art keywords
evidence
fault
rmsd
recoil
reliability
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
CN202210649020.6A
Other languages
Chinese (zh)
Other versions
CN115048959B (en
Inventor
魏剑峰
张发平
卢继平
杨向飞
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.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
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 Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202210649020.6A priority Critical patent/CN115048959B/en
Publication of CN115048959A publication Critical patent/CN115048959A/en
Application granted granted Critical
Publication of CN115048959B publication Critical patent/CN115048959B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Locating Faults (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

本发明公开的基于RMSD‑DS的火炮反后坐装置故障诊断方法，属于火炮故障诊断领域。本发明首先确定火炮反后坐装置的典型故障模式和故障特性信号，通过高斯模型获取每种故障特性信号相对应证据的概率分配；然后通过构造RMSD相似系数和求解每个证据的可靠度定量描述每个证据在融合决策郭总中的重要程度，据此给证据分配权重，以此消除信息间的冲突影响；最后求解加权平均后的整合证据，应用DS融合规则对整合证据进行自身融合，得到最终的融合结果，实现火炮反后坐装置的故障诊断。本发明求解每种故障特性信号所对应证据的基本概率分配值的方法简易，故障诊断效果优越。本发明能够提高融合冲突信息时火炮反后坐装置故障诊断效率和精度。

Figure 202210649020

The invention discloses a RMSD-DS-based artillery anti-recoil device fault diagnosis method, which belongs to the field of artillery fault diagnosis. The invention first determines the typical failure mode and failure characteristic signal of the anti-recoil device of the artillery, and obtains the probability distribution of each kind of fault characteristic signal corresponding to the evidence through the Gaussian model; The importance of each piece of evidence in the fusion decision, according to which weights are assigned to the evidence to eliminate the impact of conflict between information; finally, the weighted average of the integrated evidence is calculated, and the DS fusion rule is used to fuse the integrated evidence itself to obtain the final result. The fusion result is realized, and the fault diagnosis of the artillery anti-recoil device is realized. The method of the invention for solving the basic probability distribution value of the evidence corresponding to each fault characteristic signal is simple, and the fault diagnosis effect is excellent. The invention can improve the fault diagnosis efficiency and precision of the artillery anti-recoil device when the conflicting information is fused.

Figure 202210649020

Description

基于RMSD-DS的火炮反后坐装置故障诊断方法Fault diagnosis method of artillery anti-recoil device based on RMSD-DS

技术领域technical field

本发明涉及基于RMSD-DS的火炮反后坐装置故障诊断方法，属于火炮故障诊断技术领域。The invention relates to a fault diagnosis method for an artillery anti-recoil device based on RMSD-DS, and belongs to the technical field of artillery fault diagnosis.

背景技术Background technique

火炮反后坐装置作为火炮的关键部件，承担着火炮射击时后坐能量的耗散与储存，以及复位炮身的作用。在战场中，作战环境的复杂性和不确定性使得火炮反后坐装置故障频发，若未及时诊断并解决供火炮反后坐装置故障，则会严重影响炮弹发射效率和射击精度，甚至贻误宝贵战机，引发严重的战场事故。因而对火炮反后坐装置的故障诊断方法研究具有重要的现实意义。As a key component of the artillery, the anti-recoil device of the artillery undertakes the dissipation and storage of the recoil energy when the artillery is fired, as well as the function of resetting the gun body. In the battlefield, the complexity and uncertainty of the combat environment make the artillery anti-recoil device failures occur frequently. If the failure of the artillery anti-recoil device is not diagnosed and solved in time, it will seriously affect the firing efficiency and shooting accuracy of artillery shells, and even delay valuable fighter planes. , causing serious battlefield accidents. Therefore, the research on the fault diagnosis method of the anti-recoil device of the artillery has important practical significance.

火炮反后坐装置常以其最大后坐位移、最大后坐速度，最大复进速度和复进到位速度四种信号源为基础开展基于多源信息融合的故障诊断工作。由于战场环境的复杂性，火炮反后坐装置的数据传感器易受到损坏或是数据采集过程受到干扰，导致传感器输出的信息之间存在相互冲突。此时若应用传统的多源信息融合方法，类似于神经网络方法，在辨识火炮反后坐装置的故障诊断模式时易出现诊断效率低下、诊断精度低下的情况，无法满足火炮反后坐装置故障诊断需求。Artillery anti-recoil devices often carry out fault diagnosis based on multi-source information fusion based on four signal sources: maximum recoil displacement, maximum recoil speed, maximum return speed and return speed. Due to the complexity of the battlefield environment, the data sensors of the artillery anti-recoil device are easily damaged or the data acquisition process is disturbed, resulting in conflicting information output by the sensors. At this time, if the traditional multi-source information fusion method is used, similar to the neural network method, when identifying the fault diagnosis mode of the artillery anti-recoil device, it is prone to low diagnostic efficiency and low diagnostic accuracy, which cannot meet the fault diagnosis requirements of the artillery anti-recoil device. .

发明内容SUMMARY OF THE INVENTION

为了解决融合冲突信息时现有火炮反后坐装置故障诊断方法效率低、精度低等问题，本发明的主要目的是提供基于RMSD-DS的火炮反后坐装置故障诊断方法，该方法确定火炮反后坐装置典型故障模式及故障特征信号；采集、获取火炮反后坐装置在典型故障模式下对应的故障特征信号；获取的在典型故障模式下对应的故障特征信号，并将所述故障特征信号分类为故障训练样本数据、故障待检样本数据；求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差，然后构造属于不同故障模式的训练样本在不同故障信号上的高斯模型；根据构建的火炮反后坐装置故障模式高斯模型，求解火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配；根据求解得到的火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配，在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的冲突因子，并根据求解的所有冲突因子，构造冲突因子矩阵；在火炮反后坐装置故障模式框架下，定义并求解各个证据间的均方根偏移(Root Mean Square Deviation,RMSD)距离；以所述冲突因子和所述归一化RMSD距离的几何均值作为RMSD冲突系数的取值，构造RMSD冲突系数；根据构造RMSD冲突系数，求解并构造RMSD相似系数；定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，并根据所述定义确定每个证据的可靠度；分析每个证据的可靠度，定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，并求解每个证据的权重；根据每个证据可靠度对所有证据进行权重分配，降低信息之间的冲突性，然后通过加权平均后得到整合证据；在火炮故障模式框架下利用Dempster-Shafer(DS)证据理论方法对整合证据进行自身融合，得到对应火炮反后坐装置故障模式的发生概率；遍历所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，即基于RMSD-DS实现对火炮反后坐装置故障的高精度效率诊断。In order to solve the problems of low efficiency and low precision of the existing artillery anti-recoil device fault diagnosis method when the conflict information is merged, the main purpose of the present invention is to provide an artillery anti-recoil device fault diagnosis method based on RMSD-DS, which determines the artillery anti-recoil device fault diagnosis method. Typical failure mode and failure characteristic signal; collect and obtain the corresponding failure characteristic signal of the anti-recoil device of the artillery under the typical failure mode; obtain the corresponding failure characteristic signal under the typical failure mode, and classify the failure characteristic signal as failure training Sample data, sample data to be checked for faults; solve the mean and standard deviation of training samples belonging to different failure modes of the artillery anti-recoil device on different fault characteristic signals, and then construct the Gaussian values of training samples belonging to different failure modes on different fault signals Model; According to the constructed Gaussian model of the failure mode of the anti-recoil device of the artillery, the basic probability distribution of the evidence corresponding to the fault characteristic signal of the sample of the anti-recoil device of the artillery to be tested is solved; according to the obtained evidence corresponding to the fault characteristic signal of the sample of the anti-recoil device of the artillery to be tested Under the framework of the failure mode of the artillery anti-recoil device, define and solve the conflict factors between the various evidences, and construct the conflict factor matrix according to all the conflict factors solved; in the framework of the failure mode of the artillery anti-recoil device, define And solve the root mean square deviation (Root Mean Square Deviation, RMSD) distance between each evidence; Take the geometric mean of the conflict factor and the normalized RMSD distance as the value of the RMSD conflict coefficient, and construct the RMSD conflict coefficient; According to constructing the RMSD conflict coefficient, solve and construct the RMSD similarity coefficient; define the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidences, and determine the reliability of each evidence according to the definition; analyze each evidence The reliability of each evidence is defined as the ratio of the reliability of the evidence to the sum of the reliability of all evidence, and the weight of each evidence is calculated; the weight of all evidence is allocated according to the reliability of each evidence to reduce the reliability of information. The conflict between the two, and then obtain the integrated evidence through weighted average; the Dempster-Shafer (DS) evidence theory method is used to fuse the integrated evidence under the framework of the artillery failure mode, and the occurrence probability of the corresponding artillery anti-recoil device failure mode is obtained; The probability of occurrence of failure modes of all artillery anti-recoil devices, and the failure mode corresponding to the maximum basic probability distribution value is determined as the final diagnosis failure mode, that is, based on RMSD-DS to achieve high-precision and efficient diagnosis of artillery anti-recoil device failures.

本发明的目的是通过下述技术方案实现的。The purpose of the present invention is achieved through the following technical solutions.

本发明公开的基于RMSD-DS的火炮反后坐装置故障诊断方法，包括如下步骤：The RMSD-DS-based artillery anti-recoil device fault diagnosis method disclosed by the present invention comprises the following steps:

步骤一：确定火炮反后坐装置典型故障模式及故障特征信号。Step 1: Determine the typical failure mode and failure characteristic signal of the artillery anti-recoil device.

步骤二：采集、获取火炮反后坐装置在典型故障模式下对应的故障特征信号。Step 2: Collect and obtain the fault characteristic signal corresponding to the artillery anti-recoil device under the typical fault mode.

步骤三：分析步骤二获取的在典型故障模式下对应的故障特征信号，并将所述故障特征信号分类为故障训练样本数据、故障待检样本数据；求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差，然后构造属于不同故障模式的训练样本在不同故障信号上的高斯模型。Step 3: Analyze the corresponding fault characteristic signals in the typical fault mode obtained in step 2, and classify the fault characteristic signals into fault training sample data and fault unchecked sample data; solve the training belonging to different fault modes of the artillery anti-recoil device The mean and standard deviation of the samples on different fault characteristic signals, and then construct the Gaussian model of the training samples belonging to different fault modes on different fault signals.

步骤四：根据步骤三构建的火炮反后坐装置故障模式高斯模型，求解火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配。Step 4: According to the Gaussian model of the failure mode of the artillery anti-recoil device constructed in step 3, the basic probability distribution of the evidence corresponding to the fault characteristic signal of the sample to be inspected for the artillery anti-recoil device is solved.

步骤五：根据步骤四求解得到的火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配，在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的冲突因子，并根据求解的所有冲突因子，构造冲突因子矩阵；在火炮反后坐装置故障模式框架下，定义并求解各个证据间的RMSD距离；以所述冲突因子和所述归一化RMSD距离的几何均值作为RMSD冲突系数的取值，构造RMSD冲突系数；根据构造RMSD冲突系数，求解并构造RMSD相似系数，通过构造的RMSD相似系数便于定义后续步骤六的可靠度。Step 5: According to the basic probability distribution of the evidence corresponding to the fault characteristic signal of the artillery anti-recoil device to be inspected obtained in step 4, define and solve the conflict factors between the various evidences under the framework of the failure mode of the artillery anti-recoil device. All conflict factors solved, construct conflict factor matrix; under the framework of artillery anti-recoil device failure mode, define and solve the RMSD distance between each evidence; take the geometric mean of the conflict factor and the normalized RMSD distance as the RMSD conflict According to the value of the coefficient, the RMSD conflict coefficient is constructed; according to the constructed RMSD conflict coefficient, the RMSD similarity coefficient is solved and constructed, and the reliability of the subsequent step 6 is easily defined by the constructed RMSD similarity coefficient.

步骤六：定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，并根据所述定义确定每个证据的可靠度；分析每个证据的可靠度，定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，并求解每个证据的权重；根据每个证据可靠度对所有证据进行权重分配，降低信息之间的冲突性，然后通过加权平均后得到整合证据，便于后续步骤七的融合，提高故障诊断正确率。Step 6: Define the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidence, and determine the reliability of each evidence according to the definition; analyze the reliability of each evidence, and define the weight of each evidence It is the ratio of the reliability of the evidence to the sum of the reliability of all the evidence, and solves the weight of each evidence; according to the reliability of each evidence, weights are assigned to all evidences to reduce the conflict between information, and then through the weighted average The integrated evidence is obtained, which facilitates the fusion of the subsequent step 7 and improves the correct rate of fault diagnosis.

步骤七：在火炮故障模式框架，利用Dempster-Shafer(DS)证据理论方法对步骤六得到的整合证据进行自身融合，得到对应火炮反后坐装置故障模式的发生概率；遍历所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，即基于RMSD-DS实现对火炮反后坐装置故障的高精度效率诊断。Step 7: In the artillery failure mode framework, use the Dempster-Shafer (DS) evidence theory method to fuse the integrated evidence obtained in step 6 to obtain the probability of occurrence of the corresponding artillery anti-recoil device failure mode; traverse all artillery anti-recoil device failure modes The probability of occurrence is determined, and the failure mode corresponding to the maximum basic probability distribution value is the failure mode of the final diagnosis, that is, the high-precision and efficient diagnosis of the failure of the artillery anti-recoil device based on RMSD-DS is realized.

还包括步骤八：将步骤三确定的火炮反后坐装置故障待检样本数据代入步骤四构造的故障模式高斯模型中，求解每个故障特征信号所对应证据的基本概率分配；用步骤六确定的可靠度给每个证据重新分配权重，降低冲突信息所带来的影响，提升对反后坐装置故障诊断性能。所述提升对火炮反后坐装置的诊断性能包括提高对反后坐装置的诊断效率、诊断精度。It also includes step 8: Substitute the sample data to be inspected for the fault of the artillery anti-recoil device determined in step 3 into the failure mode Gaussian model constructed in step 4, and solve the basic probability distribution of the evidence corresponding to each fault characteristic signal; It reassigns the weight to each evidence, reduces the impact of conflicting information, and improves the fault diagnosis performance of the anti-recoil device. The improving the diagnostic performance of the artillery anti-recoil device includes improving the diagnostic efficiency and diagnostic accuracy of the anti-recoil device.

步骤一：确定火炮反后坐装置典型故障模式及故障特征信号。Step 1: Determine the typical failure mode and failure characteristic signal of the artillery anti-recoil device.

确定火炮反后坐装置的典型故障模式总共三种，分别为节制环磨损X、复进机漏气Y和制退杆活塞磨损Z，则火炮反后坐装置的故障模式框架表示为Θ＝{X,Y,Z}；确定火炮反后坐装置的故障特性信号分别为：最大后坐位移Xmax、最大后坐速度Vmax、最大复进速度Umax和复进到位速度Uend。Three typical failure modes of the anti-recoil device of the artillery are determined in total, namely, the wear of the control ring X, the leakage of the air Y of the recuperator and the wear of the piston of the brake rod Z, then the failure mode framework of the anti-recoil device of the artillery is expressed as Θ={X, Y, Z}; The fault characteristic signals to determine the anti-recoil device of the artillery are respectively: the maximum recoil displacement Xmax, the maximum recoil speed Vmax, the maximum return speed Umax and the return speed Uend.

步骤二：采集、获取火炮反后坐装置在典型故障模式下对应的故障特征信号。Step 2: Collect and obtain the fault characteristic signal corresponding to the artillery anti-recoil device under the typical fault mode.

火炮工作时，由安装在反后坐装置上的传感器采集反后坐装置在每种故障模式下的四种故障特征信号，所获取的数据用Fi表示，其中F＝X,Y,Z，分别代表节制环磨损，复进机漏气和制退杆活塞磨损三种故障模式；i＝1,2,3,4，分别代表最大后坐位移Xmax，最大后坐速度Vmax，最大复进速度Umax和复进到位速度Uend四种故障特征信号；采集到的一组样本数据表示为(F1,F2,F3,F4)，F1代表故障模式F所对应的最大后坐位移Xmax信号数据，F2代表故障模式F所对应的最大后坐速度Vmax信号数据，F3代表故障模式F所对应的最大复进速度Umax信号数据，F4代表故障模式F所对应的复进到位速度Uend信号数据。When the artillery works, the sensor installed on the anti-recoil device collects four fault characteristic signals of the anti-recoil device in each failure mode. The acquired data is represented by F i , where F=X, Y, Z, representing There are three failure modes: the wear of the control ring, the air leakage of the recoil machine and the wear of the brake rod piston; i=1, 2, 3, 4, representing the maximum recoil displacement Xmax, the maximum recoil speed Vmax, the maximum recoil speed Umax and the recoil speed respectively. In-position speed Uend four fault characteristic signals; a set of sample data collected is represented as (F 1 , F 2 , F 3 , F 4 ), F 1 represents the maximum recoil displacement Xmax signal data corresponding to fault mode F, F 2 Represents the signal data of the maximum recoil speed Vmax corresponding to the failure mode F, F3 represents the signal data of the maximum reversing speed Umax corresponding to the failure mode F, and F4 represents the reversing in-position speed Uend signal data corresponding to the failure mode F. Data.

步骤三：分析步骤二获取的在典型故障模式下对应的故障特征信号，并将所述故障特征信号分类为故障训练样本数据、故障待检样本数据；求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差，然后构造属于不同故障模式的训练样本在不同故障信号上的高斯模型。Step 3: Analyze the corresponding fault characteristic signals in the typical fault mode obtained in step 2, and classify the fault characteristic signals into fault training sample data and fault unchecked sample data; solve the training belonging to different fault modes of the artillery anti-recoil device The mean and standard deviation of the samples on different fault characteristic signals, and then construct the Gaussian model of the training samples belonging to different fault modes on different fault signals.

步骤3.1：将步骤二获取的在典型故障模式下对应的故障特征信号，分类为故障训练样本数据、故障待检样本数据。Step 3.1: Classify the corresponding fault characteristic signals in the typical fault mode obtained in step 2 into fault training sample data and fault unchecked sample data.

基于步骤二获取的在典型故障模式下对应的故障特征信号，分别从各个故障模式中所对应的四种故障特性信号数据中选取预设比例的样本数据作为故障训练样本，剩余样本数据作为故障待检样本。Based on the fault characteristic signals corresponding to the typical fault modes obtained in step 2, a preset proportion of sample data is selected from the four fault characteristic signal data corresponding to each fault mode as the fault training sample, and the remaining sample data is used as the fault pending test sample.

步骤3.2：对于步骤3.1选定的故障训练样本，求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差。Step 3.2: For the fault training samples selected in Step 3.1, calculate the mean and standard deviation of the training samples belonging to different fault modes of the artillery anti-recoil device on different fault characteristic signals.

对于选定的故障训练样本，求解属于不同故障模式的训练样本在不同故障特征信号上的平均值μ(Fi)和标准差σ(Fi)，平均值μ(Fi)的求解公式如式(1)所示，标准差σ(Fi)的求解公式如式(2)所示：For the selected fault training samples, the average μ(F i ) and standard deviation σ(F i ) of the training samples belonging to different failure modes on different fault characteristic signals are calculated. The solution formula of the average μ(F i ) is as follows As shown in Equation (1), the solution formula of the standard deviation σ (Fi ) is shown in Equation (2):

Figure BDA0003685211890000041
Figure BDA0003685211890000041

Figure BDA0003685211890000042
Figure BDA0003685211890000042

式(1)和式(2)中，F＝X,Y,Z，代表三种故障模式；i＝1,2,3,4，代表四种故障特征信号；j＝1,2,…,N，代表数据序列；In formulas (1) and (2), F=X, Y, Z, representing three failure modes; i=1, 2, 3, 4, representing four fault characteristic signals; j=1, 2,..., N, represents the data sequence;

步骤3.3：根据步骤3.2求解得到的平均值和标准差，构造属于不同故障模式的训练样本在不同故障信号上的高斯模型。Step 3.3: Construct Gaussian models of training samples belonging to different failure modes on different failure signals according to the mean value and standard deviation obtained in step 3.2.

根据步骤3.2求解得到的平均值μ(Fi)和标准差σ(Fi)，构造属于不同故障模式的训练样本在在不同故障信号上的高斯模型(隶属度函数)，如公式(3)所示：According to the mean value μ(F i ) and standard deviation σ(F i ) obtained from the solution in step 3.2, the Gaussian model (membership function) of the training samples belonging to different failure modes on different failure signals is constructed, as shown in formula (3) shown:

Figure BDA0003685211890000043
Figure BDA0003685211890000043

式(3)中，F＝X,Y,Z，代表三种故障模式；i＝1,2,3,4，代表四种故障特征信号。In formula (3), F=X, Y, Z, representing three fault modes; i=1, 2, 3, 4, representing four fault characteristic signals.

故障特性信号为最大后坐位移(Xmax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：When the fault characteristic signal is the maximum recoil displacement (Xmax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model is:

Figure BDA0003685211890000044
Figure BDA0003685211890000044

Figure BDA0003685211890000045
Figure BDA0003685211890000045

Figure BDA0003685211890000046
Figure BDA0003685211890000046

故障特性信号为最大后坐速度(Vmax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA0003685211890000047
和
Figure BDA0003685211890000048
When the fault characteristic signal is the maximum recoil speed (Vmax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model is:
Figure BDA0003685211890000047
and
Figure BDA0003685211890000048

Figure BDA0003685211890000049
Figure BDA0003685211890000049

Figure BDA00036852118900000410
Figure BDA00036852118900000410

Figure BDA00036852118900000411
Figure BDA00036852118900000411

故障特性信号为最大复进速度(Umax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA00036852118900000412
和
Figure BDA00036852118900000413
When the fault characteristic signal is the maximum return speed (Umax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model on the wear (Z) is:
Figure BDA00036852118900000412
and
Figure BDA00036852118900000413

Figure BDA0003685211890000051
Figure BDA0003685211890000051

Figure BDA0003685211890000052
Figure BDA0003685211890000052

Figure BDA0003685211890000053
Figure BDA0003685211890000053

得故障特性信号为复进到位速度(Uend)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA0003685211890000054
和
Figure BDA0003685211890000055
When the fault characteristic signal is the return in-position speed (Uend), the failure mode is the control ring wear (X), the air leakage of the return machine (Y) and the brake rod piston wear (Z) The Gaussian model is:
Figure BDA0003685211890000054
and
Figure BDA0003685211890000055

Figure BDA0003685211890000056
Figure BDA0003685211890000056

Figure BDA0003685211890000057
Figure BDA0003685211890000057

Figure BDA0003685211890000058
Figure BDA0003685211890000058

公式(4)至公式(15)即为不同故障模式的训练样本在不同故障信号上的高斯模型。Equations (4) to (15) are the Gaussian models of training samples of different failure modes on different failure signals.

步骤四：根据步骤三构建的火炮反后坐装置故障模式高斯模型，求解火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配，能够保证后续步骤反后坐装置故障诊断精度基础上，提高故障诊断效率。Step 4: According to the Gaussian model of the failure mode of the artillery anti-recoil device constructed in step 3, the basic probability distribution of the evidence corresponding to the fault characteristic signal of the sample to be inspected for the artillery anti-recoil device can be solved, which can ensure the accuracy of the fault diagnosis of the anti-recoil device in the subsequent steps. Troubleshooting Efficiency.

步骤4.1：根据步骤3.3构建的火炮反后坐装置故障模式高斯模型，求解待检样本与每种故障信号下不同故障模式高斯模型的交点纵坐标。Step 4.1: According to the failure mode Gaussian model of the artillery anti-recoil device constructed in step 3.3, solve the ordinate of the intersection of the sample to be tested and the Gaussian model of different failure modes under each failure signal.

对于故障模式未知的一组待检样本，对应的数据可以表示为(F1,F2,F3,F4)，其中F＝X、Y、Z；下标中的1代表最大后坐位移(Xmax)，2代表最大后坐速度(Vmax)，3代表最大复进速度(Umax)，4代表复进到位速度(Uend)。For a set of samples to be tested whose failure mode is unknown, the corresponding data can be expressed as (F 1 , F 2 , F 3 , F 4 ), where F=X, Y, Z; 1 in the subscript represents the maximum recoil displacement ( Xmax), 2 represents the maximum recoil speed (Vmax), 3 represents the maximum return speed (Umax), and 4 represents the return speed (Uend).

故障特征信号为最大后坐位移(Xmax)时，待检样本与不同故障模式的高斯模型交点纵坐标求解公式为：When the fault characteristic signal is the maximum recoil displacement (Xmax), the ordinate solution formula of the intersection of the sample to be tested and the Gaussian model of different fault modes is:

Figure BDA0003685211890000059
Figure BDA0003685211890000059

Figure BDA00036852118900000510
Figure BDA00036852118900000510

Figure BDA00036852118900000511
Figure BDA00036852118900000511

故障特征信号为最大后坐速度(Vmax)时，待检样本与不同故障模式的高斯模型交点纵坐标为：

Figure BDA0003685211890000061
When the fault characteristic signal is the maximum recoil velocity (Vmax), the ordinate of the intersection of the sample to be tested and the Gaussian models of different fault modes is:
Figure BDA0003685211890000061

Figure BDA0003685211890000062
Figure BDA0003685211890000062

Figure BDA0003685211890000063
Figure BDA0003685211890000063

Figure BDA0003685211890000064
Figure BDA0003685211890000064

故障特征信号为最大复进速度(Umax)时，待检样本与不同故障模式的高斯模型交点纵坐标为：

Figure BDA0003685211890000065
When the fault characteristic signal is the maximum recovery speed (Umax), the ordinate of the intersection of the sample to be tested and the Gaussian models of different fault modes is:
Figure BDA0003685211890000065

Figure BDA0003685211890000066
Figure BDA0003685211890000066

Figure BDA0003685211890000067
Figure BDA0003685211890000067

Figure BDA0003685211890000068
Figure BDA0003685211890000068

故障特征信号为复进到位速度(Uend)时，待检样本与不同故障模式的高斯模型交点纵坐标为：

Figure BDA0003685211890000069
When the fault characteristic signal is the return position speed (Uend), the ordinate of the intersection of the sample to be tested and the Gaussian model of different fault modes is:
Figure BDA0003685211890000069

Figure BDA00036852118900000610
Figure BDA00036852118900000610

Figure BDA00036852118900000611
Figure BDA00036852118900000611

Figure BDA00036852118900000612
Figure BDA00036852118900000612

步骤4.2：表示四种故障特征信号所对应证据的基本概率分配。Step 4.2: Represent the basic probability distribution of the evidence corresponding to the four fault characteristic signals.

每个待检样本中含有四种故障特征信号(Xmax、Vmax、Umax和Uend)，每种故障特征信号对应一组证据，则每种故障特征信号(Xmax、Vmax、Umax和Uend)所对应证据的基本概率分配函数可表示为mi(i＝1,2,3,4)；在步骤一中火炮反后坐装置故障模式有X,Y,Z三种，则一组证据的基本概率分配包含有mi(X)、mi(Y)和mi(Z)，其中mi(X)表示在证据mi下待检样本属于故障模式X的基本概率分配，mi(Y)表示在证据mi下待检样本属于故障模式Y的基本概率分配，mi(Z)表示在证据mi下待检样本属于故障模式Z的基本概率分配。Each sample to be inspected contains four fault characteristic signals (Xmax, Vmax, Umax and Uend), each fault characteristic signal corresponds to a set of evidence, then the evidence corresponding to each fault characteristic signal (Xmax, Vmax, Umax and Uend) The basic probability distribution function of can be expressed as m i (i=1, 2, 3, 4); in step 1, there are three failure modes of the anti-recoil device of the artillery, X, Y, and Z, then the basic probability distribution of a set of evidence includes There are m i (X), m i (Y) and m i (Z), where m i (X) represents the basic probability distribution that the sample to be tested belongs to the failure mode X under the evidence m i , and m i (Y) represents the The basic probability distribution of the sample to be inspected under the evidence m i belongs to the failure mode Y, and m i (Z) represents the basic probability distribution of the sample to be inspected under the evidence m i to belong to the failure mode Z.

步骤4.3：根据步骤4.1，获取得到待检样本与每种故障信号下不同故障模式高斯模型的交点纵坐标，分别求解待检样本的每种故障特性信号所对应证据的基本概率分配。Step 4.3: According to Step 4.1, obtain the ordinate of the intersection of the sample to be tested and the Gaussian model of different failure modes under each fault signal, and solve the basic probability distribution of the evidence corresponding to each fault characteristic signal of the sample to be tested.

故障特征信号为最大后坐位移(Xmax)时所对应证据m1的基本概率分配函数求解公式为：When the fault characteristic signal is the maximum recoil displacement (Xmax), the basic probability distribution function solution formula of the corresponding evidence m 1 is:

Figure BDA0003685211890000071
Figure BDA0003685211890000071

Figure BDA0003685211890000072
Figure BDA0003685211890000072

Figure BDA0003685211890000073
Figure BDA0003685211890000073

故障特征信号为最大后坐速度(Vmax)时对应证据m2的基本概率分配函数为：m2(X)，m2(Y)，m2(Z)；When the fault characteristic signal is the maximum recoil velocity (Vmax), the basic probability distribution function corresponding to the evidence m 2 is: m 2 (X), m 2 (Y), m 2 (Z);

Figure BDA0003685211890000074
Figure BDA0003685211890000074

Figure BDA0003685211890000075
Figure BDA0003685211890000075

Figure BDA0003685211890000076
Figure BDA0003685211890000076

故障特征信号为最大复进速度(Umax)时对应证据m3的基本概率分配函数为：m3(X)，m3(Y)，m3(Z)；When the fault characteristic signal is the maximum recovery speed (Umax), the basic probability distribution function corresponding to the evidence m 3 is: m 3 (X), m 3 (Y), m 3 (Z);

Figure BDA0003685211890000077
Figure BDA0003685211890000077

Figure BDA0003685211890000078
Figure BDA0003685211890000078

Figure BDA0003685211890000079
Figure BDA0003685211890000079

故障特征信号为复进到位速度(Uend)时对应证据m4的基本概率分配函数为：m4(X)，m4(Y)，m4(Z)。The basic probability distribution function of corresponding evidence m 4 is: m 4 (X), m 4 (Y), m 4 (Z).

Figure BDA00036852118900000710
Figure BDA00036852118900000710

Figure BDA00036852118900000711
Figure BDA00036852118900000711

Figure BDA0003685211890000081
Figure BDA0003685211890000081

步骤五：根据步骤四求解得到的火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配，在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的冲突因子，并根据求解的所有冲突因子，构造冲突因子矩阵；在火炮反后坐装置故障模式框架下，定义并求解各个证据间的RMSD距离；以所述冲突因子和所述归一化RMSD距离的几何均值作为RMSD冲突系数的取值，构造RMSD冲突系数；根据构造RMSD冲突系数，求解并构造RMSD相似系数，通过构造的RMSD相似系数便于定义后续步骤六的可靠度。Step 5: According to the basic probability distribution of the evidence corresponding to the fault characteristic signal of the artillery anti-recoil device to be inspected obtained in step 4, define and solve the conflict factors between the various evidences under the framework of the failure mode of the artillery anti-recoil device. All conflict factors solved, construct conflict factor matrix; under the framework of artillery anti-recoil device failure mode, define and solve the RMSD distance between each evidence; take the geometric mean of the conflict factor and the normalized RMSD distance as the RMSD conflict According to the value of the coefficient, the RMSD conflict coefficient is constructed; according to the constructed RMSD conflict coefficient, the RMSD similarity coefficient is solved and constructed, and the reliability of the subsequent step 6 is easily defined by the constructed RMSD similarity coefficient.

步骤5.1：在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的冲突因子，并根据求解的所有冲突因子，构造冲突因子矩阵。所述各个证据之间的冲突因子即每两组证据之间的冲突因子。Step 5.1: Under the framework of the failure mode of the artillery anti-recoil device, define and solve the conflict factors between the various evidences, and construct a conflict factor matrix according to all the solved conflict factors. The conflict factor between the various evidences is the conflict factor between each two groups of evidences.

为方便给出求解冲突因子的公式，在火炮故障模式框架Θ＝{X,Y,Z}下，定义m1和m2为两组证据，对应的故障模式分别表示为F′(F′＝X,Y,Z)和F″(F″＝X,Y,Z)，则证据m1和m2的冲突因子如式(40)所示：In order to give the formula for solving the conflict factor conveniently, under the artillery failure mode framework Θ={X, Y, Z}, m 1 and m 2 are defined as two groups of evidences, and the corresponding failure modes are respectively expressed as F′(F′= X, Y, Z) and F″ (F″=X, Y, Z), then the conflict factor of evidence m 1 and m 2 is shown in formula (40):

Figure BDA0003685211890000082
Figure BDA0003685211890000082

根据公式(40)得各证据间的冲突因子矩阵为：According to formula (40), the conflict factor matrix between each evidence is:

Figure BDA0003685211890000083
Figure BDA0003685211890000083

不过冲突因子存在缺陷，根据公式(40)可知两个证据相同时求解得到的冲突因子不为0，因此需通过后续步骤5.2引入证据间的RMSD距离来修正冲突因子，在后续步骤5.3中构造冲突系数，即RMSD冲突系数。However, there is a flaw in the conflict factor. According to formula (40), it can be seen that the conflict factor obtained when the two evidences are the same is not 0. Therefore, the conflict factor needs to be corrected by introducing the RMSD distance between the evidences in the subsequent step 5.2, and the conflict is constructed in the subsequent step 5.3. coefficient, that is, the RMSD conflict coefficient.

步骤5.2：在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的RMSD距离，并根据求解的所有RMSD距离，构造RMSD距离矩阵，求解归一化后的RMSD距离矩阵。Step 5.2: Under the framework of the failure mode of the artillery anti-recoil device, define and solve the RMSD distance between each evidence, and construct the RMSD distance matrix according to all the solved RMSD distances, and solve the normalized RMSD distance matrix.

定义m1和m2为两组证据，对应的故障模式分别表示为F′(F′＝X,Y,Z)和F″(F″＝X,Y,Z)，则定义证据m1和m2间的均方根偏移(Root Mean Square Deviation,RMSD)距离为：Define m 1 and m 2 as two groups of evidences, and the corresponding failure modes are expressed as F′(F′=X,Y,Z) and F″(F″ = X,Y,Z), then define evidences m1 and The Root Mean Square Deviation (RMSD) distance between m 2 is:

Figure BDA0003685211890000084
Figure BDA0003685211890000084

根据公式(42)求解得到各证据间的RMSD距离矩阵，如式(43)所示：According to formula (42), the RMSD distance matrix between each evidence is obtained, as shown in formula (43):

Figure BDA0003685211890000091
Figure BDA0003685211890000091

然后寻找RMSD距离矩阵中的最大值RMSDmax＝max{RMSD}，接下来对RMSD距离矩阵进行归一化处理，即RMSD距离矩阵的每个元素除以RMSDmax，得到归一化之后的RMSD距离矩阵，如式(44)所示：Then find the maximum value in the RMSD distance matrix, RMSD max =max{RMSD}, and then normalize the RMSD distance matrix, that is, divide each element of the RMSD distance matrix by RMSD max to get the normalized RMSD distance matrix, as shown in equation (44):

Figure BDA0003685211890000092
Figure BDA0003685211890000092

步骤5.3：定义以步骤5.1所述冲突因子和步骤5.2中所述归一化RMSD距离的几何均值作为RMSD冲突系数的取值，构造RMSD冲突系数。Step 5.3: Define the geometric mean of the conflict factor described in Step 5.1 and the normalized RMSD distance described in Step 5.2 as the value of the RMSD conflict coefficient to construct the RMSD conflict coefficient.

以步骤5.1得到的冲突因子和步骤5.2得到的归一化RMSD距离的几何均值作为RMSD冲突系数的取值，定义证据m1和m2的RMSD冲突系数表示为：Taking the conflict factor obtained in step 5.1 and the geometric mean of the normalized RMSD distance obtained in step 5.2 as the value of the RMSD conflict coefficient, the RMSD conflict coefficients of the defined evidences m 1 and m 2 are expressed as:

Figure BDA0003685211890000093
Figure BDA0003685211890000093

式(45)中，K(m1,m2)代表证据m1和m2的冲突因子，RMSD(m1,m2)代表证据m1和m2归一化后的RMSD距离；In formula (45), K(m 1 , m 2 ) represents the conflict factor of evidence m 1 and m 2 , and RMSD(m 1 , m 2 ) represents the normalized RMSD distance of evidence m 1 and m 2 ;

根据公式(45)得RMSD冲突系数矩阵为：According to formula (45), the RMSD conflict coefficient matrix is:

Figure BDA0003685211890000094
Figure BDA0003685211890000094

步骤5.4：以步骤5.3中所述的RMSD冲突系数为基础，求解并构造RMSD相似系数。Step 5.4: Based on the RMSD conflict coefficients described in step 5.3, solve and construct the RMSD similarity coefficients.

步骤5.3中构造的RMSD冲突系数代表证据间的冲突程度，取值范围为[0,1]，则用1减去RMSD冲突系数则可以代表证据间的相似程度，定义证据m1和m2的RMSD相似系数表示为： The RMSD conflict coefficient constructed in step 5.3 represents the degree of conflict between the evidences. The RMSD similarity coefficient is expressed as:

SimRMSD(m1,m2)＝1-ConRMSD(m1,m2) (47)Sim RMSD (m 1 ,m 2 )=1-Con RMSD (m 1 ,m 2 ) (47)

根据公式(47)可得RMSD相似系数矩阵为：According to formula (47), the RMSD similarity coefficient matrix can be obtained as:

Figure BDA0003685211890000101
Figure BDA0003685211890000101

步骤六：定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，并根据所述定义确定每个证据的可靠度；分析每个证据的可靠度，定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，并求解每个证据的权重；根据每个证据可靠度对所有证据进行权重分配，降低信息之间的冲突性，然后通过加权平均后得到整合证据，便于后续步骤七的融合，提高故障诊断正确率。Step 6: Define the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidence, and determine the reliability of each evidence according to the definition; analyze the reliability of each evidence, and define the weight of each evidence It is the ratio of the reliability of the evidence to the sum of the reliability of all the evidence, and solves the weight of each evidence; according to the reliability of each evidence, weights are assigned to all evidences to reduce the conflict between information, and then through the weighted average The integrated evidence is obtained, which facilitates the fusion of the subsequent step 7 and improves the correct rate of fault diagnosis.

步骤6.1：定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，并根据所述定义确定每个证据的可靠度。Step 6.1: Define the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidences, and determine the reliability of each evidence according to the definition.

定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，则证据m1的可靠度用公式表示为：The reliability of each evidence is defined as the sum of the RMSD similarity coefficients of the evidence and other evidence, then the reliability of evidence m 1 is expressed as:

Rel(m1)＝SimRMSD(m1,m2)+SimRMSD(m1,m3)+SimRMSD(m1,m4) (49)Rel(m 1 )=Sim RMSD (m 1 ,m 2 )+Sim RMSD (m 1 ,m 3 )+Sim RMSD (m 1 ,m 4 ) (49)

证据m2的可靠度用公式表示为： The reliability of evidence m2 is expressed by the formula:

Rel(m2)＝SimRMSD(m2,m1)+SimRMSD(m2,m3)+SimRMSD(m2,m4) (50)Rel(m 2 )=Sim RMSD (m 2 ,m 1 )+Sim RMSD (m 2 ,m 3 )+Sim RMSD (m 2 ,m 4 ) (50)

证据m3的可靠度用公式表示为：The reliability of evidence m3 is expressed by the formula:

Rel(m3)＝SimRMSD(m3,m1)+SimRMSD(m3,m2)+SimRMSD(m3,m4) (51)Rel(m 3 )=Sim RMSD (m 3 ,m 1 )+Sim RMSD (m 3 ,m 2 )+Sim RMSD (m 3 ,m 4 ) (51)

证据m4的可靠度用公式表示为：The reliability of evidence m 4 is expressed by the formula:

Rel(m4)＝SimRMSD(m4,m1)+SimRMSD(m4,m2)+SimRMSD(m4,m3) (52)Rel(m 4 )=Sim RMSD (m 4 ,m 1 )+Sim RMSD (m 4 ,m 2 )+Sim RMSD (m 4 ,m 3 ) (52)

其中，证据的可靠度代表其他证据对该证据的支持程度；Among them, the reliability of evidence represents the degree of support for the evidence by other evidence;

证据的可靠度越大，表明该证据在融合决策过程中的重要性高，后续步骤6.2分配的权重宜大；The greater the reliability of the evidence, the higher the importance of the evidence in the fusion decision-making process, and the weight assigned in the subsequent step 6.2 should be larger;

证据的可靠度越小，表明该证据在融合决策过程中的重要性低，后续步骤6.2分配的权重宜小。The smaller the reliability of the evidence, the lower the importance of the evidence in the fusion decision-making process, and the weight assigned in the subsequent step 6.2 should be small.

步骤6.2：分析步骤6.1确定的每个证据的可靠度，定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，并求解每个证据的权重。Step 6.2: Analyze the reliability of each evidence determined in Step 6.1, define the weight of each evidence as the ratio of the reliability of the evidence to the sum of the reliability of all evidence, and solve the weight of each evidence.

定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，则证据m1的权重表示为：The weight of each evidence is defined as the ratio of the reliability of the evidence to the sum of the reliability of all evidences, then the weight of evidence m 1 is expressed as:

Figure BDA0003685211890000102
Figure BDA0003685211890000102

证据m2的可靠度用公式表示为： The reliability of evidence m2 is expressed by the formula:

Figure BDA0003685211890000103
Figure BDA0003685211890000103

证据m3的可靠度用公式表示为：The reliability of evidence m3 is expressed by the formula:

Figure BDA0003685211890000111
Figure BDA0003685211890000111

证据m4的可靠度用公式表示为：The reliability of evidence m 4 is expressed by the formula:

Figure BDA0003685211890000112
Figure BDA0003685211890000112

步骤6.3：根据步骤6.2中每个证据可靠度对所有证据进行权重分配，降低信息之间的冲突性，然后通过加权平均后得到整合证据，便于后续步骤七的融合，提高故障诊断正确率。Step 6.3: All the evidences are weighted according to the reliability of each evidence in Step 6.2 to reduce the conflict between the information, and then the integrated evidence is obtained through the weighted average, which is convenient for the fusion of the subsequent step 7 and improves the correct rate of fault diagnosis.

根据步骤6.2中分配的权重，通过加权平均后得到整合证据，表示为：According to the weights assigned in step 6.2, the integrated evidence is obtained after weighted averaging, which is expressed as:

Figure BDA0003685211890000113
Figure BDA0003685211890000113

进一步地，得到在整合证据下故障模式分别为X、Y和Z时的基本概率分配，表示为：Further, the basic probability distribution when the failure modes are X, Y and Z respectively under the integrated evidence is obtained, which is expressed as:

Figure BDA0003685211890000114
Figure BDA0003685211890000114

Figure BDA0003685211890000115
Figure BDA0003685211890000115

Figure BDA0003685211890000116
Figure BDA0003685211890000116

步骤七：在火炮故障模式框架，利用Dempster-Shafer(DS)证据理论方法对步骤六得到的整合证据进行自身融合，得到对应火炮反后坐装置故障模式的发生概率；遍历所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，即基于RMSD-DS实现对火炮反后坐装置故障的高精度效率诊断。Step 7: In the artillery failure mode framework, use the Dempster-Shafer (DS) evidence theory method to fuse the integrated evidence obtained in step 6 to obtain the probability of occurrence of the corresponding artillery anti-recoil device failure mode; traverse all artillery anti-recoil device failure modes The probability of occurrence is determined, and the failure mode corresponding to the maximum basic probability distribution value is the failure mode of the final diagnosis, that is, the high-precision and efficient diagnosis of the failure of the artillery anti-recoil device based on RMSD-DS is realized.

步骤7.1：定义m1和m2为两组证据，对应的故障模式分别表示为F′(F′＝X,Y,Z)和F″(F″＝X,Y,Z)，给出证据m1和m2的DS融合规则。Step 7.1: Define m 1 and m 2 as two groups of evidences, and the corresponding failure modes are expressed as F′(F′=X,Y,Z) and F″(F″=X,Y,Z), respectively, and give evidences DS fusion rules for m 1 and m 2 .

为方便给出DS融合规则，在火炮故障模式框架Θ＝{X,Y,Z}下，m1和m2为两组证据，对应的故障模式分别表示为F′(F′＝X,Y,Z)和F″(F″＝X,Y,Z)，则证据m1和m2的DS融合规则如式(61)所示：In order to give the DS fusion rules conveniently, under the artillery failure mode framework Θ={X, Y, Z}, m 1 and m 2 are two groups of evidences, and the corresponding failure modes are respectively expressed as F′(F′=X,Y , Z) and F″ (F″=X, Y, Z), then the DS fusion rule of evidence m 1 and m 2 is shown in formula (61):

Figure BDA0003685211890000117
Figure BDA0003685211890000117

步骤7.2：根据步骤7.1中所给出的DS融合规则，将整合证据自身融合3次，利用DS融合规则对整合证据进行融合，得到对应火炮反后坐装置故障模式的发生概率。Step 7.2: According to the DS fusion rule given in Step 7.1, fuse the integrated evidence itself three times, and use the DS fusion rule to fuse the integrated evidence to obtain the probability of occurrence of the corresponding artillery anti-recoil device failure mode.

步骤7.3：根据步骤7.2遍历得到所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，即基于RMSD-DS方法实现对火炮反后坐装置故障的高精度效率诊断。Step 7.3: According to step 7.2, the probability of occurrence of all artillery anti-recoil device failure modes is obtained by traversing, and the failure mode corresponding to the maximum basic probability distribution value is determined as the final diagnosis failure mode, that is, based on the RMSD-DS method, the artillery anti-recoil device is realized Highly accurate and efficient diagnosis of failures.

有益效果：Beneficial effects:

1、相比于神经网络等传统融合方法，本发明公开的基于RMSD-DS的火炮反后坐装置故障诊断方法，在火炮反后坐装置故障模式框架下，通过构造RMSD相似系数和求解每个证据的可靠度定量描述每个证据的重要程度，根据每个证据的可靠度对所有证据进行权重分配，降低冲突信息所带来的影响，通过加权平均后得到整合证据，利用DS方法整合证据进行融合，得到对应火炮反后坐装置故障模式的发生概率；遍历所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，提高对火炮反后坐装置故障诊断精度。1. Compared with traditional fusion methods such as neural networks, the RMSD-DS-based artillery anti-recoil device fault diagnosis method disclosed in the present invention, under the framework of the artillery anti-recoil device failure mode, by constructing the RMSD similarity coefficient and solving the equation of each evidence. Reliability quantitatively describes the importance of each piece of evidence. According to the reliability of each piece of evidence, all evidence is weighted to reduce the impact of conflicting information. The integrated evidence is obtained after weighted averaging, and the DS method is used to integrate evidence for fusion. Obtain the occurrence probability of the corresponding artillery anti-recoil device failure mode; traverse the occurrence probability of all artillery anti-recoil device failure modes, determine the failure mode corresponding to the maximum basic probability distribution value is the final diagnosis failure mode, improve the anti-recoil device failure mode of the artillery Diagnostic accuracy.

2、本发明公开的基于RMSD-DS的火炮反后坐装置故障诊断方法，通过分析火炮反后坐装置的故障历史数据，建立火炮反后坐装置故障模式的高斯模型，通过所述火炮反后坐装置故障模式的高斯模型求解火炮反后坐装置故障特征信号所对应证据的基本概率分配，提高火炮反后坐装置故障诊断效率。2. The RMSD-DS-based fault diagnosis method of the artillery anti-recoil device disclosed by the present invention, through analyzing the fault history data of the artillery anti-recoil device, a Gaussian model of the failure mode of the artillery anti-recoil device is established, and through the artillery anti-recoil device failure mode The Gaussian model is used to solve the basic probability distribution of the evidence corresponding to the fault characteristic signal of the artillery anti-recoil device, so as to improve the fault diagnosis efficiency of the artillery anti-recoil device.

3、本发明公开的基于RMSD-DS的火炮反后坐装置故障诊断方法，在实现有益效果1、2的基础上，基于RMSD-DS的火炮反后坐装置故障诊断方法实现对火炮反后坐装置故障的高精度效率诊断。3. The RMSD-DS-based artillery anti-recoil device fault diagnosis method disclosed in the present invention, on the basis of realizing the beneficial effects 1 and 2, the RMSD-DS-based artillery anti-recoil device fault diagnosis method realizes the fault diagnosis of the artillery anti-recoil device fault. High-precision efficiency diagnostics.

附图说明Description of drawings

图1是本发明的基于RMSD-DS的火炮反后坐装置故障诊断方法流程图。Fig. 1 is the flow chart of the fault diagnosis method of the artillery anti-recoil device based on RMSD-DS of the present invention.

图2是不同故障特性信号下各种模式的高斯模型，其中：图2(a)为故障特性信号为Xmax时各种故障模式的高斯模型，图2(b)为故障特性信号为Vmax时各种故障模式的高斯模型，图2(c)为故障特性信号为Umax时各种故障模式的高斯模型，图2(d)为故障特性信号为Uend时各种故障模式的高斯模型。Figure 2 is the Gaussian model of various modes under different fault characteristic signals, in which: Figure 2(a) is the Gaussian model of various failure modes when the fault characteristic signal is Xmax, and Figure 2(b) is when the fault characteristic signal is Vmax. Figure 2(c) shows the Gaussian models of various failure modes when the fault characteristic signal is Umax, and Figure 2(d) shows the Gaussian models of various failure modes when the fault characteristic signal is Uend.

图3求解两个证据间RMSD相似系数的流程图。Figure 3 is a flow chart for solving the RMSD similarity coefficient between two evidences.

具体实施方式Detailed ways

为了更好的说明本发明的目的和优点，下面结合附图和实例对发明内容做进一步说明，并于传统的神经网络融合方法和DS证据理论方法进行比较。In order to better illustrate the purpose and advantages of the present invention, the content of the invention is further described below with reference to the accompanying drawings and examples, and a comparison is made between the traditional neural network fusion method and the DS evidence theory method.

如图1所示；本实施例公开的基于RMSD-DS的火炮反后坐装置故障诊断方法，具体实现步骤如下：As shown in Figure 1; the disclosed method for diagnosing faults of artillery anti-recoil devices based on RMSD-DS in the present embodiment, the specific implementation steps are as follows:

步骤一：确定火炮反后坐装置典型故障模式及故障特征信号。Step 1: Determine the typical failure mode and failure characteristic signal of the artillery anti-recoil device.

确定火炮反后坐装置的典型故障模式总共三种，分别为节制环磨损X、复进机漏气Y和制退杆活塞磨损Z，则火炮反后坐装置的故障模式框架表示为Θ＝{X,Y,Z}；确定火炮反后坐装置的故障特性信号分别为：最大后坐位移Xmax、最大后坐速度Vmax、最大复进速度Umax和复进到位速度Uend。Three typical failure modes of the anti-recoil device of the artillery are determined in total, namely, the wear of the control ring X, the leakage of the air Y of the recuperator and the wear of the piston of the brake rod Z, then the failure mode framework of the anti-recoil device of the artillery is expressed as Θ={X, Y, Z}; The fault characteristic signals to determine the anti-recoil device of the artillery are respectively: the maximum recoil displacement Xmax, the maximum recoil speed Vmax, the maximum return speed Umax and the return speed Uend.

步骤二：采集、获取火炮反后坐装置在典型故障模式下对应的故障特征信号。Step 2: Collect and obtain the fault characteristic signal corresponding to the artillery anti-recoil device under the typical fault mode.

火炮工作时，由安装在反后坐装置上的传感器采集反后坐装置在每种故障模式下的四种故障特征信号，所获取的数据用Fi表示，其中F＝X,Y,Z，分别代表节制环磨损，复进机漏气和制退杆活塞磨损三种故障模式；i＝1,2,3,4，分别代表最大后坐位移Xmax，最大后坐速度Vmax，最大复进速度Umax和复进到位速度Uend四种故障特征信号；采集到的一组样本数据表示为(F1,F2,F3,F4)，即F1代表故障模式F所对应的最大后坐位移Xmax信号数据，F2代表故障模式F所对应的最大后坐速度Vmax信号数据，F3代表故障模式F所对应的最大复进速度Umax信号数据，F4代表故障模式F所对应的复进到位速度Uend信号数据。When the artillery works, the sensor installed on the anti-recoil device collects four fault characteristic signals of the anti-recoil device in each failure mode. The acquired data is represented by F i , where F=X, Y, Z, representing There are three failure modes: the wear of the control ring, the air leakage of the recoil machine and the wear of the brake rod piston; i=1, 2, 3, 4, representing the maximum recoil displacement Xmax, the maximum recoil speed Vmax, the maximum recoil speed Umax and the recoil speed respectively. In-position speed Uend four fault characteristic signals; a set of sample data collected is expressed as (F 1 , F 2 , F 3 , F 4 ), that is, F 1 represents the maximum recoil displacement Xmax signal data corresponding to failure mode F, F 2 represents the signal data of the maximum recoil speed Vmax corresponding to the failure mode F, F 3 represents the signal data of the maximum return speed Umax corresponding to the failure mode F, and F 4 represents the signal data of the return in-position speed Uend corresponding to the failure mode F.

每种故障模式下，各获取100组故障数据，总计300组数据。In each failure mode, 100 sets of failure data are obtained, for a total of 300 sets of data.

步骤三：分析步骤二获取的在典型故障模式下对应的故障特征信号，并将所述故障特征信号分类为故障训练样本数据、故障待检样本数据；求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差，然后构造属于不同故障模式的训练样本在不同故障信号上的高斯模型。Step 3: Analyze the corresponding fault characteristic signals in the typical fault mode obtained in step 2, and classify the fault characteristic signals into fault training sample data and fault unchecked sample data; solve the training belonging to different fault modes of the artillery anti-recoil device The mean and standard deviation of the samples on different fault characteristic signals, and then construct the Gaussian model of the training samples belonging to different fault modes on different fault signals.

步骤3.1：将步骤二获取的在典型故障模式下对应的故障特征信号，分类为故障训练样本数据、故障待检样本数据。Step 3.1: Classify the corresponding fault characteristic signals in the typical fault mode obtained in step 2 into fault training sample data and fault unchecked sample data.

基于步骤二获取的在典型故障模式下对应的故障特征信号，分别从各个故障模式中所对应的四种故障特性信号数据中选取80％的样本数据作为故障训练样本，剩余20％样本数据作为故障待检样本。Based on the corresponding fault characteristic signals in the typical fault mode obtained in step 2, 80% of the sample data are selected from the four fault characteristic signal data corresponding to each fault mode as the fault training sample, and the remaining 20% of the sample data is used as the fault Sample to be tested.

为了验证方法的有效性，通过调换故障模式Y与故障模式Z下所对应的最大后坐位移数据来模拟火炮反后坐装置传感器发生损坏；此过程的目的是让传感器输出的信息之间相互冲突。In order to verify the effectiveness of the method, the damage to the sensor of the artillery anti-recoil device is simulated by exchanging the maximum recoil displacement data corresponding to the failure mode Y and the failure mode Z; the purpose of this process is to make the information output by the sensors conflict with each other.

步骤3.2：对于步骤3.1选定的故障训练样本，求解属于火炮反后坐装置不同故障模式的训练样本在不同故障特征信号上的平均值和标准差。Step 3.2: For the fault training samples selected in Step 3.1, calculate the mean and standard deviation of the training samples belonging to different fault modes of the artillery anti-recoil device on different fault characteristic signals.

求解得到的结果如表1所示。The obtained results are shown in Table 1.

表1训练样本(不同故障模式)的均值和标准差Table 1 Mean and standard deviation of training samples (different failure modes)

Figure BDA0003685211890000131
Figure BDA0003685211890000131

步骤3.3：根据步骤3.2求解得到的平均值和标准差，构造属于不同故障模式的训练样本在不同故障信号上的高斯模型。Step 3.3: Construct Gaussian models of training samples belonging to different failure modes on different failure signals according to the mean value and standard deviation obtained in step 3.2.

故障特性信号为最大后坐位移(Xmax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：When the fault characteristic signal is the maximum recoil displacement (Xmax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model is:

Figure BDA0003685211890000141
Figure BDA0003685211890000141

Figure BDA0003685211890000142
Figure BDA0003685211890000142

Figure BDA0003685211890000143
Figure BDA0003685211890000143

故障特性信号为最大后坐速度(Vmax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA0003685211890000144
和
Figure BDA0003685211890000145
When the fault characteristic signal is the maximum recoil speed (Vmax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model is:
Figure BDA0003685211890000144
and
Figure BDA0003685211890000145

Figure BDA0003685211890000146
Figure BDA0003685211890000146

Figure BDA0003685211890000147
Figure BDA0003685211890000147

Figure BDA0003685211890000148
Figure BDA0003685211890000148

故障特性信号为最大复进速度(Umax)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA0003685211890000149
和
Figure BDA00036852118900001410
When the fault characteristic signal is the maximum return speed (Umax), the fault mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model on the wear (Z) is:
Figure BDA0003685211890000149
and
Figure BDA00036852118900001410

Figure BDA00036852118900001411
Figure BDA00036852118900001411

Figure BDA00036852118900001412
Figure BDA00036852118900001412

Figure BDA00036852118900001413
Figure BDA00036852118900001413

故障特性信号为复进到位速度(Uend)时，故障模式为节制环磨损(X)、复进机漏气(Y)和制退杆活塞磨损(Z)上的高斯模型为：

Figure BDA00036852118900001414
和
Figure BDA00036852118900001415
When the fault characteristic signal is the reversing in-position speed (Uend), the failure mode is the control ring wear (X), the reversing machine leakage (Y) and the brake rod piston wear (Z) The Gaussian model on the wear (Z) is:
Figure BDA00036852118900001414
and
Figure BDA00036852118900001415

Figure BDA00036852118900001416
Figure BDA00036852118900001416

Figure BDA00036852118900001417
Figure BDA00036852118900001417

Figure BDA0003685211890000151
Figure BDA0003685211890000151

求解上述的高斯模型后，在每种故障特性信号下，绘制各种故障模式的高斯模型，如附图2所示。After solving the above-mentioned Gaussian model, under each fault characteristic signal, draw the Gaussian model of various failure modes, as shown in FIG. 2 .

步骤四：根据步骤三构建的火炮反后坐装置故障模式高斯模型，求解火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配。Step 4: According to the Gaussian model of the failure mode of the artillery anti-recoil device constructed in step 3, the basic probability distribution of the evidence corresponding to the fault characteristic signal of the sample to be inspected for the artillery anti-recoil device is solved.

每种故障模式下，待检样本各有20组，由于文本篇幅限制，从每种故障模式中只给出一组待检样本数据的每种故障特性信号相对应证据的基本概率分配，如表2-表4所示。In each failure mode, there are 20 groups of samples to be inspected. Due to the limitation of text space, only the basic probability distribution of the evidence corresponding to each failure characteristic signal of one group of sample data to be inspected is given from each failure mode, as shown in the table. 2 - shown in Table 4.

表2实际故障为X时，每种故障特性信号相对应证据的基本概率分配值Table 2 When the actual fault is X, the basic probability distribution value of each fault characteristic signal corresponding to the evidence

Figure BDA0003685211890000152
Figure BDA0003685211890000152

对于该组待检样本，从表2中可知，实际故障为X时，证据m1、m2和m3支持故障模式X发生，证据m4支持故障模式Y发生，证据之间存在冲突情况。For this group of samples to be tested, it can be seen from Table 2 that when the actual fault is X, evidences m 1 , m 2 and m 3 support the occurrence of failure mode X, and evidence m 4 supports the occurrence of failure mode Y, and there is a conflict between the evidences.

表3实际故障为Y时，每种故障特性信号相对应证据的基本概率分配值Table 3 When the actual fault is Y, the basic probability distribution value of each fault characteristic signal corresponding to the evidence

Figure BDA0003685211890000153
Figure BDA0003685211890000153

对于该组待检样本，从表3中可知，实际故障为Y时，证据m2、m3和m4支持故障模式Y发生，证据m1支持故障模式Z发生，证据之间存在冲突情况。For this group of samples to be tested, it can be seen from Table 3 that when the actual fault is Y, evidences m 2 , m 3 and m 4 support the occurrence of failure mode Y, and evidence m 1 supports the occurrence of failure mode Z, and there is a conflict between the evidences.

表4实际故障为Z时，每种故障特性信号相对应证据的基本概率分配值Table 4 When the actual fault is Z, the basic probability distribution value of each fault characteristic signal corresponding to the evidence

Figure BDA0003685211890000154
Figure BDA0003685211890000154

对于该组待检样本，从表4中可知，实际故障为Z时，证据m1支持故障模式X发生，证据m2、m3和m4支持故障模式Z发生，证据之间存在冲突情况。For this group of samples to be tested, it can be seen from Table 4 that when the actual fault is Z, evidence m 1 supports the occurrence of failure mode X, and evidences m 2 , m 3 and m 4 support the occurrence of failure mode Z, and there is a conflict between the evidences.

步骤五：根据步骤四求解得到的火炮反后坐装置待检样本故障特征信号所对应证据的基本概率分配，在火炮反后坐装置故障模式框架下，定义并求解各个证据之间的冲突因子，并根据求解的所有冲突因子，构造冲突因子矩阵；在火炮反后坐装置故障模式框架下，定义并求解各个证据间的RMSD距离；以所述冲突因子和所述归一化RMSD距离的几何均值作为RMSD冲突系数的取值，构造RMSD冲突系数；根据构造RMSD冲突系数，求解并构造RMSD相似系数，通过构造的RMSD相似系数便于定义后续步骤六的可靠度。Step 5: According to the basic probability distribution of the evidence corresponding to the fault characteristic signal of the artillery anti-recoil device to be inspected obtained in step 4, define and solve the conflict factors between the various evidences under the framework of the failure mode of the artillery anti-recoil device. All conflict factors solved, construct conflict factor matrix; under the framework of artillery anti-recoil device failure mode, define and solve the RMSD distance between each evidence; take the geometric mean of the conflict factor and the normalized RMSD distance as the RMSD conflict According to the value of the coefficient, the RMSD conflict coefficient is constructed; according to the constructed RMSD conflict coefficient, the RMSD similarity coefficient is solved and constructed, and the reliability of the subsequent step 6 is easily defined by the constructed RMSD similarity coefficient.

求解两个证据间RMSD相似系数的流程图如附图3所示。The flowchart for solving the RMSD similarity coefficient between two evidences is shown in Figure 3.

基于步骤四所给出数据，求解得到的RMSD相似系数为，Based on the data given in step 4, the obtained RMSD similarity coefficient is,

实际故障为X时，其中一组待检样本数据的证据间的RMSD相似系数矩阵为：When the actual fault is X, the RMSD similarity coefficient matrix between the evidences of a set of sample data to be checked is:

Figure BDA0003685211890000161
Figure BDA0003685211890000161

实际故障为Y时，其中一组待检样本数据的证据间的RMSD相似系数矩阵为：When the actual fault is Y, the RMSD similarity coefficient matrix between the evidences of a set of sample data to be checked is:

Figure BDA0003685211890000162
Figure BDA0003685211890000162

实际故障为Z时，其中一组待检样本数据的证据间的RMSD相似系数矩阵为：When the actual fault is Z, the RMSD similarity coefficient matrix between the evidences of a set of sample data to be checked is:

Figure BDA0003685211890000163
Figure BDA0003685211890000163

步骤六：定义每个证据的可靠度为该证据与其他证据的RMSD相似系数之和，并根据所述定义确定每个证据的可靠度；分析每个证据的可靠度，定义每个证据的权重为该证据的可靠度与所有证据可靠度之和的比值，并求解每个证据的权重；根据每个证据可靠度对所有证据进行权重分配，降低信息之间的冲突性，然后通过加权平均后得到整合证据，便于后续步骤七的融合，提高故障诊断正确率。Step 6: Define the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidence, and determine the reliability of each evidence according to the definition; analyze the reliability of each evidence, and define the weight of each evidence It is the ratio of the reliability of the evidence to the sum of the reliability of all the evidence, and solves the weight of each evidence; according to the reliability of each evidence, weights are assigned to all evidences to reduce the conflict between information, and then through the weighted average The integrated evidence is obtained, which facilitates the fusion of the subsequent step 7 and improves the correct rate of fault diagnosis.

实际故障为X时，其中一组待检样本数据的整合证据为：When the actual fault is X, the integrated evidence of one set of sample data to be checked is:

Figure BDA0003685211890000164
Figure BDA0003685211890000164

实际故障为Y时，其中一组待检样本数据的整合证据为：When the actual fault is Y, the integrated evidence of one set of sample data to be checked is:

Figure BDA0003685211890000165
Figure BDA0003685211890000165

实际故障为Z时，其中一组待检样本数据的整合证据为：When the actual fault is Z, the integrated evidence of one set of sample data to be checked is:

Figure BDA0003685211890000166
Figure BDA0003685211890000166

步骤七：整合证据的DS融合与诊断结果的输出。Step 7: Integrate DS fusion of evidence and output of diagnostic results.

根据DS融合规则，将整合证据自身融合3次，得到最终的融合结果。According to the DS fusion rule, the integrated evidence itself is fused three times to obtain the final fusion result.

实际故障为X时，其中一组待检样本数据的最终融合结果为：When the actual fault is X, the final fusion result of one set of sample data to be checked is:

m(X)＝0.9999，m(Y)＝3.44e-05，m(Z)＝4.83e-05；m(X)=0.9999, m(Y)=3.44e-05, m(Z)=4.83e-05;

最终诊断模式为：X；诊断结果正确。The final diagnosis mode is: X; the diagnosis result is correct.

实际故障为Y时，其中一组待检样本数据的最终融合结果为：When the actual fault is Y, the final fusion result of one set of sample data to be checked is:

m(X)＝0.0081，m(Y)＝0.9886，m(Z)＝0.0033；m(X)=0.0081, m(Y)=0.9886, m(Z)=0.0033;

最终诊断模式为：Y；诊断结果正确。The final diagnosis mode is: Y; the diagnosis result is correct.

实际故障为Z时，其中一组待检样本数据的最终融合结果为：When the actual fault is Z, the final fusion result of one set of sample data to be checked is:

m(X)＝9.16e-04，m(Y)＝1.27e-05，m(Z)＝0.9991；m(X)=9.16e-04, m(Y)=1.27e-05, m(Z)=0.9991;

最终诊断模式为：Z；诊断结果正确。The final diagnosis mode is: Z; the diagnosis result is correct.

按照同样的方法，求解得到所有待检样本的诊断结果，如表5所示。According to the same method, the diagnostic results of all samples to be tested are obtained by solving, as shown in Table 5.

表5所有待检样本的诊断结果(本专利方法)Table 5 Diagnostic results of all samples to be tested (this patented method)

Figure BDA0003685211890000171
Figure BDA0003685211890000171

表5结果显示，本专利所提方法对故障模式X和Y的故障诊断正确率达到100％，对故障模式Z的诊断正确率达到95％，总计故障诊断正确率为98.3％，表明本专利方法有着突出的诊断效果，优越的诊断精度。The results in Table 5 show that the correct rate of fault diagnosis for fault modes X and Y of the method proposed in this patent reaches 100%, the correct rate of fault diagnosis for fault mode Z reaches 95%, and the total fault diagnosis correct rate is 98.3%, indicating that the patented method It has outstanding diagnostic effect and superior diagnostic accuracy.

步骤七：在火炮故障模式框架，利用Dempster-Shafer(DS)证据理论方法对步骤六得到的整合证据进行自身融合，得到对应火炮反后坐装置故障模式的发生概率；遍历所有火炮反后坐装置故障模式的发生概率，确定最大基本概率分配值所对应的故障模式即为最终诊断的故障模式，即基于RMSD-DS实现对火炮反后坐装置故障的高精度效率诊断。Step 7: In the artillery failure mode framework, use the Dempster-Shafer (DS) evidence theory method to fuse the integrated evidence obtained in step 6 to obtain the probability of occurrence of the corresponding artillery anti-recoil device failure mode; traverse all artillery anti-recoil device failure modes The probability of occurrence is determined, and the failure mode corresponding to the maximum basic probability distribution value is the failure mode of the final diagnosis, that is, the high-precision and efficient diagnosis of the failure of the artillery anti-recoil device based on RMSD-DS is realized.

为进一步凸显本专利方法的诊断效果，给出应用DS融合规则和BP神经网络方法得到的诊断结果，如表6-表7所示。In order to further highlight the diagnostic effect of the patented method, the diagnostic results obtained by applying the DS fusion rule and the BP neural network method are given, as shown in Table 6-Table 7.

表6所有待检样本的诊断结果(DS)Table 6 Diagnostic results (DS) of all samples to be tested

Figure BDA0003685211890000172
Figure BDA0003685211890000172

Figure BDA0003685211890000181
Figure BDA0003685211890000181

表6结果显示，DS方法对故障模式X的故障诊断正确率达到100％，对故障模式Y的诊断正确率为1％，对故障模式Y的诊断正确率为95％，总计故障诊断正确率68.3％，远远低于本专利所提方法的诊断正确率。The results in Table 6 show that the correct rate of fault diagnosis by DS method for fault mode X reaches 100%, the correct rate for fault mode Y is 1%, and the correct rate for fault mode Y is 95%. The total fault diagnosis correct rate is 68.3 %, far lower than the diagnostic accuracy of the method proposed in this patent.

表7所有待检样本的诊断结果(BP神经网络)Table 7 Diagnostic results of all samples to be tested (BP neural network)

Figure BDA0003685211890000182
Figure BDA0003685211890000182

表7结果显示，BP神经网络方法对故障模式X的故障诊断正确率达到70％，对故障模式Y的诊断正确率为100％，对故障模式Y的诊断正确率为75％，总计故障诊断正确率81.67％，远远低于本专利所提方法的诊断正确率。The results in Table 7 show that the BP neural network method has a fault diagnosis accuracy rate of 70% for failure mode X, 100% for failure mode Y, 75% for failure mode Y, and the total fault diagnosis is correct. The diagnostic accuracy rate is 81.67%, which is far lower than the diagnostic accuracy rate of the method proposed in this patent.

综合表6和表7可知，本实施例的诊断效果优越，有着更高的诊断效率和精度。From Table 6 and Table 7, it can be seen that the diagnostic effect of this embodiment is superior, and the diagnostic efficiency and accuracy are higher.

步骤八：将步骤三确定的火炮反后坐装置故障待检样本数据代入步骤四构造的故障模式高斯模型中，求解每个故障特征信号所对应证据的基本概率分配；用步骤六确定的可靠度给每个证据重新分配权重，降低冲突信息所带来的影响，提升对反后坐装置故障诊断性能。所述提升对火炮反后坐装置的诊断性能包括提高对反后坐装置的诊断效率、诊断精度。Step 8: Substitute the sample data to be checked for the fault of the artillery anti-recoil device determined in Step 3 into the failure mode Gaussian model constructed in Step 4, and solve the basic probability distribution of the evidence corresponding to each fault characteristic signal; use the reliability determined in Step 6 to give The weight of each evidence is redistributed to reduce the impact of conflicting information and improve the fault diagnosis performance of the anti-recoil device. The improving the diagnostic performance of the artillery anti-recoil device includes improving the diagnostic efficiency and diagnostic accuracy of the anti-recoil device.

以上公开的具体描述，对发明的目的、技术方案和有效效果做了进一步的阐述，但是本发明的实施例并非局限于此，凡在本发明的精神和原则之内，所做的任何修改应纳入本发明的保护范围之内。The specific description disclosed above further elaborates the purpose, technical solution and effective effect of the invention, but the embodiments of the present invention are not limited to this, and any modifications made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. The RMSD-DS-based gun recoil device fault diagnosis method is characterized by comprising the following steps of:
the method comprises the following steps: determining a typical fault mode and a fault characteristic signal of the gun recoil preventing device;
step two: acquiring and obtaining corresponding fault characteristic signals of the gun recoil device under a typical fault mode;
step three: analyzing the corresponding fault characteristic signals obtained in the step two under the typical fault mode, and classifying the fault characteristic signal data into fault training sample data and fault to-be-detected sample data; solving the average value and the standard deviation of training samples belonging to different fault modes of the gun recoil resisting device on different fault characteristic signals, and then constructing Gaussian models of the training samples belonging to different fault modes on different fault signals;
step four: solving basic probability distribution of evidences corresponding to fault characteristic signals of the to-be-detected sample of the artillery anti-recoil device according to the failure mode Gaussian model of the artillery anti-recoil device constructed in the third step;
step five: according to the basic probability distribution of the evidence corresponding to the fault characteristic signals of the to-be-detected sample of the gun recoil device obtained by solving in the fourth step, defining and solving conflict factors among the evidences under the fault mode framework of the gun recoil device, and constructing a conflict factor matrix according to all the solved conflict factors; defining and solving Root Mean Square Deviation (RMSD) distances among all evidences under a failure mode framework of the gun anti-recoil device; constructing an RMSD collision coefficient by taking the collision factor and the geometric mean value of the normalized RMSD distance as the value of the RMSD collision coefficient; solving and constructing an RMSD similarity coefficient according to the constructed RMSD conflict coefficient, and conveniently defining the reliability of the subsequent step six through the constructed RMSD similarity coefficient;
step six: defining the reliability of each evidence as the sum of RMSD similarity coefficients of the evidence and other evidences, and determining the reliability of each evidence according to the definition; analyzing the reliability of each evidence, defining the weight of each evidence as the ratio of the reliability of the evidence to the sum of the reliabilities of all the evidences, and solving the weight of each evidence; carrying out weight distribution on all evidences according to the reliability of each evidence to reduce the conflict between information, and then obtaining an integrated evidence through weighted average, thereby facilitating the fusion of the subsequent step seven and improving the accuracy of fault diagnosis;
step seven: in a gun fault mode frame, self-fusing the integration evidence obtained in the step six by using a Dempster-Shafer (DS) evidence theory method to obtain the occurrence probability of the fault mode of the corresponding gun anti-recoil device; and traversing the occurrence probability of the fault modes of all the gun recoil prevention devices, determining that the fault mode corresponding to the maximum basic probability distribution value is the finally diagnosed fault mode, namely realizing high-precision efficiency diagnosis of the gun recoil prevention device fault based on RMSD-DS.
2. The RMSD-DS based gun recoil device fault diagnosis method of claim 1, further comprising the steps of: substituting the sample data to be detected of the failure of the gun recoil device determined in the third step into the failure mode Gaussian model constructed in the fourth step, and solving the basic probability distribution of the evidence corresponding to each failure characteristic signal; the reliability determined in the step six is used for redistributing the weight to each evidence, so that the influence caused by conflict information is reduced, and the fault diagnosis performance of the anti-recoil device is improved; the improvement of the diagnosis performance of the anti-recoil device comprises improvement of diagnosis efficiency and diagnosis precision of the anti-recoil device.
3. The RMSD-DS-based gun recoil device fault diagnosis method as claimed in claim 1 or 2, characterized in that the first step is realized by the method as follows:
determining three typical failure modes of the artillery anti-recoil device, namely a check ring abrasion X, a re-advancing machine air leakage Y and a check rod piston abrasion Z, wherein the three typical failure modes are the check ring abrasion X, the re-advancing machine air leakage Y and the check rod piston abrasion Z, and then a failure mode frame of the artillery anti-recoil device is expressed as theta ═ X, Y and Z }; the fault characteristic signals of the gun anti-recoil device are determined as follows: a maximum squat displacement Xmax, a maximum squat speed Vmax, a maximum reentry speed Umax, and a reentry to position speed Uend.
4. The RMSD-DS-based gun recoil device fault diagnosis method as claimed in claim 3, wherein the second step is realized by the following method:
when the artillery works, four fault characteristic signals of the anti-recoil device in each fault mode are collected by a sensor arranged on the anti-recoil device, and the obtained data is F i The method comprises the following steps of (1) representing three fault modes of check ring wear, double-feed machine air leakage and check rod piston wear, wherein F is X, Y and Z; i is 1,2,3 and 4, which respectively represent four fault characteristic signals of a maximum recoil displacement Xmax, a maximum recoil speed Vmax, a maximum recoil speed Umax and a recoil to reach speed Uend; a set of collected sample dataIs represented by (F) 1 ,F 2 ,F 3 ,F 4 )，F 1 Representing maximum recoil displacement Xmax signal data, F, corresponding to failure mode F 2 Represents the maximum squat speed Vmax signal data corresponding to the failure mode F, F 3 Representing maximum remade speed Umax signal data, F, corresponding to the failure mode F 4 Representing the signal data of the speed Uend of the double-entry bit corresponding to the failure mode F.
5. The RMSD-DS based artillery recoil device fault diagnosis method of claim 4, wherein the third step comprises the following steps:
step 3.1: classifying the fault characteristic signals corresponding to the typical fault mode acquired in the step two into fault training sample data and fault to-be-detected sample data;
based on the fault characteristic signals corresponding to the typical fault modes acquired in the step two, sample data in a preset proportion is selected from four corresponding fault characteristic signal data in each fault mode to serve as fault training samples, and the residual sample data serves as a fault to-be-detected sample;
step 3.2: for the fault training samples selected in the step 3.1, solving the average value and the standard deviation of the training samples belonging to different fault modes of the gun recoil device on different fault characteristic signals;
for the selected fault training samples, solving the average value mu (F) of the training samples belonging to different fault modes on different fault characteristic signals i ) And standard deviation σ (F) i ) Average value of μ (F) i ) The formula (1) shows the standard deviation sigma (F) i ) Is expressed by equation (2):
Figure FDA0003685211880000021
Figure FDA0003685211880000022
in the formulas (1) and (2), F ═ X, Y, Z represent three failure modes; i is 1,2,3,4, which represents four fault characteristic signals; j ═ 1,2, …, N, and represents a data sequence;
step 3.3: constructing Gaussian models of training samples belonging to different fault modes on different fault signals according to the average value and the standard deviation obtained by solving in the step 3.2;
average value mu (F) obtained by solving according to step 3.2 i ) And standard deviation σ (F) i ) And constructing Gaussian models (membership function) of the training samples belonging to different fault modes on different fault signals, wherein the Gaussian models are shown in a formula (3):
Figure FDA0003685211880000031
in formula (3), F ═ X, Y, Z, represents three failure modes; i is 1,2,3,4, which represents four fault characteristic signals;
when the fault characteristic signal is the maximum recoil displacement (Xmax), the fault modes are Gaussian models on the check ring abrasion (X), the re-advancing machine air leakage (Y) and the check rod piston abrasion (Z), and the Gaussian models are as follows:
Figure FDA0003685211880000032
Figure FDA0003685211880000033
Figure FDA0003685211880000034
when the fault characteristic signal is the maximum recoil speed (Vmax), the fault mode is a Gaussian model on the check ring abrasion (X), the double-advancing machine air leakage (Y) and the check rod piston abrasion (Z) as follows:
Figure FDA0003685211880000035
and
Figure FDA0003685211880000036
Figure FDA0003685211880000037
Figure FDA0003685211880000038
Figure FDA0003685211880000039
when the fault characteristic signal is the maximum re-advancing speed (Umax), the fault modes are Gaussian models on the check ring abrasion (X), the re-advancing machine air leakage (Y) and the check rod piston abrasion (Z) as follows:
Figure FDA00036852118800000310
and
Figure FDA00036852118800000311
Figure FDA00036852118800000312
Figure FDA00036852118800000313
Figure FDA00036852118800000314
when the fault characteristic signal is the speed of the double-in-place (Uend), the fault mode is the controlThe Gaussian models of the ring abrasion (X), the air leakage (Y) of the re-advancing machine and the piston abrasion (Z) of the braking and retreating rod are as follows:
Figure FDA0003685211880000041
and
Figure FDA0003685211880000042
Figure FDA0003685211880000043
Figure FDA0003685211880000044
Figure FDA0003685211880000045
。
equations (4) to (15) are gaussian models of the training samples of different failure modes on different failure signals.
6. The RMSD-DS based artillery recoil device failure diagnostic method of claim 5, wherein the fourth step comprises the steps of:
step 4.1: solving the vertical coordinate of the intersection point of the sample to be detected and the Gaussian models with different fault modes under each fault signal according to the Gaussian models with the fault modes of the gun recoil device constructed in the step 3.3;
for a set of suspect samples for which the failure mode is unknown, the corresponding data can be represented as (F) 1 ,F 2 ,F 3 ,F 4 ) Wherein F is X, Y, Z; 1 in the subscripts represents the maximum squat displacement (Xmax), 2 represents the maximum squat speed (Vmax), 3 represents the maximum re-entry speed (Umax), and 4 represents the re-entry to position speed (Uend);
when the fault characteristic signal is the maximum recoil displacement (Xmax), the solving formula of the vertical coordinate of the intersection point of the sample to be detected and the Gaussian model of different fault modes is as follows:
Figure FDA0003685211880000046
Figure FDA0003685211880000047
Figure FDA0003685211880000048
when the fault characteristic signal is the maximum recoil speed (Vmax), the vertical coordinate of the intersection point of the sample to be detected and the Gaussian models of different fault modes is as follows:
Figure FDA0003685211880000049
Figure FDA00036852118800000410
Figure FDA00036852118800000411
Figure FDA00036852118800000412
when the fault characteristic signal is the maximum recurrence velocity (Umax), the ordinate of the intersection point of the sample to be detected and the Gaussian models of different fault modes is as follows:
Figure FDA0003685211880000051
Figure FDA0003685211880000052
Figure FDA0003685211880000053
Figure FDA0003685211880000054
when the fault characteristic signal is a complex-in-place speed (Uend), the vertical coordinate of the intersection point of the sample to be detected and the Gaussian models of different fault modes is as follows:
Figure FDA0003685211880000055
Figure FDA0003685211880000056
Figure FDA0003685211880000057
Figure FDA0003685211880000058
step 4.2: representing basic probability distribution of evidences corresponding to the four fault characteristic signals;
each sample to be checked contains four fault characteristic signals (Xmax, Vmax, Umax and Uend), each fault characteristic signal corresponds to one group of evidences, and then the basic probability distribution function of the evidences corresponding to each fault characteristic signal (Xmax, Vmax, Umax and Uend) can be represented as m i (i ═ 1,2,3, 4); in the step one, the failure modes of the gun recoil preventing device are X, Y and Z, and the basic probability distribution of a group of evidences comprises m i (X)、m i (Y) and m i (Z) wherein m i (X) is shown in the evidence m i Fundamental probability of a lower inspected sample belonging to failure mode XDistribution, m i (Y) is shown in the evidence m i The lower to-be-examined sample belongs to the fundamental probability distribution of the failure mode Y, m i (Z) is shown in the evidence m i The lower sample to be detected belongs to the basic probability distribution of the fault mode Z;
step 4.3: according to the step 4.1, acquiring the vertical coordinate of the intersection point of the to-be-detected sample and the Gaussian models with different fault modes under each fault signal, and respectively solving the basic probability distribution of the evidence corresponding to each fault characteristic signal of the to-be-detected sample;
evidence m corresponding to the fault characteristic signal of the maximum recoil displacement (Xmax) 1 The solving formula of the basic probability distribution function is as follows:
Figure FDA0003685211880000059
Figure FDA00036852118800000510
Figure FDA0003685211880000061
corresponding evidence m when the fault signature is at maximum squat speed (Vmax) 2 The basic probability distribution function of (a) is: m is 2 (X)，m 2 (Y)，m 2 (Z)；
Figure FDA0003685211880000062
Figure FDA0003685211880000063
Figure FDA0003685211880000064
Corresponding evidence m when the fault characteristic signal is the maximum re-entry speed (Umax) 3 The basic probability distribution function of (a) is: m is 3 (X)，m 3 (Y)，m 3 (Z)；
Figure FDA0003685211880000065
Figure FDA0003685211880000066
Figure FDA0003685211880000067
The corresponding evidence m when the fault characteristic signal is the speed of the multiple entry (Uend) 4 The basic probability distribution function of (a) is: m is 4 (X)，m 4 (Y)，m 4 (Z)；
Figure FDA0003685211880000068
Figure FDA0003685211880000069
Figure FDA00036852118800000610
。
7. The RMSD-DS based artillery recoil device fault diagnosis method of claim 6 wherein the step five comprises the steps of:
step 5.1: defining and solving conflict factors among all evidences under a failure mode framework of the gun recoil prevention device, and constructing a conflict factor matrix according to all solved conflict factors; the conflict factors among the evidences are the conflict factors among every two groups of evidences;
to conveniently give a formula for solving the conflict factor, m is defined under a cannon fault mode framework theta ═ X, Y, Z ═ m 1 And m 2 For two sets of evidence, the corresponding failure modes are denoted as F '(F' ═ X, Y, Z) and F ″ (F ″ ═ X, Y, Z), respectively, and evidence m is evidence 1 And m 2 Is as shown in equation (40):
Figure FDA0003685211880000071
the collision factor matrix among the evidences according to the formula (40) is:
Figure FDA0003685211880000072
however, the collision factor has a defect, and it can be known from the formula (40) that the collision factor obtained by solving when the two evidences are the same is not 0, so that the collision factor needs to be corrected by introducing the RMSD distance between the evidences in the subsequent step 5.2, and a collision coefficient, that is, the RMSD collision coefficient, is constructed in the subsequent step 5.3;
step 5.2: under the fault mode framework of the gun recoil device, RMSD distances among all evidences are defined and solved, an RMSD distance matrix is constructed according to all the solved RMSD distances, and the normalized RMSD distance matrix is solved;
definition m 1 And m 2 For two sets of evidence, the corresponding failure modes are denoted as F '(F' ═ X, Y, Z) and F ″ (F ═ X, Y, Z), respectively, and evidence m is defined 1 And m 2 The Root Mean Square Deviation (RMSD) distance between is:
Figure FDA0003685211880000073
and (3) solving according to a formula (42) to obtain an RMSD distance matrix among the evidences, wherein the formula (43) is as follows:
Figure FDA0003685211880000074
then searching the maximum value RMSD in the RMSD distance matrix max Max { RMSD }, followed by normalization of the RMSD distance matrix, i.e., each element of the RMSD distance matrix divided by the RMSD max And obtaining a normalized RMSD distance matrix, as shown in formula (44):
Figure FDA0003685211880000081
step 5.3: defining the collision factor in the step 5.1 and the geometric mean value of the normalized RMSD distance in the step 5.2 as the value of the RMSD collision coefficient, and constructing the RMSD collision coefficient;
defining evidence m by taking the collision factor obtained in the step 5.1 and the geometric mean of the normalized RMSD distance obtained in the step 5.2 as the value of the RMSD collision coefficient 1 And m 2 The RMSD collision coefficient of (a) is expressed as:
Figure FDA0003685211880000082
in formula (45), K (m) 1 ,m 2 ) Representative evidence m 1 And m 2 Conflict factor of (2), RMSD (m) 1 ,m 2 ) Represents evidence m 1 And m 2 Normalized RMSD distance;
the RMSD collision coefficient matrix obtained according to equation (45) is:
Figure FDA0003685211880000083
step 5.4: based on the RMSD collision coefficient in the step 5.3, solving and constructing an RMSD similarity coefficient;
the RMSD collision coefficient constructed in step 5.3 represents the collision degree among evidences, and the value range is [0,1 ]]Subtracting the RMSD collision coefficient from 1 can represent the similarity degree between the evidences, and define the evidence m 1 And m 2 The RMSD similarity coefficient of (a) is expressed as:
Sim RMSD (m 1 ,m 2 )＝1-Con RMSD (m 1 ,m 2 ) (47)
the RMSD similarity coefficient matrix obtained according to equation (47) is:
Figure FDA0003685211880000084
。
8. the RMSD-DS based artillery recoil device failure diagnostic method of claim 7, wherein the sixth step comprises the steps of:
step 6.1: defining the reliability of each evidence as the sum of RMSD similarity coefficients of the evidence and other evidences, and determining the reliability of each evidence according to the definition;
defining the reliability of each evidence as the sum of the RMSD similarity coefficients of the evidence and other evidences, and determining the evidence m 1 The reliability of (d) is formulated as:
Rel(m 1 )＝Sim RMSD (m 1 ,m 2 )+Sim RMSD (m 1 ,m 3 )+Sim RMSD (m 1 ,m 4 ) (49)
evidence m 2 The reliability of (d) is formulated as:
Rel(m 2 )＝Sim RMSD (m 2 ,m 1 )+Sim RMSD (m 2 ,m 3 )+Sim RMSD (m 2 ,m 4 ) (50)
evidence m 3 The reliability of (d) is formulated as:
Rel(m 3 )＝Sim RMSD (m 3 ,m 1 )+Sim RMSD (m 3 ,m 2 )+Sim RMSD (m 3 ,m 4 ) (51)
evidence m 4 The reliability of (d) is formulated as:
Rel(m 4 )＝Sim RMSD (m 4 ,m 1 )+Sim RMSD (m 4 ,m 2 )+Sim RMSD (m 4 ,m 3 ) (52)
wherein, the reliability of the evidence represents the support degree of other evidence to the evidence;
the greater the reliability of the evidence is, the higher the importance of the evidence in the fusion decision process is, and the weight distributed in the subsequent step 6.2 is preferably large;
the smaller the reliability of the evidence is, the lower the importance of the evidence in the fusion decision process is, and the weight distributed in the subsequent step 6.2 is preferably small;
step 6.2: analyzing the reliability of each evidence determined in the step 6.1, defining the weight of each evidence as the ratio of the reliability of the evidence to the sum of the reliabilities of all the evidences, and solving the weight of each evidence;
defining the weight of each evidence as the ratio of the reliability of the evidence to the sum of all evidence reliabilities, and determining the evidence m 1 The weight of (d) is expressed as:
Figure FDA0003685211880000091
evidence m 2 The reliability of (d) is formulated as:
Figure FDA0003685211880000092
evidence m 3 The reliability of (d) is formulated as:
Figure FDA0003685211880000093
evidence m 4 The reliability of (d) is formulated as:
Figure FDA0003685211880000094
step 6.3: performing weight distribution on all evidences according to the reliability of each evidence in the step 6.2, reducing the conflict between information, and then obtaining an integrated evidence through weighted average, so that the integration in the subsequent step seven is facilitated, and the fault diagnosis accuracy is improved;
the integrated evidence is obtained by weighted averaging according to the weights assigned in step 6.2, and is represented as:
Figure FDA0003685211880000095
the basic probability distribution for failure modes of X, Y and Z, respectively, under the evidence of integration is obtained and is expressed as:
Figure FDA0003685211880000101
Figure FDA0003685211880000102
Figure FDA0003685211880000103
。
9. the method for diagnosing a malfunction of an anti-recoil mechanism of a gun based on RMSD-DS according to claim 8, wherein said seventh step comprises the steps of:
step 7.1: definition m 1 And m 2 For two sets of evidence, the corresponding failure modes are denoted F '(F' ═ X, Y, Z) and F ″ (F ═ X, Y, Z), respectively, giving evidence m 1 And m 2 The DS fusion rule of (1);
in artillery failure mode to give DS fusion rules convenientlyFrame Θ is { X, Y, Z }, m 1 And m 2 For two sets of evidence, the corresponding failure modes are denoted as F '(F' ═ X, Y, Z) and F ″ (F ″ ═ X, Y, Z), respectively, and evidence m is evidence 1 And m 2 The DS fusion rule of (1) is shown as formula (61):
Figure FDA0003685211880000104
step 7.2: fusing the integration evidence for 3 times according to the DS fusion rule given in the step 7.1, and fusing the integration evidence by using the DS fusion rule to obtain the occurrence probability of the fault mode of the corresponding artillery recoil prevention device;
step 7.3: and (3) obtaining the occurrence probability of the fault modes of all the gun recoil resisting devices according to the traversal in the step (7.2), determining that the fault mode corresponding to the maximum basic probability distribution value is the finally diagnosed fault mode, namely realizing the high-precision and efficient diagnosis of the fault of the gun recoil resisting devices based on an RMSD-DS method.
CN202210649020.6A 2022-06-09 2022-06-09 Method for diagnosing faults of gun anti-squat device based on RMSD-DS Active CN115048959B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210649020.6A CN115048959B (en) 2022-06-09 2022-06-09 Method for diagnosing faults of gun anti-squat device based on RMSD-DS

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210649020.6A CN115048959B (en) 2022-06-09 2022-06-09 Method for diagnosing faults of gun anti-squat device based on RMSD-DS

Publications (2)

Publication Number Publication Date
CN115048959A true CN115048959A (en) 2022-09-13
CN115048959B CN115048959B (en) 2024-06-21

Family

ID=83162215

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210649020.6A Active CN115048959B (en) 2022-06-09 2022-06-09 Method for diagnosing faults of gun anti-squat device based on RMSD-DS

Country Status (1)

Country Link
CN (1) CN115048959B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115979058A (en) * 2022-12-30 2023-04-18 中国人民解放军32382部队 A Method of Fault Diagnosis for New Self-propelled Artillery System

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520266A (en) * 2018-03-01 2018-09-11 西北工业大学 A Time Domain Fusion Fault Diagnosis Method Based on DS Evidence Theory
CN109540520A (en) * 2018-11-29 2019-03-29 中国船舶重工集团海装风电股份有限公司 A kind of rolling bearing fault fusion diagnosis method based on improvement D-S evidence theory
US20210003640A1 (en) * 2019-07-01 2021-01-07 Wuhan University Fault locating method and system based on multi-layer evaluation model
CN113063314A (en) * 2021-03-23 2021-07-02 哈尔滨工程大学 Fault diagnosis method for gun launching system based on SVM (support vector machine) and GA-SVM (genetic algorithm-support vector machine)
CN114444585A (en) * 2022-01-13 2022-05-06 北京理工大学 Multi-source information fusion method for conflict evidence

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520266A (en) * 2018-03-01 2018-09-11 西北工业大学 A Time Domain Fusion Fault Diagnosis Method Based on DS Evidence Theory
CN109540520A (en) * 2018-11-29 2019-03-29 中国船舶重工集团海装风电股份有限公司 A kind of rolling bearing fault fusion diagnosis method based on improvement D-S evidence theory
US20210003640A1 (en) * 2019-07-01 2021-01-07 Wuhan University Fault locating method and system based on multi-layer evaluation model
CN113063314A (en) * 2021-03-23 2021-07-02 哈尔滨工程大学 Fault diagnosis method for gun launching system based on SVM (support vector machine) and GA-SVM (genetic algorithm-support vector machine)
CN114444585A (en) * 2022-01-13 2022-05-06 北京理工大学 Multi-source information fusion method for conflict evidence

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115979058A (en) * 2022-12-30 2023-04-18 中国人民解放军32382部队 A Method of Fault Diagnosis for New Self-propelled Artillery System

Also Published As

Publication number Publication date
CN115048959B (en) 2024-06-21

Similar Documents

Publication Publication Date Title
CN110851957A (en) Atmospheric data sensing system resolving method based on deep learning
CN112308381B (en) Equipment contribution data analysis method, system, storage medium and computer device
CN111950627B (en) Multi-source information fusion method and application thereof
CN104239712B (en) Real-time evaluation method for anti-interference performance of radar
CN108427400B (en) A fault diagnosis method for aircraft pitot tubes based on neural network analytical redundancy
CN106169124B (en) A Confidence Inference Method for Comprehensive Evaluation of System-Level Product Reliability
CN110348752A (en) A kind of large scale industry system structure security assessment method considering environmental disturbances
CN114971345B (en) Quality measuring method, equipment and storage medium for built environment
CN113295421B (en) Engine fault diagnosis method based on improved conflict coefficient and reliability entropy
CN115048959A (en) RMSD-DS-based gun recoil prevention device fault diagnosis method
CN110750876B (en) A bearing data model training and usage method
CN115017984A (en) A kind of aviation engine failure risk early warning method and system
CN110889207A (en) System combination model credibility intelligent evaluation method based on deep learning
CN118396980B (en) New energy vehicle shock absorber rod detection system and method based on machine vision
CN110046651A (en) A kind of pipeline conditions recognition methods based on monitoring data multi-attribute feature fusion
CN109684713A (en) Bayes-based complex system reliability analysis method
CN115455833B (en) Pneumatic uncertainty characterization method considering classification
CN114722695B (en) A FADS solution system and method based on dimensionless input-output neural network
CN117496350A (en) A flying bird detection method based on the improved YOLO-v5 algorithm
CN110705132A (en) Guidance control system performance fusion evaluation method based on multi-source heterogeneous data
CN112906746B (en) Multi-source track fusion evaluation method based on structural equation model
CN113534129B (en) Method and system for evaluating high-speed target detection performance of foundation broadband radar
CN113108949B (en) Model fusion-based sonde temperature sensor error prediction method
CN114757332A (en) Intelligent fault detection method for aircraft pneumatic sensor
CN115169461A (en) A multi-level model-based method for identifying and locating burst pipes in water supply network

Legal Events

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