CN103793589A - High-speed train fault handling method - Google Patents
High-speed train fault handling methodDownload PDFInfo
- Publication number
- CN103793589A CN103793589ACN201210428024.8ACN201210428024ACN103793589ACN 103793589 ACN103793589 ACN 103793589ACN 201210428024 ACN201210428024 ACN 201210428024ACN 103793589 ACN103793589 ACN 103793589A
- Authority
- CN
- China
- Prior art keywords
- fault
- rule
- node
- faults
- bullet train
- 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
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription23
- 238000005065miningMethods0.000claimsdescription8
- 230000008878couplingEffects0.000claims4
- 238000010168coupling processMethods0.000claims4
- 238000005859coupling reactionMethods0.000claims4
- 239000012141concentrateSubstances0.000claims1
- 239000000203mixtureSubstances0.000claims1
- 230000001364causal effectEffects0.000abstractdescription11
- 238000012423maintenanceMethods0.000abstractdescription10
- 238000003672processing methodMethods0.000abstractdescription5
- 238000004458analytical methodMethods0.000abstractdescription3
- 239000010410layerSubstances0.000description4
- 238000010586diagramMethods0.000description2
- 239000002356single layerSubstances0.000description2
- XLYOFNOQVPJJNP-UHFFFAOYSA-NwaterSubstancesOXLYOFNOQVPJJNP-UHFFFAOYSA-N0.000description2
- 125000002015acyclic groupChemical group0.000description1
- 230000009286beneficial effectEffects0.000description1
- 230000007812deficiencyEffects0.000description1
- 238000003745diagnosisMethods0.000description1
- 230000000694effectsEffects0.000description1
- 238000005516engineering processMethods0.000description1
- 238000013178mathematical modelMethods0.000description1
Images
Landscapes
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
Translated fromChineseDescription
Translated fromChinese技术领域technical field
本发明专利涉及故障诊断技术，具体涉及一种高速列车故障原因分析处理方法。The patent of the present invention relates to fault diagnosis technology, in particular to a method for analyzing and processing the fault causes of high-speed trains.
背景技术Background technique
高速列车网络控制系统故障间复杂的因果关系，给列车维修带来了极大困难。因此，寻找故障原因，定位根源故障，对节省列车维修成本具有十分重要的意义。The complex causal relationship between faults in the network control system of high-speed trains has brought great difficulties to train maintenance. Therefore, finding the cause of the failure and locating the root cause of the failure are of great significance to saving the cost of train maintenance.
目前的故障原因分析处理方法通常根据专家经验，采用贝叶斯网络对故障间的因果关系进行建模，并通过求解贝叶斯网络，获得可能的根源故障。贝叶斯网络是一种概率网络，它是基于概率推理的图形化网络，而贝叶斯公式则是这个概率网络的基础。贝叶斯网络是基于概率推理的数学模型，基于概率推理的贝叶斯网络(Bayesian network)是为了解决不定性和不完整性问题而提出的，它对于解决复杂设备不确定性和关联性引起的故障有很的优势，在多个领域中获得广泛应用。The current fault cause analysis and processing methods usually use Bayesian network to model the causal relationship between faults based on expert experience, and obtain possible root faults by solving the Bayesian network. Bayesian network is a kind of probabilistic network, which is a graphical network based on probabilistic reasoning, and Bayesian formula is the basis of this probabilistic network. Bayesian network is a mathematical model based on probabilistic reasoning. Bayesian network based on probabilistic reasoning is proposed to solve the problems of uncertainty and incompleteness. The fault has great advantages and is widely used in many fields.
规则推理，是指把相关领域的专家知识形式化的描述出来，形成系统规则。这些规则表示着该领域的一些问题与这些问题相应的答案，可以利用它们来模仿专家在求解中的关联推理能力。Rule reasoning refers to the formal description of expert knowledge in related fields to form system rules. These rules represent some problems in this field and the corresponding answers to these problems, and they can be used to imitate the associative reasoning ability of experts in solving problems.
基于规则中处理的变量的类别：1）关联规则处理的变量可以分为布尔型和数值型。布尔型关联规则处理的值都是离散的、种类化的，它显示了这些变量之间的关系；而数值型关联规则可以和多维关联或多层关联规则结合起来，对数值型字段进行处理，将其进行动态的分割，或者直接对原始的数据进行处理，当然数值型关联规则中也可以包含种类变量。2）基于规则中数据的抽象层次：基于规则中数据的抽象层次，可以分为单层关联规则和多层关联规则。在单层的关联规则中，所有的变量都没有考虑到现实的数据是具有多个不同的层次的；而在多层的关联规则中，对数据的多层性已经进行了充分的考虑。3）基于规则中涉及到的数据的维数：关联规则中的数据，可以分为单维的和多维的。Based on the categories of the variables processed in the rules: 1) The variables processed by the association rules can be classified as Boolean and numerical. The values processed by Boolean association rules are all discrete and categorical, which shows the relationship between these variables; while numerical association rules can be combined with multi-dimensional association or multi-layer association rules to process numerical fields, Split it dynamically, or directly process the original data. Of course, numerical association rules can also contain category variables. 2) Based on the abstract level of data in rules: based on the abstract level of data in rules, it can be divided into single-layer association rules and multi-layer association rules. In the single-layer association rules, all the variables do not take into account that the actual data has multiple different levels; while in the multi-layer association rules, the multi-layer nature of the data has been fully considered. 3) Based on the dimensionality of the data involved in the rules: the data in the association rules can be divided into single-dimensional and multi-dimensional.
采用贝叶斯网络对故障间的因果关系进行建模这类方法需要关于故障间因果关系的专家经验，但在实际应用中，高速列车许多故障间的因果关系往往还不为人所知，没有专家经验可循。在这种情况下，已有的基于贝叶斯网络的故障原因处理方法就不再适用了。如何发现故障间尚不为人知的因果关联关系，从而在缺少相关专家经验的情况下，对高速列车所产生的大量故障中寻找到根源故障，成为了有待解决的问题。Modeling the causal relationship between faults using Bayesian networks requires expert experience on the causal relationship between faults, but in practical applications, the causal relationship between many faults of high-speed trains is often unknown, and no experts There is experience to follow. In this case, the existing Bayesian network-based fault cause processing method is no longer applicable. How to discover the unknown causal relationship among the faults, so that in the absence of relevant expert experience, how to find the root fault among the large number of faults generated by high-speed trains has become a problem to be solved.
发明内容Contents of the invention
针对现有技术中的不足，本发明通过结合关联规则挖掘和规则推理，对故障原因进行分析，大大节省维修成本。Aiming at the deficiencies in the prior art, the present invention analyzes the causes of failures by combining association rule mining and rule reasoning, thereby greatly saving maintenance costs.
为解决如上的技术问题，本发明提供了一种基于关联规则挖掘与规则推理的高速列车故障原因分析处理方法，其具体步骤如下：In order to solve the above technical problems, the invention provides a high-speed train failure cause analysis and processing method based on association rule mining and rule reasoning, and its specific steps are as follows:
1）查询故障列表中在用户设定时间内发生的故障和故障代码，组成一故障集；1) Query the faults and fault codes that occurred within the user-set time in the fault list to form a fault set;
2）对所述故障集进行扫描得到满足最小支持度的频繁项目集，在所述项目集中生成故障关联规则并得到所述故障关联规则中的合法故障关联规则集；2) Scanning the fault set to obtain a frequent item set satisfying the minimum support, generating fault association rules in the item set and obtaining a legal fault association rule set in the fault association rules;
3）将所述合法故障关联规则集通过规则图表示，根据步骤1）所述故障列表中故障与该规则图上的节点进行匹配，得到匹配后的规则图；3) The legal fault association rule set is represented by a rule graph, and according to step 1) the faults in the fault list are matched with the nodes on the rule graph to obtain the matched rule graph;
4）在所述匹配后的规则图中遍历找到所有节点均被匹配路径；计算出所述被匹配路径上各个节点所代表故障的重要性并排序；4) Traversing through the matched rule graph to find the matched path for all nodes; calculating and sorting the importance of faults represented by each node on the matched path;
5）根据所述重要性排序按照故障重要性由高到低进行处理。5) According to the order of importance, process the faults in descending order of importance.
所述故障的重要性P(v)=O(v)+L(v)，其中，O(v)为节点v在规则图上的出度，L(v)为所有通过节点v的被匹配路径的最大路径长度值。The importance of the fault P(v)=O(v)+L(v), where O(v) is the out-degree of node v on the rule graph, and L(v) is the matched The maximum path length value for the path.
所述故障模式集是所有频繁项目集的集合；所述频繁项目集是所包含的故障同时出现的次数大于用户设定的最小支持度的项目集。The failure mode set is a set of all frequent item sets; the frequent item set is an item set in which the number of simultaneous occurrences of faults is greater than the minimum support set by the user.
所述合法故障关联规则集包括若干故障关联规则，所述每一条关联规则左子式为根源故障，右子式为结果故障的故障关联规则。The legal fault correlation rule set includes several fault correlation rules, the left sub-form of each correlation rule is the root cause fault, and the right sub-form is the fault correlation rule of the resulting fault.
所述匹配后的规则图中的每个节点代表高速列车的故障，有向边从根源故障中发出指向结果故障，组成一条故障关联规则。Each node in the matched rule graph represents a fault of the high-speed train, and directed edges point to the result fault from the root fault to form a fault association rule.
所述故障关联规则表示高速列车故障间的因果关系。The fault association rules represent the causal relationship between high-speed train faults.
所述频繁项集根据频繁项集挖掘算法Apriori得到。The frequent itemsets are obtained according to the frequent itemsets mining algorithm Apriori.
将所述频繁项集中出现时间早的故障作为根源故障，出现时间晚的故障作为结果故障，组成若干故障关联规则。Taking the early fault in the frequent itemset as the root fault, and the late fault as the result fault, a number of fault association rules are formed.
将所述频繁项集的置信度作为该故障关联规则为真的概率，获取故障间未知的关联关系。Using the confidence degree of the frequent itemsets as the probability that the fault association rule is true, the unknown association relationship between faults is obtained.
将所述关联规则集中左子式的根源故障作为子节点，右子式的结果故障作为父节点；对于同一条路径上节点所表示的故障，按照先修子节点所代表的故障，再修理父节点所代表的故障顺序进行处理。The root fault of the left sub-form in the association rule set is used as a child node, and the result fault of the right sub-form is used as a parent node; for the faults represented by nodes on the same path, the fault represented by the sub-node is first repaired, and then the parent node is repaired The fault sequence represented is processed.
本发明的有益效果Beneficial effects of the present invention
首先，本发明利用关联规则挖掘获取故障间的关联关系，这样便可在专家知识缺乏的情况下，支持对故障原因的处理；同时，本发明利用规则匹配寻找海量故障中的因果关系，使维修可以优先修理重要性高的根源故障，从而大大降低了高速列车的故障维修成本。First of all, the present invention utilizes association rules to mine and obtain the associations between faults, so that in the absence of expert knowledge, it can support the processing of fault causes; at the same time, the present invention uses rule matching to find causal relations among massive faults, enabling maintenance The root faults with high importance can be repaired first, thereby greatly reducing the fault maintenance cost of high-speed trains.
附图说明Description of drawings
图1是本发明高速列车故障处理方法流程图；Fig. 1 is a high-speed train failure processing method flowchart of the present invention;
图2是本发明高速列车故障处理方法一实施例中规则图。Fig. 2 is a rule diagram in an embodiment of the high-speed train fault handling method of the present invention.
具体实施方式：Detailed ways:
下面将结合本发明实施例中的附图，对本分买那个实施例中的技术方案进行清楚、完整地描述，可以理解的是，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will clearly and completely describe the technical solution in that embodiment of the present invention in conjunction with the accompanying drawings in the embodiment of the present invention. It should be understood that the described embodiments are only some of the embodiments of the present invention, not all of them. the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
发明原理Principle of invention
本发明利用关联规则挖掘获取故障间的关联关系，同时，本发明利用规则匹配寻找海量故障中的因果关系，先将原理和步骤详述如下：The present invention uses association rules to mine and obtain the association relationship between faults. At the same time, the present invention uses rule matching to find the causal relationship among massive faults. First, the principles and steps are described in detail as follows:
（1）对用户指定时间内高速列车发生的故障集进行关联规则挖掘，关联规则挖掘的方法（可参见陈京民编著，数据仓库原理、设计与应用，水利水电出版社，2004，）发现故障集内故障的因果关系，这一步具体包括：(1) Mining the association rules for the failure sets of high-speed trains within the specified time by the user, and the method of association rule mining (see Chen Jingmin, Principles, Design and Application of Data Warehouse, Water Conservancy and Hydropower Press, 2004,) to find faults in the fault set The causality of the fault, this step specifically includes:
1.1）对在用户所指定的时间段内的故障列表进行查询，提取在这一时间段内发生的故障及其故障代码，形成故障集，对故障集进行扫描，找到所有满足用户给定的最小支持度的频繁项目集；（最小支持度可参见陈京民编著，数据仓库原理、设计与应用，水利水电出版社，2004；）频繁项目集是指出现频率大于最小支持度的项集；在此，项目集则是包含了若干故障的集合。1.1) Query the fault list within the time period specified by the user, extract the faults and their fault codes that occurred within this time period, form a fault set, scan the fault set, and find all the minimum faults that meet the user's given requirements. Frequent itemsets of support; (Minimum support can be found in Chen Jingmin, Principles, Design and Application of Data Warehouse, Water Conservancy and Hydropower Press, 2004;) Frequent itemsets refer to itemsets whose occurrence frequency is greater than the minimum support; here, An item set is a collection of faults.
1.2）将（1.1）中获得的频繁项目集，组成故障模式集（即所有频繁项目集的集合），并根据故障模式集，生成关联规则，每条关联规则表示了故障间的因果关系1.2) Combine the frequent item sets obtained in (1.1) to form a failure mode set (that is, the set of all frequent item sets), and generate association rules based on the failure mode set, and each association rule represents the causal relationship between failures
（2）对（1）中所获得的关联规则集进行检查，获得合法的故障关联规则集。一个合法的故障关联规则集包含若干故障关联规则。每条关联规则的左子式为根源故障，右子式则为结果故障。(2) Check the association rule set obtained in (1) to obtain a legal fault association rule set. A legal set of fault association rules contains several fault association rules. The left sub-form of each association rule is the root fault, and the right sub-form is the result fault.
（3）将合法的故障关联规则集中的规则表示为一个有向无环的规则图。图中的每个节点代表高速列车的故障；有向边从一个根源故障中发出，指向一个结果故障。(3) Express the rules in the legal fault association rule set as a directed acyclic rule graph. Each node in the graph represents a fault of a high-speed train; directed edges emanating from a root fault point to a consequent fault.
（4）将用户提供的故障列表中高速列车出现的故障与规则图上的节点逐一进行比较，当规则图上某节点所代表的故障出现时，则该节点被匹配。规则图上的节点表示的是故障而不是代表一条规则。两个节点加上它们之间的有向边代表一条故障关联规则(4) Compare the faults of high-speed trains in the fault list provided by the user with the nodes on the rule graph one by one. When the fault represented by a node on the rule graph occurs, the node is matched. Nodes on the rule graph represent faults rather than a rule. Two nodes plus a directed edge between them represent a fault association rule
（5）根据节点匹配后的规则图，寻找所有节点均被匹配的路径。每条路径的入口节点即为根源故障。也就是说，从图中的叶子节点（入口节点）出发，寻找与其相连的被匹配的结点，直至找到图中的根结点（出口结点），此时便在规则图上找到了一条其上节点均被匹配的路径。(5) According to the rule graph after node matching, find the path where all nodes are matched. The entry node of each path is the root cause of failure. That is to say, starting from the leaf node (entry node) in the graph, looking for the matched node connected to it, until the root node (exit node) in the graph is found, at this time a rule graph is found The path on which all nodes are matched.
（6）对于所有在（5）中被找到的路径，计算各节点所代表故障的重要性。设P(v)为节点v的重要性，则P(v)=O(v)+L(v)。其中，O(v)为节点v在（3）所描述的规则图上的出度，图中一个节点的出度是指在图中从这个节点发出的有向边的数目，L(v)为节点v所在的（5）中寻找出的所有路径的长度的最大值。在步骤6)中可以获得图中每个节点的重要性P(v)；路径长度最大值是指节点v所在的若干路径的长度的最大值，是计算节点v重要性的一项，即L(v)(6) For all paths found in (5), calculate the importance of faults represented by each node. Let P(v) be the importance of node v, then P(v)=O(v)+L(v). Among them, O(v) is the out-degree of node v on the regular graph described in (3). The out-degree of a node in the graph refers to the number of directed edges sent from this node in the graph. L(v) is the maximum length of all paths found in (5) where node v is located. In step 6), the importance P(v) of each node in the graph can be obtained; the maximum path length refers to the maximum length of several paths where node v is located, and is an item for calculating the importance of node v, namely L (v)
（7）按（6）中所计算的各入口节点的重要性由高到低的顺序进行排序。维修时，优先修理重要性值高的根源故障。(7) Sort according to the importance of each entry node calculated in (6) from high to low. When repairing, give priority to repairing root faults with high importance values.
图1是给出了实施的具体流程。首先，用户（领域专家）给出需要关注故障的故障编码，并根据具体需要设置最小支持度等相关参数的值。（这些具体需要是从领域专家在高速列车维修中所积累的有关故障同时出现情况的经验中获取的）在此，最小支持度是指项集在给定的故障表中同时出现的次数。在此基础上，将这些设置的参数（最小支持度）以及给定的故障表中所有出现的故障作为输入，采用频繁项集挖掘算法Apriori算法，分析处理出所有频繁项目集。为方便起见，我们称这些频繁项目集的集合为故障模式集。Apriori算法的具体处理过程可参见文献Rakesh Agrawal,Ramakrishnan Srikant,“Fast Algorithms for Mining AssociationRules”,Proceedings ofthe 20th VLDB Conference,1994.。假设，此时所分析出的故障模式集为为{{f10,f12}，{f10,f22}，{f10,f23}，{f11，f10}，{f12，f6}，{f12,f10}，{f13，f29}，{f24，f11}，{f25,f11}}。各频繁项集的可置信度为0.93，0.97，0.65，1，0.61，1，1，1，1。其中，置信度是指故障A出现的同时故障B也出现的可能性。Figure 1 shows the specific process of implementation. First, the user (domain expert) gives the fault code of the fault that needs attention, and sets the value of the relevant parameters such as the minimum support according to the specific needs. (These specific needs are obtained from the experience of domain experts in the maintenance of high-speed trains about the simultaneous occurrence of faults.) Here, the minimum support refers to the number of times itemsets appear simultaneously in a given fault table. On this basis, the parameters (minimum support) of these settings and all the faults in the given fault table are used as input, and the frequent itemset mining algorithm Apriori algorithm is used to analyze and process all frequent itemsets. For convenience, we call the set of these frequent itemsets the failure mode set. The specific processing process of the Apriori algorithm can be found in the literature Rakesh Agrawal, Ramakrishnan Srikant, "Fast Algorithms for Mining Association Rules", Proceedings of the 20th VLDB Conference, 1994. Assume that the failure mode set analyzed at this time is {{f10, f12}, {f10, f22}, {f10, f23}, {f11, f10}, {f12, f6}, {f12, f10}, {f13, f29}, {f24, f11}, {f25, f11}}. The confidence levels of each frequent itemsets are 0.93, 0.97, 0.65, 1, 0.61, 1, 1, 1, 1. Among them, confidence refers to the possibility that fault B also occurs when fault A occurs.
对上述所获得的故障模式集中的各频繁项集进行分析，将各频繁项集中出现时间早的故障作为根源故障，将出现时间晚的故障作为结果故障，组成若干故障关联规则，频繁项集的置信度则可作为该故障关联规则为真的概率，从而获取故障间未知的关联关系。表1给出了所获得的故障关联规则。Analyze the frequent itemsets in the failure mode set obtained above, take the early faults in each frequent itemset as the root fault, and take the late faults as the result faults to form several fault association rules. The confidence degree can be used as the probability that the fault association rule is true, so as to obtain the unknown association relationship between faults. Table 1 presents the obtained fault association rules.
表1Table 1
分析表1中的各关联规则，将各关联规则中左子式的根源故障作为子节点，将右子式的结果故障作为父节点，从而将这些关联规则表示为如图2所示的规则图。假设此时高速列车维修人员所关注的故障为f25,f11,f10,f21，f23，f13以及f29，则此时在图2规则图中寻找到相应的被匹配的节点为f25,f11,f10,f21，f23，f13以及f29。在此基础上，在进行了匹配的规则图上，寻找由以上这些被匹配了的节点所组成的路径。在此，找到了如下的路径，即：f13→f29;f25→f11→f10→f21,f22,f23;f12→f06;f12→f10→f21,f22,f23。Analyze each association rule in Table 1, take the root fault of the left sub-form in each association rule as the child node, and use the result fault of the right sub-form as the parent node, so as to express these association rules as the rule graph shown in Figure 2 . Assuming that the faults that the high-speed train maintenance personnel are concerned about at this time are f25, f11, f10, f21, f23, f13 and f29, then the corresponding matched nodes found in the rule diagram in Figure 2 are f25, f11, f10, f21, f23, f13 and f29. On this basis, on the matched rule graph, search for a path composed of the above matched nodes. Here, the following paths are found, namely: f13→f29; f25→f11→f10→f21, f22, f23; f12→f06; f12→f10→f21, f22, f23.
根据所找到的路径以及图2所表示的规则图，计算各路径上各节点的重要性，可得，P(f13)=2;P(f29)=0;P(f25)=4;P(f24)=4;P(f11)=3;P(f12)=4;P(f10)=4;P(f6)=0;P(f21)=0;P(f22)=0;P(f23)=0。这样，对于所寻找到的每一条路径上的根源故障，即，f12,f13,f25来说，P(f25)>P(f12)>P(f13)。于是，维修时，将按照f25,f12和f13的顺序来进行修理。而对于同一条路径上的节点所表示的故障，则按照先修子节点所代表的故障，再修理父节点所代表的故障的顺序来进行。According to the path found and the rule graph shown in Figure 2, calculate the importance of each node on each path, P(f13)=2; P(f29)=0; P(f25)=4; P( f24)=4;P(f11)=3;P(f12)=4;P(f10)=4;P(f6)=0;P(f21)=0;P(f22)=0;P(f23 )=0. In this way, for the found root faults on each path, ie, f12, f13, f25, P(f25)>P(f12)>P(f13). Therefore, during maintenance, it will be repaired in the order of f25, f12 and f13. For the faults represented by the nodes on the same path, repair the faults represented by the child nodes first, and then repair the faults represented by the parent nodes.
上述实施例仅为例示性说明本发明的原理及其功效，而非用于限制本发明的范围。任何熟于此技术的本领域技术人员均可在不违背本发明的技术原理及精神下，对实施例作修改与变化。本发明的保护范围应以权利要求书所述为准。The above-mentioned embodiments are only illustrative to illustrate the principles and effects of the present invention, and are not intended to limit the scope of the present invention. Any person skilled in the art can modify and change the embodiments without violating the technical principle and spirit of the present invention. The scope of protection of the present invention should be defined by the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210428024.8ACN103793589B (en) | 2012-10-31 | 2012-10-31 | High-speed train fault handling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210428024.8ACN103793589B (en) | 2012-10-31 | 2012-10-31 | High-speed train fault handling method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103793589Atrue CN103793589A (en) | 2014-05-14 |
| CN103793589B CN103793589B (en) | 2017-01-18 |
Family
ID=50669251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210428024.8AExpired - Fee RelatedCN103793589B (en) | 2012-10-31 | 2012-10-31 | High-speed train fault handling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103793589B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104460651A (en)* | 2014-10-24 | 2015-03-25 | 北京交控科技有限公司 | ZC double-system downtime fault early-warning method and device based on autonomous learning |
| CN104777827A (en)* | 2015-01-21 | 2015-07-15 | 中国铁路总公司 | Method for diagnosing fault of high-speed railway signal system vehicle-mounted equipment |
| CN105045256A (en)* | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105868551A (en)* | 2016-03-28 | 2016-08-17 | 北京交通大学 | Fault association rule construction method |
| CN109358572A (en)* | 2018-09-26 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of machinery equipment O&M |
| CN110705597A (en)* | 2019-09-04 | 2020-01-17 | 中国科学院计算技术研究所 | Method and system for detection of network emergent events based on event causality extraction |
| CN116186106A (en)* | 2022-12-16 | 2023-05-30 | 国能铁路装备有限责任公司 | Railway freight car fault diagnosis method, device and equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101937447B (en)* | 2010-06-07 | 2012-05-23 | 华为技术有限公司 | Alarm association rule mining method, and rule mining engine and system |
| CN102111296A (en)* | 2011-01-10 | 2011-06-29 | 浪潮通信信息系统有限公司 | Mining method for communication alarm association rule based on maximal frequent item set |
| CN102638100B (en)* | 2012-04-05 | 2014-02-19 | 华北电力大学 | Correlation analysis and diagnosis method of abnormal alarm signal of regional power grid equipment |
- 2012
- 2012-10-31CNCN201210428024.8Apatent/CN103793589B/ennot_activeExpired - Fee Related
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104460651A (en)* | 2014-10-24 | 2015-03-25 | 北京交控科技有限公司 | ZC double-system downtime fault early-warning method and device based on autonomous learning |
| CN104777827A (en)* | 2015-01-21 | 2015-07-15 | 中国铁路总公司 | Method for diagnosing fault of high-speed railway signal system vehicle-mounted equipment |
| CN105045256A (en)* | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105045256B (en)* | 2015-07-08 | 2018-11-20 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on date comprision |
| CN105868551A (en)* | 2016-03-28 | 2016-08-17 | 北京交通大学 | Fault association rule construction method |
| CN109358572A (en)* | 2018-09-26 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of machinery equipment O&M |
| CN110705597A (en)* | 2019-09-04 | 2020-01-17 | 中国科学院计算技术研究所 | Method and system for detection of network emergent events based on event causality extraction |
| CN116186106A (en)* | 2022-12-16 | 2023-05-30 | 国能铁路装备有限责任公司 | Railway freight car fault diagnosis method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103793589B (en) | 2017-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103793589B (en) | High-speed train fault handling method | |
| Schoknecht et al. | Similarity of business process models—a state-of-the-art analysis | |
| Fleischhacker et al. | Mining RDF data for property axioms | |
| CN111930774B (en) | An automatic construction method and system for electric power knowledge graph ontology | |
| CN114138759B (en) | Secondary equipment fault processing push method and system based on knowledge graph reasoning | |
| CN105117771B (en) | A kind of agricultural machinery fault recognition method based on correlation rule directed acyclic graph | |
| Al-Bakri et al. | Inferring same-as facts from linked data: an iterative import-by-query approach | |
| CN117114102A (en) | Transformer fault diagnosis method based on Bayesian network and fault tree | |
| Chen | Data mining applications in e-government information security | |
| CN110134873B (en) | A Weibo Rumor Prediction Method Based on AHP | |
| CN109634949B (en) | Mixed data cleaning method based on multiple data versions | |
| CN114936307A (en) | A Normalized Graph Model Construction Method | |
| Liu et al. | Link prediction algorithm for signed social networks based on local and global tightness | |
| Mabrouk et al. | An efficient Bayesian network structure learning algorithm in the presence of deterministic relations | |
| Skandar et al. | An efficient duplication record detection algorithm for data cleansing | |
| Yang et al. | Temporal inductive logic reasoning | |
| Zhao et al. | Content-structural relation inference in knowledge base | |
| CN118210922A (en) | False news detection method based on graph roll-up network and attention mechanism | |
| Sun et al. | Abnormal entity-aware knowledge graph completion | |
| Niepert et al. | Probabilistic-logical web data integration | |
| Prasad | Optimized high-utility itemsets mining for effective association mining paper | |
| Wang et al. | A survey on data cleaning methods in cyberspace | |
| Li et al. | Text-Rich Graph Neural Networks With Subjective-Objective Semantic Modeling | |
| Luo et al. | An incremental feature selection approach based on information entropy for incomplete data | |
| Borate et al. | XML Duplicate Detection with Improved network pruning algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20170118 Termination date:20191031 |