CN110851656A

CN110851656A - Equipment fault diagnosis method and device based on bipartite graph

Info

Publication number: CN110851656A
Application number: CN201810828234.3A
Authority: CN
Inventors: 宋英豪; 杨杰; 黄建军
Original assignee: Ennew Digital Technology Co Ltd
Current assignee: Ennew Digital Technology Co Ltd
Priority date: 2018-07-25
Filing date: 2018-07-25
Publication date: 2020-02-28

Abstract

The invention discloses a device fault diagnosis method and device based on bipartite graph, the method includes: when at least one current abnormal phenomenon occurs in the target equipment, determining at least one current fault type triggering the at least one current abnormal phenomenon; forming a directed bipartite graph according to at least one current abnormal phenomenon and at least one current fault type; determining a condition probability table corresponding to each current abnormal phenomenon and each current fault type; and determining the current probability of each current fault type of the target equipment according to the directed bipartite graph, each current abnormal phenomenon and the conditional probability table corresponding to each current fault type. Through the technical scheme of the invention, the possibility of various fault types possibly occurring on the equipment can be measured according to one or more abnormal phenomena occurring on the equipment, so that a user can conveniently and quickly maintain the equipment with the fault by adopting a more targeted maintenance means.

Description

Equipment fault diagnosis method and device based on bipartite graph

Technical Field

The invention relates to the technical field of computers, in particular to a bipartite graph-based equipment fault diagnosis method and device.

Background

In order to maintain equipment (such as a gas boiler) in time when the equipment fails, the working parameters of the equipment are generally collected, and whether the equipment has an abnormal phenomenon or not is determined according to the collected working parameters, so that one or more types of possible faults of the equipment are determined according to the abnormal phenomenon of the equipment.

When different fault types occur to the equipment, the same change of working parameters of the equipment can be caused to trigger the equipment to generate the same abnormal phenomenon, but the influence degrees of the different fault types on the same abnormal phenomenon are possibly different, and when the different fault types occur to the equipment, different maintenance means are also needed to maintain the equipment; therefore, in order to facilitate a user to quickly perform maintenance on a failed device by using a more targeted maintenance means, how to measure the possibility of various failure types of the device according to one or more abnormal phenomena occurring in the device becomes a problem to be solved urgently.

Disclosure of Invention

The invention provides a bipartite graph-based equipment fault diagnosis method and device, which can measure the possibility of various fault types possibly occurring in equipment according to one or more abnormal phenomena occurring in the equipment, thereby facilitating a user to quickly maintain the equipment with faults by adopting a more targeted maintenance means.

In a first aspect, the present invention provides a bipartite graph-based device fault diagnosis method, including:

when at least one current abnormal phenomenon occurs in target equipment, determining at least one current fault type triggering the at least one current abnormal phenomenon;

forming a directed bipartite graph according to the at least one current abnormal phenomenon and the at least one current fault type;

determining a condition probability table corresponding to each current abnormal phenomenon and each current fault type respectively;

and determining the current probability of each current fault type of the target equipment according to the directed bipartite graph, each current abnormal phenomenon and a conditional probability table corresponding to each current fault type.

Preferably, the first and second electrodes are formed of a metal,

further comprising:

predetermining at least one sample fault type, and determining at least one sample abnormal phenomenon triggered correspondingly by each sample fault type;

forming a directed network according to the at least one sample fault type and the at least one sample abnormal phenomenon;

then the process of the first step is carried out,

forming a directed bipartite graph according to the at least one current anomaly and the at least one current fault type, including: and extracting a directed bipartite graph from the directed network according to the at least one current abnormal phenomenon and the at least one current fault type.

Preferably, the first and second electrodes are formed of a metal,

further comprising:

generating a conditional probability table corresponding to each sample fault type and each sample abnormal phenomenon in advance;

then the process of the first step is carried out,

the determining the conditional probability table corresponding to each current abnormal phenomenon and each current fault type respectively comprises: and determining a conditional probability table corresponding to each current abnormal phenomenon and each current fault type from the generated conditional probability tables.

Preferably, the first and second electrodes are formed of a metal,

the generating of the conditional probability table corresponding to each of the sample failure types and each of the sample anomalies respectively comprises:

determining obstacle probability values respectively corresponding to each sample fault type, and generating a conditional probability table respectively corresponding to each sample fault type according to the obstacle probability values respectively corresponding to each sample fault type;

determining at least one trigger condition corresponding to each sample abnormal phenomenon according to the directed network;

and for each sample abnormal phenomenon, determining a condition probability value of each current trigger condition corresponding to the sample abnormal phenomenon, and generating a condition probability table corresponding to the sample abnormal phenomenon according to the condition probability value of each current trigger condition.

Preferably, the first and second electrodes are formed of a metal,

further comprising:

periodically collecting the operating parameters of the target equipment at set time intervals;

and determining whether the target equipment generates at least one current abnormal phenomenon according to the acquired operation parameters.

In a second aspect, the present invention provides a bipartite graph-based device fault diagnosis apparatus, including:

the fault type determining module is used for determining at least one current fault type triggering at least one current abnormal phenomenon when the target equipment generates the at least one current abnormal phenomenon;

the bipartite graph construction module is used for forming a directed bipartite graph according to the at least one current abnormal phenomenon and the at least one current fault type;

a probability table determining module, configured to determine a conditional probability table corresponding to each of the current abnormal phenomena and each of the current fault types;

and the probability calculation module is used for determining the current probability of each current fault type of the target equipment according to the directed bipartite graph, each current abnormal phenomenon and the conditional probability table respectively corresponding to each current fault type.

Preferably, the first and second electrodes are formed of a metal,

further comprising: a sample selection module and a network construction module; wherein,

the sample selection module is used for predetermining at least one sample fault type and determining at least one sample abnormal phenomenon triggered correspondingly by each sample fault type;

the network construction module is used for forming a directed network according to the at least one sample fault type and the at least one sample abnormal phenomenon;

then the process of the first step is carried out,

the bipartite graph construction module is used for extracting the directed bipartite graph from the directed network according to the at least one current abnormal phenomenon and the at least one current fault type.

Preferably, the first and second electrodes are formed of a metal,

further comprising: a probability table generating module; wherein,

the probability table generating module is configured to generate in advance a conditional probability table corresponding to each of the sample failure types and each of the sample abnormalities;

then, the probability table determining module is configured to determine a conditional probability table corresponding to each of the current abnormal phenomena and each of the current failure types from the generated conditional probability tables.

Preferably, the first and second electrodes are formed of a metal,

the probability table generating module is specifically configured to execute the following steps:

Preferably, the first and second electrodes are formed of a metal,

further comprising: the device comprises a parameter acquisition module and an abnormality detection module; wherein,

the parameter acquisition module is used for periodically acquiring the operating parameters of the target equipment at set time intervals;

and the anomaly detection module is used for determining whether the target equipment generates at least one current anomaly phenomenon according to the acquired operation parameters.

The invention provides a device fault diagnosis method and a device based on a bipartite graph, wherein when at least one current abnormal phenomenon occurs in target equipment, one or more current fault types triggering the current abnormal phenomena are firstly determined, then a directed bipartite graph is formed according to various current abnormal phenomena and the determined current fault types, and after each current abnormal phenomenon and a condition probability table respectively corresponding to each current fault type are further determined, the current probability of each current fault type occurring in the target equipment can be determined according to the directed bipartite graph, each current abnormal phenomenon and the condition probability table respectively corresponding to each current fault type; the current probability can more objectively reflect the possibility of the target equipment generating the corresponding current fault type, namely the current probability can measure the possibility of the target equipment generating the corresponding current fault type, and a user can determine one or more current fault types which are most likely to occur to the target equipment according to the current probabilities respectively corresponding to the current fault types, so that the user can conveniently and rapidly maintain the equipment with the faults by adopting a more targeted maintenance means.

Drawings

In order to more clearly illustrate the embodiments or prior art solutions in the present specification, the drawings needed to be used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and it is obvious for a person skilled in the art to obtain other drawings based on these drawings without any creative effort.

Fig. 1 is a schematic flowchart of an apparatus fault diagnosis method based on a bipartite graph according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of another bipartite graph-based equipment fault diagnosis method according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an apparatus fault diagnosis device based on bipartite graph according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of another apparatus fault diagnosis device based on bipartite graph according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a directed network provided in an embodiment of the present invention;

FIG. 6 is a schematic diagram of a directed bipartite graph according to an embodiment of the invention;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

As shown in fig. 1, an embodiment of the present invention provides an apparatus fault diagnosis method based on a bipartite graph, including:

step 101, when at least one current abnormal phenomenon occurs in target equipment, determining at least one current fault type triggering the at least one current abnormal phenomenon;

102, forming a directed bipartite graph according to the at least one current abnormal phenomenon and the at least one current fault type;

step 103, determining a conditional probability table corresponding to each current abnormal phenomenon and each current fault type respectively;

and 104, determining the current probability of each current fault type of the target equipment according to the directed bipartite graph, each current abnormal phenomenon and the conditional probability table respectively corresponding to each current fault type.

As shown in fig. 1, when at least one current abnormal phenomenon occurs in a target device, the method determines one or more current fault types triggering the current abnormal phenomena, then forms a directed bipartite graph according to the various current abnormal phenomena and the determined various current fault types, and further determines a conditional probability table corresponding to each current abnormal phenomenon and each current fault type, and then determines a current probability of occurrence of each current fault type in the target device according to the directed bipartite graph, each current abnormal phenomenon, and the conditional probability table corresponding to each current fault type; the current probability can more objectively reflect the possibility of the target equipment generating the corresponding current fault type, namely the current probability can measure the possibility of the target equipment generating the corresponding current fault type, and a user can determine one or more current fault types which are most likely to occur to the target equipment according to the current probabilities respectively corresponding to the current fault types, so that the user can conveniently and rapidly maintain the equipment with the faults by adopting a more targeted maintenance means.

For example, when it is determined that the current abnormal phenomenon a occurs in the target device, in the conventional technical solution, only three current fault types, such as B1, B2, B3, which may occur in the target device, can be determined, by the technical solution provided in the embodiment of the present invention, on the basis of determining that the current fault type triggering the current abnormal phenomenon a includes B1, B2, and B3, it is further determined, according to the formed directed bipartite graph and the condition probability tables respectively corresponding to each current abnormal phenomenon and each current fault type, that the current probabilities respectively corresponding to B1, B2, and B3 are B1, B2, B3, B1, B2, and B3 can objectively reflect the possibility that the target device respectively occurs to B1, B2, and B3, and the user can determine one or more current fault types that the target device is most likely to occur according to the sizes of B1, B2, and B3; for example, the current fault type B1 corresponding to the current probability B1 with the largest numerical value is determined as the current fault type most likely to occur to the target device (or the current fault types corresponding to one or more current probabilities with numerical values larger than a preset threshold value are determined as the current fault type most likely to occur to the target device), and then the user may perform maintenance on the target device quickly by using a more targeted maintenance means with respect to the determined current fault type B1 most likely to occur to the target device.

Accordingly, based on the method provided by the embodiment of the invention, the time waste caused by the fact that the user maintains the target equipment by adopting the maintenance means corresponding to the failure type of the target equipment which does not occur can be avoided to a certain extent, so that the target equipment is prevented from being further damaged due to the fact that the target equipment which fails to be maintained timely and effectively.

In particular, target devices include, but are not limited to, gas boilers, gas pipelines, and other types of devices, and the methods provided by the various embodiments of the present invention are particularly applicable to gas boilers; when the method provided by the embodiment of the invention is implemented for the gas boiler, the number of nodes included in the formed directed bipartite graph is small, and when the current probability of each current fault type of the target equipment is determined according to the directed bipartite graph, each current abnormal phenomenon and the condition probability table respectively corresponding to each current fault type, each obtained current probability can more objectively reflect the possibility of the corresponding current fault type of the gas boiler.

Based on the embodiment shown in fig. 1, in a preferred embodiment of the present invention, the method further comprises:

step 100a, predetermining at least one sample fault type, and determining at least one sample abnormal phenomenon triggered correspondingly by each sample fault type;

step 100b, forming a directed network according to the at least one sample fault type and the at least one sample abnormal phenomenon;

then, the step 102 includes: and extracting a directed bipartite graph from the directed network according to the at least one current abnormal phenomenon and the at least one current fault type.

In this embodiment, a limited number of sample devices identical to the target device may be sampled and analyzed in advance to determine one or more sample fault types that may occur in the target device (taking the target device as a gas boiler, the sample fault types include, but are not limited to, long-time positive pressure combustion, imbalance of wind-fuel ratio, and insufficient combustion), and determine one or more sample abnormal phenomena (taking the target device as a gas boiler, the sample abnormal phenomena include, but are not limited to, too high smoke intensity, and imbalance of boiler pressure) that are triggered corresponding to each sample fault type, so that a directed network is formed according to the various sample fault types and the various sample abnormal phenomena; when fault diagnosis is carried out on specific target equipment in the subsequent process, the corresponding directed bipartite graph is extracted from the formed directed network only according to various current fault types and various current abnormal phenomena which may occur to the target equipment, the directed bipartite graph is not required to be reconstructed, the calculated amount can be reduced to a great extent, the corresponding directed bipartite graph can be obtained quickly, and resource consumption is reduced.

It should be noted that, when at least one current abnormal phenomenon occurs in the target device, the formed directed network may also be queried to determine at least one current fault type triggering the at least one current abnormal phenomenon.

Based on the foregoing embodiments, in an embodiment of the present invention, after forming a directed network according to at least one sample fault type and at least one sample anomaly, the method further includes:

step 100c, pre-generating a conditional probability table corresponding to each sample fault type and each sample abnormal phenomenon;

then, the step 103 includes: and determining a conditional probability table corresponding to each current abnormal phenomenon and each current fault type from the generated conditional probability tables.

In this embodiment, by generating in advance a condition probability table corresponding to each sample fault type and each sample abnormal phenomenon, when performing fault diagnosis on a specific target device in a subsequent process, a condition probability table corresponding to each current abnormal phenomenon and each current fault type may be determined from each generated condition probability table, and it is not necessary to reconstruct the condition probability tables corresponding to each current abnormal phenomenon and each current fault type, which may further reduce the amount of calculation, and may more quickly implement measurement of the possibility of occurrence of each current fault type on the target device, and further reduce resource consumption.

Specifically, in a possible implementation manner, the generating a conditional probability table corresponding to each of the sample failure types and each of the sample anomalies respectively includes:

In this implementation, a limited number of sample devices that are the same as the target device may be sampled and analyzed to determine the obstacle probability value corresponding to each sample fault type; specifically, the obstacle probability value refers to a proportion of all sample devices in a limited number of sample devices in which a corresponding sample fault type occurs, which should be recorded in a subsequently generated conditional probability table corresponding to the sample fault type, within a set time length.

In this implementation manner, determining at least one trigger condition corresponding to each sample abnormal phenomenon according to the directed network specifically means that, for a sample abnormal phenomenon, each subset (including an empty set) of a full set formed by various first sample fault types (i.e., the first sample fault types corresponding to the first sample abnormal phenomenon and nodes connected to the directed network and pointing to the nodes in the direction) that can trigger the sample device to generate the sample abnormal phenomenon is determined, where a meaning of any subset is specifically: the sample equipment generates all the second sample fault types contained in the subset, and any third sample fault type does not occur (the third sample fault type specifically refers to other first sample fault types except each second sample type in all the first sample fault types capable of triggering the sample abnormal phenomenon); correspondingly, the conditional probability value of each current trigger condition corresponding to the sample abnormal phenomenon is determined, and the conditional probability value can also be obtained by sampling and analyzing a limited number of sample devices.

The method provided by the implementation mode determines the condition probability tables respectively corresponding to each sample fault type and each sample abnormal phenomenon, compared with the method that the weight coefficient is directly defined for two sample fault types and sample abnormal phenomena with triggering relations, the method further considers the correlation influence of different sample fault types on the same sample abnormal phenomenon, and when the current probabilities respectively corresponding to each current fault phenomenon are determined according to the directed bipartite graph, each sample fault type and each sample abnormal phenomenon, each current probability can more accurately and objectively reflect the possibility of the corresponding current fault type of the target equipment.

Based on the foregoing embodiments, in order to continuously monitor the target device in operation, so that when the target device has a corresponding fault type, a user can timely and quickly perform maintenance on the faulty device by using a targeted maintenance means to ensure that the target device can operate more efficiently, an embodiment of the present invention further includes: periodically collecting the operating parameters of the target equipment at set time intervals; and determining whether the target equipment generates at least one current abnormal phenomenon according to the acquired operation parameters.

Taking a gas boiler as an example of equipment needing fault diagnosis, the method for diagnosing the fault of the equipment based on the bipartite graph is implemented for the gas boiler, and as shown in fig. 2, the method specifically includes the following steps:

step 201, sampling and analyzing a limited number of sample gas boilers to determine at least one sample fault type and at least one sample abnormal phenomenon correspondingly triggered by each sample fault type, and forming a directed network according to the at least one sample fault type and the at least one sample abnormal phenomenon.

As will be understood by those skilled in the art, the types of possible faults of the gas boiler include, but are not limited to, long-time positive pressure combustion, imbalance of the wind-fuel ratio, insufficient combustion, and possible abnormal phenomena of the gas boiler include, but are not limited to, too high smoke intensity, imbalance of the boiler pressure; for convenience of description in this embodiment, the sample abnormality determination that may occur to the gas boiler includes four types, i.e., S1, S2, S3, and S4, the sample failure types that may occur to the gas boiler include three types, i.e., F1, F2, and F3, and the examples include that S1, S2, and S3 may be triggered when the gas boiler generates F1, S2 and S4 may be triggered when the gas boiler generates F2, and S3 and S4 may be triggered when the gas boiler generates F3.

Accordingly, a directed network as shown in fig. 3 may be formed; in the directional network shown in the figure, F1, F2 and F3 are respectively used as a cause node, S1, S2, S3 and S4 are respectively used as a result node, and when a directional connecting line connecting the cause node and the result node represents a sample fault type represented by the cause node of the gas boiler, a sample abnormal phenomenon represented by the result node of the gas boiler which is in directional connection with the gas boiler may be triggered.

Step 202, determining at least one trigger condition corresponding to each sample abnormal phenomenon according to the formed directed network.

Based on the directed network as shown in fig. 3, it may be determined that the trigger condition corresponding to S1 includes: { F1} and empty set; the trigger conditions corresponding to S2 include: { F1}, { F2}, { F1, F2} and empty set; the trigger conditions corresponding to S3 include: { F1}, { F3}, { F1, F3} and empty set; the trigger conditions corresponding to S4 include: { F2}, { F3}, { F2, F3}, and null set.

Step 203, performing sampling analysis on a limited number of sample gas boilers to determine obstacle probability values respectively corresponding to each sample fault type and determine condition probability values of each current trigger condition respectively corresponding to each sample abnormal phenomenon.

It should be understood by those skilled in the art that the condition probability value corresponding to the trigger condition specifically refers to: for a trigger condition corresponding to a sample abnormal phenomenon, when the total amount of target sample gas boilers in all second sample fault types contained in the trigger condition and in which no third sample fault type occurs (the third sample fault type specifically means that in all first sample fault types capable of triggering the sample abnormal phenomenon, other first sample fault types except for all second sample types) in all sample gas boilers is m, the ratio between the total amount n of the sample gas boilers in which the sample abnormal phenomenon occurs in m target sample gas boilers is m.

As will be understood by those skilled in the art, the obstacle probability value corresponding to the sample fault type specifically refers to: and the target sample gas boilers of the corresponding sample fault types of the limited number of sample gas boilers in a set time period account for the proportion of all the sample gas boilers.

Step 204, generating a conditional probability table corresponding to each sample fault type according to the obstacle probability values corresponding to each sample fault type; and aiming at each sample abnormal phenomenon, generating a condition probability table corresponding to the sample abnormal phenomenon according to the condition probability value of each current trigger condition corresponding to the current sample abnormal phenomenon.

Here, the conditional probability table corresponding to the sample fault type should carry the obstacle probability value corresponding to the fault type, and for convenience of understanding, for example, the conditional probability tables corresponding to the sample fault types F1 and F2 are respectively generated, the conditional probability tables shown in tables 1 and 2 below may be generated, and the conditional probability table corresponding to F3 is similar to tables 1 and 2, and will not be described herein again.

TABLE 1

It should be understood that, in table 1, X1 is the probability value of the obstacle corresponding to F1, that is, the probability representing that the gas boiler generates F1 is X1, and the probability that the gas boiler does not generate F1 is 1-X1.

TABLE 2

Occurrence of F2	Probability of
		1 (occurrence)	X2
0 (not taking place)	1-X2

It should be understood that, in table 2, X2 is the probability value of the obstacle corresponding to F2, that is, the probability representing that the gas boiler generates F1 is X2, and the probability that the gas boiler does not generate F2 is 1-X2.

Meanwhile, taking the generation of the conditional probability tables corresponding to S1 and S2 as an example, the conditional probability tables shown in the following tables 3 and 4 may be generated, and the conditional probability tables corresponding to S3 and S4 are similar to the conditional probability table corresponding to S2, which is not repeated herein.

TABLE 3

	1(S1 generation)	0(S1 does not occur)
			1(F1 generation)	Y1	1-Y1
0(F1 not occurring)	Y2	1-Y2

It should be understood that, in table 3, Y1 is the conditional probability value of a trigger condition corresponding to S1, that is, when the gas boiler generates F1, the probability of the gas boiler generating S1 is Y1, and correspondingly, when the gas boiler generates F1, the probability value of the gas boiler not generating S1 is 1-Y1; y2 is a conditional probability value of another trigger condition corresponding to S1, that is, when the gas boiler does not generate F1, the probability of the gas boiler generating S1 is Y2, and correspondingly, when the gas boiler does not generate F1, the probability of the gas boiler not generating S1 is 1-Y2.

TABLE 4

		1(S2 generation)	0(S2 does not occur)
				1(F1 generation)	1(F2 generation)	Z1	1-Z1
1(F1 generation)	0(F2 not occurring)	Z2	1-Z2
				0(F1 not occurring)	1(F2 generation)	Z3	1-Z3
0(F1 not occurring)	0(F2 not occurring)	Z4	1-Z4

It should be understood that, in table 4, Z1 represents the conditional probability corresponding to the trigger condition { F1, F2}, that is, when the gas boiler simultaneously generates F1 and F2, the probability of the gas boiler generating S2 is Z1, and correspondingly, when the gas boiler simultaneously generates F1 and F2, the probability of the gas boiler not generating S2 is 1-Z1; z2 represents the conditional probability corresponding to the trigger condition { F1}, namely the probability that the gas boiler generates S2 is Z2 when the gas boiler generates F1 and does not generate F2, and correspondingly, the probability that the gas boiler does not generate S2 when the gas boiler generates F1 and does not generate F2 is 1-Z2; z3 represents the conditional probability corresponding to the trigger condition { F2}, namely the probability that the gas boiler generates S2 is Z3 when the gas boiler generates F2 and does not generate F1, and correspondingly, the probability that the gas boiler does not generate S2 when the gas boiler generates F2 and does not generate F1 is 1-Z3; z4 represents the conditional probability corresponding to the trigger condition null set, that is, when the gas boiler does not generate F1 and F2, the probability of the gas boiler generating S2 is Z4, and correspondingly, when the gas boiler does not generate F1 and does not generate F2, the probability of the gas boiler not generating S2 is 1-Z4.

Step 205, periodically collecting the operation parameters of the target gas boiler at set time intervals.

Here, the operation parameters of the gas filtering include, but are not limited to, any one or more of a flue gas concentration, an internal gas pressure, and a combustion temperature, so that whether the target gas boiler has abnormal phenomena such as too high flue gas gravity, boiler pressure imbalance, and the like can be determined according to the operation parameters, and for convenience of description, in the embodiment of the present invention, only the determination of the current abnormal phenomena occurring in the target gas boiler includes S2 as an example.

Step 206, determining whether the target gas-fired boiler generates at least one current abnormal phenomenon according to the collected operation parameters, and if so, executing step 207; otherwise, step 205 is performed.

Step 207, determining at least one current fault type triggering at least one current abnormal phenomenon according to the directed network.

It is apparent that, when the determined at least one current abnormality includes S2, it may be determined that at least one current fault type includes F1 and F2 according to the directed network as shown in the drawing.

And 208, extracting the directed bipartite graph from the formed directed network according to at least one current abnormal phenomenon and at least one current fault type.

Here, a directed bipartite graph as shown in fig. 4 can be extracted from the directed network as shown in the drawing.

Step 209 determines a conditional probability table corresponding to each current abnormal phenomenon and each current failure type from the generated conditional probability tables.

Here, the conditional probability tables shown in table 1, table 2, and table 4 above can be determined.

Step 210, determining the current probability of each current fault type of the target device according to the directed bipartite graph, each current abnormal phenomenon and the conditional probability table corresponding to each current fault type.

Specifically, bayesian inference can be performed on the basis of the directed bipartite graph shown in fig. 4 in conjunction with tables 1, 2 and 4 to calculate the current probabilities corresponding to F1 and F2, respectively.

In the subsequent process, the user can quickly maintain the target equipment by adopting a more targeted maintenance means according to the current probabilities respectively corresponding to F1 and F2; for example, when the current probability corresponding to F1 is greater than the current probability corresponding to F2, it indicates that the probability of the target gas boiler generating F1 is much higher than that of F2, and the user may first use the maintenance means corresponding to F1 to maintain the target gas boiler; otherwise, it indicates that the probability of the target gas equipment generating F2 is much higher than that of F1, and the user may first perform maintenance on the target gas equipment by using the maintenance means corresponding to F2.

Referring to fig. 5, based on the same concept as the method embodiment of the present invention, an embodiment of the present invention provides an apparatus for diagnosing a device fault based on a bipartite graph, including:

a fault type determining module 501, configured to determine, when at least one current abnormal phenomenon occurs in a target device, at least one current fault type that triggers the at least one current abnormal phenomenon;

a bipartite graph construction module 502, configured to form a directed bipartite graph according to the at least one current abnormal phenomenon and the at least one current fault type;

a probability table determining module 503, configured to determine a conditional probability table corresponding to each of the current abnormal phenomena and each of the current fault types;

a probability calculating module 504, configured to determine a current probability of each current fault type occurring to the target device according to the conditional probability tables respectively corresponding to the directed bipartite graph, each current abnormal phenomenon, and each current fault type.

Referring to fig. 6, in a preferred embodiment of the present invention, the apparatus further includes: a sample selection module 601 and a network construction module 602; wherein,

the sample selection module 601 is configured to determine at least one sample fault type in advance, and determine at least one sample abnormal phenomenon triggered by each sample fault type;

the network constructing module 602 is configured to form a directed network according to the at least one sample fault type and the at least one sample abnormal phenomenon;

then, the bipartite graph constructing module 502 is configured to extract a directed bipartite graph from the directed network according to the at least one current anomaly and the at least one current fault type.

Referring to fig. 6, in an embodiment of the present invention, the apparatus further includes: a probability table generating module 603; wherein,

the probability table generating module 603 is configured to generate in advance a conditional probability table corresponding to each of the sample failure types and each of the sample abnormal phenomena;

then, the probability table determining module 503 is configured to determine a conditional probability table corresponding to each of the current abnormal phenomena and each of the current failure types from the generated conditional probability tables.

In an embodiment of the present invention, the probability table generating module 603 is specifically configured to execute the following steps:

Referring to fig. 6, in a preferred embodiment of the present invention, the apparatus further includes: a parameter acquisition module 604 and an anomaly detection module 605; wherein,

the parameter collecting module 604 is configured to periodically collect the operating parameters of the target device at set time intervals;

the anomaly detection module 605 is configured to determine whether at least one current anomaly occurs in the target device according to the acquired operating parameters.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. On the hardware level, the electronic device comprises a processor and optionally an internal bus, a network interface and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 7, but this does not indicate only one bus or one type of bus.

And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.

In a possible implementation manner, the processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program, and the corresponding computer program can also be obtained from other equipment so as to form the bipartite graph-based equipment fault diagnosis device on a logic level. And the processor executes the program stored in the memory so as to realize the equipment fault diagnosis method based on the bipartite graph provided by any embodiment of the invention through the executed program.

The method executed by the bipartite graph-based equipment fault diagnosis device according to the embodiment shown in fig. 7 in the present specification can be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.

Embodiments of the present specification also propose a computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by an electronic device including a plurality of application programs, can cause the electronic device to perform the bipartite graph-based device fault diagnosis method provided in any embodiment of the present invention, and in particular to perform the method shown in fig. 1 and/or fig. 2.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units or modules by function, respectively. Of course, the functionality of the various elements or modules may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A device fault diagnosis method based on bipartite graph is characterized by comprising the following steps:

2. The method of claim 1, further comprising:

then the process of the first step is carried out,

3. The method of claim 2, further comprising:

then the process of the first step is carried out,

4. The method of claim 3,

5. The method of any of claims 1 to 4, further comprising:

6. An apparatus for diagnosing a failure of a device based on a bipartite graph, comprising:

7. The apparatus of claim 6,

then the process of the first step is carried out,

8. The apparatus of claim 7,

further comprising: a probability table generating module; wherein,

9. The apparatus of claim 8,

10. The apparatus of any one of claims 6 to 9,