CN114330138A - Fault diagnosis method and device and electronic equipment - Google Patents
Fault diagnosis method and device and electronic equipment Download PDFInfo
- Publication number
- CN114330138A CN114330138A CN202111679890.XA CN202111679890A CN114330138A CN 114330138 A CN114330138 A CN 114330138A CN 202111679890 A CN202111679890 A CN 202111679890A CN 114330138 A CN114330138 A CN 114330138A
- Authority
- CN
- China
- Prior art keywords
- fault
- node
- diagnosis
- nodes
- target
- 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.)
- Pending
Links
Images
Landscapes
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The application provides a fault diagnosis method, a fault diagnosis device and electronic equipment. The method comprises the following steps: acquiring characteristic parameters of a fault; inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data; acquiring a target fault type from a fault tree set as a target fault tree of child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons; diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result; and determining a fault reason corresponding to the fault according to the diagnosis result. The method combines the fault tree and the neural network, can realize the rapid and accurate positioning of the fault source, and enables maintenance personnel to find the fault in time and prevent the fault in the bud.
Description
Technical Field
The invention relates to the field of fault diagnosis, in particular to a fault diagnosis method, a fault diagnosis device and electronic equipment.
Background
With the development of economy and the continuous expansion of urban scale, high-rise residences, hotels, office buildings and the like are increased continuously, so that the quantity of electromechanical equipment of the building is increased more and more, wherein the total quantity of elevators in the whole country reaches 560 thousands at present.
The use of building electromechanical devices brings convenience to people to go in and out of high-rise buildings, but the problems of operation, maintenance and safety of the building electromechanical devices are more and more prominent. However, the number of technical practitioners of the building electromechanical equipment is not correspondingly increased, and the domestic building electromechanical equipment industry faces the dilemma of technical talent shortage, difficult debugging and difficult maintenance. At present, aiming at the treatment of the faults of the electromechanical equipment of the building, most maintenance personnel basically rely on own experience and product specifications, the faults are maintained through manual operation and thinking, and the maintenance efficiency is seriously dependent on the own technical ability and experience of the maintenance personnel. According to the conventional fault diagnosis condition of the building electrical system, the fault diagnosis condition is limited by the traditional concept and the technical level, most of the fault diagnosis conditions adopt a manual detection mode, the requirements on manpower, material resources and financial resources are high, and the accuracy of a detection result cannot be guaranteed. Although the existing fault technology of the building electromechanical equipment is continuously updated, the operation stability of the system is still influenced by various factors to cause faults in the overall view, and the diagnostic result is relatively low in accuracy and can provide limited help for fault processing. In addition, in the implementation of all fault diagnosis technologies, a part of algorithms cannot meet actual requirements, and certain influence is generated on the accuracy of a diagnosis result. In order to implement the fault diagnosis technology in place and improve the accuracy of the diagnosis result, the existing problems need to be optimized, and the appropriate fault diagnosis technology is selected according to the actual use condition of the building electromechanical equipment, so that the diagnosis result is ensured to have high accuracy and effectiveness.
Therefore, the intellectualization of the maintenance process of the building electromechanical equipment and the maintenance process of the building electromechanical equipment are urgent needs of the market of the building electromechanical equipment control products at present.
Disclosure of Invention
The present invention is directed to a fault diagnosis method, a device thereof, and an electronic apparatus, so as to solve the problems in the prior art.
In order to achieve the above object, according to one aspect of the present invention, there is provided a fault diagnosis method including: acquiring characteristic parameters of a fault; inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data; acquiring a target fault type from a fault tree set as a target fault tree of child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons; diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result; and determining a fault reason corresponding to the fault according to the diagnosis result.
Optionally, the method further includes: determining a plurality of logic rules corresponding to a plurality of fault reasons according to a plurality of fault types and a plurality of logical relations between the fault reasons; and establishing a fault tree according to a plurality of logic rules, wherein a plurality of fault types correspond to a plurality of first nodes, a plurality of fault reasons correspond to a plurality of second nodes, and the second nodes are child nodes of the first nodes.
Optionally, the plurality of first nodes include a failure large class node and a failure small class node, where the failure small class node is a child node of one failure large class node, and the failure large class node is a top event of a failure tree in the failure tree set.
Optionally, the fault categories include at least: elevator door failure, elevator inverter failure, elevator motor failure, and elevator operation failure.
Optionally, diagnosing the child nodes of the target fault tree according to a preset traversal order, including: traversing a target fault tree from a child node corresponding to the target fault type, and sequentially diagnosing a plurality of child nodes of the fault tree according to the diagnosis sequence from a parent node to the child nodes, wherein whether a first child node in the plurality of child nodes is abnormal or not is judged, and a first judgment result is generated; stopping diagnosis and determining a leaf node corresponding to the first child node under the condition that the first judgment result indicates yes, wherein the diagnosis result corresponding to the fault comprises a fault reason corresponding to the leaf node; and under the condition that the first judgment result indicates no, continuously traversing the target fault tree according to the diagnosis sequence until reaching a leaf node corresponding to the first child node, and stopping diagnosis.
Optionally, the diagnosing the child nodes of the target fault tree according to a preset traversal order further includes: determining a first brother node from at least one brother node of the first child node under the condition that the diagnosis reaches a leaf node corresponding to the first child node and the plurality of child nodes are judged to have no abnormality; and continuously traversing the target fault tree from the first brother node according to a preset traversing sequence.
Optionally, the method further includes: under the condition that the first judgment result indicates yes, storing the event corresponding to the first child node into an abnormal event library; and under the condition that the first judgment result indicates no, storing the event corresponding to the first child node into a normal event library.
According to another aspect of the present invention, there is also provided a fault diagnosis apparatus including: the first acquisition module is used for acquiring the characteristic parameters of the fault; the output module is used for inputting the characteristic parameters into the neural network model and outputting the target fault type, wherein the neural network model is obtained through training of multiple groups of data, and each group of data in the multiple groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data; a second obtaining module, configured to obtain a target fault type from the fault tree set as a target fault tree of child nodes, where the target fault tree includes multiple leaf nodes, and the multiple leaf nodes correspond to multiple fault reasons; the diagnosis module is used for diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result; and the determining module is used for determining a fault reason corresponding to the fault according to the diagnosis result.
According to another aspect of the present invention, there is also provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the fault diagnosis method as described above.
According to another aspect of the present invention, there is also provided a computer-readable storage medium, wherein instructions of the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the fault diagnosis method as described above.
The technical scheme of the invention is applied to provide a fault diagnosis method, the method firstly obtains characteristic parameters of faults, inputs the characteristic parameters into a neural network model and outputs a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of obtaining characteristic parameters of sample fault data and labels of fault types corresponding to the characteristic parameters for identifying the sample fault data, then obtaining a target fault tree with a target fault type as child nodes from a fault tree set, wherein the target fault tree comprises a plurality of leaf nodes, the leaf nodes correspond to a plurality of fault reasons, then diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result, and determining the fault reasons corresponding to the fault according to the diagnosis result, so that the fault tree and the intelligent diagnosis technology based on the neural network are combined, the method is based on the diagnosis of the neural network model according to the characteristics of the elevator system fault, and meanwhile, based on a knowledge-cause-effect framework of the fault tree model, the requirement of distributed diagnosis of operation of building electromechanical equipment is met, and the fault source can be quickly and accurately positioned, the method has the advantages that maintenance personnel can find faults in time, the faults are prevented in the bud, the fault rate of the building electromechanical equipment is reduced, the service life is prolonged, the sequencing of the detection and diagnosis process of the building electromechanical system is realized, the equipment recovery timeliness is greatly improved, and the operation guarantee capability of the building electromechanical equipment is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a block diagram illustrating a hardware configuration of a computer terminal for a fault diagnosis method according to an exemplary embodiment;
FIG. 2 is a block flow diagram illustrating a method of fault diagnosis in accordance with an exemplary embodiment;
FIG. 3 is a relational block diagram of a fault type according to embodiment 1 of the present invention;
FIG. 4 is a schematic diagram of a fault tree based on a door fault according to embodiment 1 of the present invention;
fig. 5 is a fault tree based on frequency converter/motor faults according to embodiment 1 of the present invention;
FIG. 6 is a schematic diagram of a fault tree based on operational faults according to embodiment 1 of the present invention;
fig. 7 is a relationship diagram of a fault tree based on an ascending method of a minimal cut set according to embodiment 1 of the present invention;
fig. 8 is an apparatus block diagram of a fault diagnosis method according to embodiment 2 of the present invention;
fig. 9 is an apparatus block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
The fault diagnosis method provided by the embodiment of the application can be executed in a mobile terminal, a computer terminal or a similar operation device. Fig. 1 shows a hardware configuration block diagram of a computer terminal (or electronic device) for implementing the fault diagnosis method. As shown in fig. 1, the computer terminal 10 (or electronic device 10) may include one or more (shown as 102a, 102b, … …, 102 n) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors 102 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or electronic device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).
The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the fault diagnosis method in the embodiment of the present application, and the processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the fault diagnosis method of the application program. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or electronic device).
It should be noted here that in some alternative embodiments, the computer device (or electronic device) shown in fig. 1 may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that fig. 1 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in the computer device (or electronic device) described above.
Under the operating environment, the application provides a fault diagnosis method as shown in fig. 2. It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Fig. 2 is a flowchart of a fault diagnosis method according to an embodiment of the present application, as shown in fig. 2, the method includes the following steps:
step S202, acquiring characteristic parameters of faults;
step S204, inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data;
step S206, a target fault type is obtained from the fault tree set and is used as a target fault tree of the child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons;
step S208, diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result;
and step S210, determining a fault reason corresponding to the fault according to the diagnosis result.
The method combines the intelligent diagnosis technology based on the fault tree and the neural network, diagnoses based on the neural network model according to the characteristics of the elevator system fault, and simultaneously meets the requirement of distributed diagnosis of the operation of the building electromechanical equipment based on the causal knowledge frame of the fault tree model, can realize the rapid and accurate positioning of a fault source, enables maintenance personnel to find the fault in time, prevents the fault from happening in the bud, reduces the fault rate of the building electromechanical equipment, prolongs the service life, realizes the programming of the detection and diagnosis process of the building electromechanical system, greatly improves the time efficiency of equipment recovery, and improves the operation guarantee capability of the building electromechanical equipment.
In the above step S202 of the present embodiment, the characteristic parameters of the fault are acquired. The characteristic parameter of the fault may be a parameter subjected to the fuzzy processing. And the symptom fuzzy vector obtained after the fuzzy processing is used as the input basis of the neural network.
The fuzzy processing function or the fuzzy membership function is determined by adopting an undetermined coefficient method and can be divided into two steps: 1) determining the form of the function according to the characteristic and the change rule of the diagnostic object; 2) running rules and running empirical adjustment functions. In practical application, the processing process can be simplified by adopting a segmented explicit fuzzy processing method.
In the above step S204 of the present embodiment, the characteristic parameters are input into the neural network model, and the target failure type is output. The forward reasoning of the neural network is a parallel reasoning and is realized by numerical calculation, thereby greatly improving the reasoning speed. Moreover, because the neural network adopts an implicit knowledge representation mode and is solved through neural calculation, the inference strategy completely avoids conflict.
The establishment of the neural network comprises two processes: acquisition of knowledge and storage of knowledge. The acquisition of knowledge is represented by the acquisition and selection of training samples, wherein the training samples are derived from various characteristic parameters of the same type of diagnostic objects during normal operation and fault operation.
Specifically, it can be assumed that the diagnostician system employs a three-layer BP neural network, and the numbers of neurons of the input layer, the hidden layer, and the output layer are L, M and N, respectively, and the forward reasoning process thereof can be described as follows:
calling into a fault diagnosis knowledge base;
calling in various fault symptom values { x1, x2, … and x L };
the output of the hidden layer neurons is calculated according to:
wherein i and j are the serial numbers of the neurons respectively,
a fixed value for the synaptic strength (the weight of the j-th hidden layer neuron connected to the i-th hidden layer neuron),
is the threshold for the ith neuron.
The output of the output layer neurons is calculated according to the following formula:
wherein i and j are the serial numbers of the neurons respectively,
is a fixed value for synaptic strength (the weight of the j-th output layer neuron connected with the i-th output layer neuron),
is the threshold for the ith neuron.
The output of the output neuron is determined by a given rule, such as:
from the algorithm, the forward reasoning of the neural network can well process the fuzzy input and the multi-fault diagnosis condition. For input and output modes, there may be three types of data, namely: real (or integer) data, user-defined symbolic data, and sets. The symbolic data and sets are coded into shaped data, such as 0 or 1, at the design time of the inference engine.
In one possible embodiment, the method further includes: determining a plurality of logic rules corresponding to a plurality of fault reasons according to a plurality of fault types and a plurality of logical relations between the fault reasons; and establishing a fault tree according to a plurality of logic rules, wherein a plurality of fault types correspond to a plurality of first nodes, a plurality of fault reasons correspond to a plurality of second nodes, and the second nodes are child nodes of the first nodes.
In the above embodiment, the plurality of first nodes include a failure major node and a failure minor node, where the failure minor node is a child node of one failure major node, and the failure major node is a top event of a failure tree in the failure tree set. The above-mentioned general categories of faults include at least: elevator door failure, elevator inverter and motor failure, and elevator operation failure. The events of each fault tree are packaged in an independent frame, which is beneficial to the maintenance and the updating of an event library, and only the frame related to the tree is started during diagnosis, thereby improving the reasoning speed.
Specifically, the system is structurally decomposed based on the working principle of the building electromechanical equipment system. The overall structure of the system is decomposed into a multi-level structure from the top layer to the components at the lowest level.
Taking the common special equipment elevator in the building electromechanical equipment as an example:
typical faults of elevators are divided into three main categories: i.e. door failure, inverter/motor failure, operational failure. The door faults mainly comprise door lock falling in operation, door closing but no starting of the elevator, door opening and closing resistance, door opening and closing speed non-speed change, door leaf vibration too strong and the like; the faults of the frequency converter and the motor mainly comprise main loop faults, auxiliary loop faults, overheating of radiating fins, overload of the motor and the like; the operation faults comprise operation faults and starting/braking faults, wherein the operation faults are divided into fault types of non-door-area parking or overlarge leveling error, scram faults, top-rushing or bottom-squatting faults, over-speed and under-speed, non-speed-changing when arriving at a station, overlarge noise and the like, and the starting/braking faults are divided into starting, braking, sliding faults and the like. The elevator fault classification is shown in fig. 3.
The fault tree is a directed tree, the premise of the generalized rule is a certain father node of the fault tree, and the conclusion of the generalized rule is a certain child node of the father node, so that the generalized rule is expressed as follows: (Rule n W)nIf (c) THEN ((AND, OR) (h) (i)), where n is a rule number; wnIs the weight of the rule; (c) is a prerequisite for the rule; (AND, OR) (h) (i) represents the conclusion of the rule, AND, OR represent the AND gate AND OR gate, respectively, on the fault tree.
Illustratively, on the basis of referring to the elevator company fault and maintenance manual, three fault trees are established for the three typical fault types, and the door fault, the frequency converter/motor fault and the operation fault are respectively used as the top event (namely the root node) of the tree, and the bottom event (namely the leaf node) is used as all fault reasons of the elevator. Fig. 4 to 6 are fault tree models of three typical types of faults of an elevator, respectively. The three fault trees shown in the figure have a total of 171 leaf nodes, i.e. fault causes. The reason is that thousands of faults have the most factors, and are not listed here. The No. 1-56 fault causes are fault causes of door faults, 56-85 fault causes of frequency converter/motor faults, and 86-171 fault causes of operation faults. The diagnosis comprehensiveness is achieved because all possible fault reasons on the maintenance manual are covered when the fault tree is established.
In the above step S206 and step S208 of this embodiment, the target fault type is obtained from the fault tree set as the target fault tree of the child node, and the child nodes of the target fault tree are diagnosed according to the preset traversal order, so as to obtain the diagnosis result.
In one possible embodiment, the diagnosing the child nodes of the target fault tree according to the preset traversal order includes: traversing a target fault tree from a child node corresponding to the target fault type, and sequentially diagnosing a plurality of child nodes of the fault tree according to the diagnosis sequence from a parent node to the child nodes, wherein whether a first child node in the plurality of child nodes is abnormal or not is judged, and a first judgment result is generated; stopping diagnosis and determining a leaf node corresponding to the first child node under the condition that the first judgment result indicates yes, wherein the diagnosis result corresponding to the fault comprises a fault reason corresponding to the leaf node; and under the condition that the first judgment result indicates no, continuously traversing the target fault tree according to the diagnosis sequence until reaching a leaf node corresponding to the first child node, and stopping diagnosis.
In the above embodiment, when it is judged that the leaf node corresponding to the first child node is reached by the diagnosis and it is judged that there is no abnormality in any of the plurality of child nodes, the first sibling node is determined from at least one sibling node of the first child node; and continuously traversing the target fault tree from the first brother node according to a preset traversing sequence.
Specifically, the fault tree model analysis includes qualitative analysis and quantitative analysis, and the purpose of the qualitative analysis is to find the cause and cause combination of the top event, that is, to identify all fault modes causing the top event to guide fault diagnosis, which can help to identify potential faults for guiding fault diagnosis. The task of the fault tree quantitative analysis is to calculate or estimate the probability of occurrence of a system top event. The top events of the fault tree are all common faults of the elevator, namely the occurrence probability is relatively large, and therefore only qualitative analysis is given.
Taking the example of simulating the elevator to have a fault, a fault tree model of a certain type of elevator system fault is researched.
The above fault tree model will be simplified below. The simplification mode is as follows: and (4) clearly showing the logical relationship between the fault reason and the fault phenomenon by searching all the minimal cut sets.
Take an operational failure as an example. Firstly, analyzing a fault tree of an operation fault, and finding a minimum cut set to obtain a first-order cut set of fault reasons. As shown in fig. 6, the bottom events (i.e., failure causes) of the operation failure are 86-171, and since the bottom events have mutual independence, each bottom event can be considered as a minimal cut set, that is, as long as one bottom event is established, a top event can be derived.
For example, the bottom events of a top-down or bottom-squat fault under an operational fault are, in order: 103. forced deceleration gastric loading failure, 104, position switch failure, 105, reduction in hoist rope diameter, 106, governor electrical switch failure, 107, governor mechanical switch failure. When any fault of 103-107 occurs, the fault of top rushing or bottom squating inevitably occurs.
For example, the algorithm model and principle of the fault tree in this embodiment is an ascending method of the minimal cut set (senandes algorithm), as shown in fig. 7.
R＝C∪D∪E，Q＝F∩G，P＝H∪I∪J，O＝K∪L∪M∪N，S＝A∪R＝A∪C∪D∪E，T＝Q∪P＝F∪G∪H∪I∪J，U＝B∪O＝B∪K∪L∪M∪N
Therefore, the following steps are carried out:
V＝S∪T∪U＝A∪C∪D∪E∪(F∩G)∪H∪I∪J∪B∪K∪L∪M∪N
therefore, the fault tree has 13 minimal cut sets, namely { A }, { B }, { C }, { D }, { E }, { F }, { G }, { H }, { I }, { J }, { K }, { L }, { M }, and { N }, and the 13 minimal cut sets constitute the weakest link of the fault tree top event. And according to the actual diagnosis condition, the 13 minimal cut sets basically and completely reflect the faults of the system in the model.
In this embodiment, the following five knowledge bases can be established:
1) each diagnosis rule is a reverse causal chain formed between a father node and a son node on the fault tree, the father node corresponds to the conclusion of the diagnosis rule, and the son node corresponds to the conclusion of the diagnosis rule;
2) the alarm rule base judges whether a certain node is abnormal or not according to the symptoms;
3) the abnormal event library is used for putting the node event into the abnormal event library if the alarm rule of a certain node on the fault tree is established;
4) if the alarm rule of a certain node on the fault tree is not established, the node event is put into a normal event library;
5) and an unknown event library, wherein if the symptom of a certain node on the fault tree is unknown, the node event is put into the unknown event library.
And adopting a depth-first search and forward and reverse mixed reasoning strategy. The reasoning process is started by a root node of a fault tree, when a plurality of nodes at the same level of a certain level are verified, forward reasoning forms an assumption in the child nodes of the node instead of verifying other nodes at the same level, and backtracking is generated only when all the child nodes are denied or the nodes are reasoned to leaf nodes. Therefore, based on the measured data and the standard data of each measuring point, a working level frame is started first, the working level frame starts an alarm rule base frame and a diagnosis rule base frame of the working level frame in sequence, the alarm rule base frame indicates whether the node is abnormal or not through a threshold value method, neural network reasoning and manual interaction, if the node is abnormal, the node enters the frame diagnosis rule base, the diagnosis rule base indicates that a certain II level frame is started through reasoning based on a fault tree, the reasoning process of the II level frame is the same as that of the I level frame, then the node enters a III level frame, and the node is sequentially reasoned until the last level frame, so that a fault source is found.
Example 2
According to an embodiment of the present application, there is also provided an apparatus for implementing the above fault diagnosis method, and fig. 8 is a block diagram of a structure of the fault diagnosis apparatus provided according to the embodiment of the present application, and as shown in fig. 8, the fault diagnosis apparatus includes: the fault diagnosis apparatus includes a first obtaining module 302, an output module 304, a second obtaining module 306, a diagnosis module 308, and a determination module 310, which are described below.
A first obtaining module 302, configured to obtain a characteristic parameter of a fault;
an output module 304, configured to input the feature parameters into a neural network model, and output a target fault type, where the neural network model is obtained through training of multiple sets of data, and each set of data in the multiple sets of data includes: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data;
a second obtaining module 306, configured to obtain a target fault type from the fault tree set as a target fault tree of the child nodes, where the target fault tree includes multiple leaf nodes, and the multiple leaf nodes correspond to multiple fault reasons;
the diagnosis module 308 is configured to diagnose the child nodes of the target fault tree according to a preset traversal order to obtain a diagnosis result;
and a determining module 310, configured to determine a failure cause corresponding to the failure according to the diagnosis result.
It should be noted here that the first acquiring module 302, the output module 304, the second acquiring module 306, the diagnosing module 308 and the determining module 310 correspond to steps S202 to S210 in embodiment 1, and the five modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in embodiment 1.
Example 3
Embodiments of the present application may provide an electronic device, which may be any one of computer terminal devices in a computer terminal group.
Optionally, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of a computer network.
Alternatively, fig. 9 is a block diagram illustrating a structure of an electronic device according to an example embodiment. As shown in fig. 9, the electronic device may include: one or more processors 401 (only one shown), a memory 402 for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement any of the fault diagnosis methods described above.
The memory may be configured to store software programs and modules, such as program instructions/modules corresponding to the fault diagnosis method and apparatus in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, so as to implement the fault diagnosis method. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: acquiring characteristic parameters of a fault; inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data; acquiring a target fault type from a fault tree set as a target fault tree of child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons; diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result; and determining a fault reason corresponding to the fault according to the diagnosis result.
Optionally, the processor may further execute the program code of the following steps: determining a plurality of logic rules corresponding to a plurality of fault reasons according to a plurality of fault types and a plurality of logical relations between the fault reasons; and establishing a fault tree according to a plurality of logic rules, wherein a plurality of fault types correspond to a plurality of first nodes, a plurality of fault reasons correspond to a plurality of second nodes, and the second nodes are child nodes of the first nodes.
Optionally, the processor may further execute the program code of the following steps: the plurality of first nodes comprise a fault large class node and a fault small class node, wherein the fault small class node is a child node of the fault large class node, and the fault large class node is a top event of a fault tree in the fault tree set.
Optionally, the processor may further execute the program code of the following steps: the major classes of faults include at least: elevator door failure, elevator inverter failure, elevator motor failure, and elevator operation failure.
Optionally, the processor may further execute the program code of the following steps: diagnosing the child nodes of the target fault tree according to a preset traversal sequence, wherein the diagnosis comprises the following steps: traversing a target fault tree from a child node corresponding to the target fault type, and sequentially diagnosing a plurality of child nodes of the fault tree according to the diagnosis sequence from a parent node to the child nodes, wherein whether a first child node in the plurality of child nodes is abnormal or not is judged, and a first judgment result is generated; stopping diagnosis and determining a leaf node corresponding to the first child node under the condition that the first judgment result indicates yes, wherein the diagnosis result corresponding to the fault comprises a fault reason corresponding to the leaf node; and under the condition that the first judgment result indicates no, continuously traversing the target fault tree according to the diagnosis sequence until reaching a leaf node corresponding to the first child node, and stopping diagnosis.
Optionally, the processor may further execute the program code of the following steps: diagnosing the child nodes of the target fault tree according to a preset traversal sequence, further comprising: determining a first brother node from at least one brother node of the first child node under the condition that the diagnosis reaches a leaf node corresponding to the first child node and the plurality of child nodes are judged to have no abnormality; and continuously traversing the target fault tree from the first brother node according to a preset traversing sequence.
Optionally, the processor may further execute the program code of the following steps: under the condition that the first judgment result indicates yes, storing the event corresponding to the first child node into an abnormal event library; and under the condition that the first judgment result indicates no, storing the event corresponding to the first child node into a normal event library.
Those of ordinary skill in the art will appreciate that the configuration shown in FIG. 9 is merely illustrative. Fig. 9 does not limit the structure of the electronic device. For example, it may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
Example 4
In an exemplary embodiment, there is also provided a computer-readable storage medium including instructions that, when executed by a processor of a terminal, enable the terminal to perform the fault diagnosis method of any one of the above. Alternatively, the computer readable storage medium may be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Alternatively, in this embodiment, the computer-readable storage medium may be used to store the program code executed by the fault diagnosis method provided in embodiment 1.
Optionally, in this embodiment, the computer-readable storage medium may be located in any one of a group of computer terminals in a computer network, or in any one of a group of mobile terminals.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: acquiring characteristic parameters of a fault; inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data; acquiring a target fault type from a fault tree set as a target fault tree of child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons; diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result; and determining a fault reason corresponding to the fault according to the diagnosis result.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining a plurality of logic rules corresponding to a plurality of fault reasons according to a plurality of fault types and a plurality of logical relations between the fault reasons; and establishing a fault tree according to a plurality of logic rules, wherein a plurality of fault types correspond to a plurality of first nodes, a plurality of fault reasons correspond to a plurality of second nodes, and the second nodes are child nodes of the first nodes.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the plurality of first nodes comprise a fault large class node and a fault small class node, wherein the fault small class node is a child node of the fault large class node, and the fault large class node is a top event of a fault tree in the fault tree set.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the major classes of faults include at least: elevator door failure, elevator inverter failure, elevator motor failure, and elevator operation failure.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: diagnosing the child nodes of the target fault tree according to a preset traversal sequence, wherein the diagnosis comprises the following steps: traversing a target fault tree from a child node corresponding to the target fault type, and sequentially diagnosing a plurality of child nodes of the fault tree according to the diagnosis sequence from a parent node to the child nodes, wherein whether a first child node in the plurality of child nodes is abnormal or not is judged, and a first judgment result is generated; stopping diagnosis and determining a leaf node corresponding to the first child node under the condition that the first judgment result indicates yes, wherein the diagnosis result corresponding to the fault comprises a fault reason corresponding to the leaf node; and under the condition that the first judgment result indicates no, continuously traversing the target fault tree according to the diagnosis sequence until reaching a leaf node corresponding to the first child node, and stopping diagnosis.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: diagnosing the child nodes of the target fault tree according to a preset traversal sequence, further comprising: determining a first brother node from at least one brother node of the first child node under the condition that the diagnosis reaches a leaf node corresponding to the first child node and the plurality of child nodes are judged to have no abnormality; and continuously traversing the target fault tree from the first brother node according to a preset traversing sequence.
Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: under the condition that the first judgment result indicates yes, storing the event corresponding to the first child node into an abnormal event library; and under the condition that the first judgment result indicates no, storing the event corresponding to the first child node into a normal event library.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, a division of a unit is merely a division of a logic function, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A fault diagnosis method, comprising:
acquiring characteristic parameters of a fault;
inputting the characteristic parameters into a neural network model, and outputting a target fault type, wherein the neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data;
acquiring the target fault type from a fault tree set as a target fault tree of child nodes, wherein the target fault tree comprises a plurality of leaf nodes, and the leaf nodes correspond to a plurality of fault reasons;
diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result;
and determining a fault reason corresponding to the fault according to the diagnosis result.
2. The method of claim 1, further comprising:
determining a plurality of logic rules corresponding to a plurality of fault reasons according to a plurality of fault types and logic relations between the plurality of fault reasons;
and establishing a fault tree according to the plurality of logic rules, wherein the plurality of fault types correspond to a plurality of first nodes, the plurality of fault reasons correspond to a plurality of second nodes, and the second nodes are child nodes of the first nodes.
3. The method of claim 2, wherein the plurality of first nodes includes a failed large class node and a failed small class node, wherein the failed small class node is a child node of the failed large class node, and wherein the failed large class node is a top event of a failure tree in the set of failure trees.
4. The method of claim 3, wherein the fault category includes at least: elevator door failure, elevator inverter failure, elevator motor failure, and elevator operation failure.
5. The method of claim 1, wherein the diagnosing the child nodes of the target fault tree according to the preset traversal order comprises:
traversing the target fault tree from a child node corresponding to the target fault type, and sequentially diagnosing a plurality of child nodes of the fault tree according to the diagnosis sequence from a parent node to the child nodes, wherein whether a first child node in the plurality of child nodes is abnormal or not is judged, and a first judgment result is generated;
stopping diagnosis and determining a leaf node corresponding to the first child node when the first judgment result indicates yes, wherein the diagnosis result corresponding to the fault comprises a fault reason corresponding to the leaf node;
and under the condition that the first judgment result indicates no, continuously traversing the target fault tree according to the diagnosis sequence until reaching a leaf node corresponding to the first child node, and stopping diagnosis.
6. The method of claim 5, wherein the diagnosing the child nodes of the target fault tree according to the predetermined traversal order further comprises:
determining a first brother node from at least one brother node of the first child node when the diagnosis reaches the leaf node corresponding to the first child node and the plurality of child nodes are judged to have no abnormality;
and continuously traversing the target fault tree from the first brother node according to the preset traversal sequence.
7. The method of claim 5, further comprising:
under the condition that the first judgment result indicates yes, storing the event corresponding to the first child node into an abnormal event library;
and under the condition that the first judgment result indicates no, storing the event corresponding to the first child node into a normal event library.
8. A failure diagnosis device characterized by comprising:
the first acquisition module is used for acquiring the characteristic parameters of the fault;
an output module, configured to input the feature parameters into a neural network model, and output a target fault type, where the neural network model is obtained through training of multiple sets of data, and each set of data in the multiple sets of data includes: the method comprises the steps of sampling fault data and a label used for identifying a fault type corresponding to the characteristic parameters of the sampling fault data;
a second obtaining module, configured to obtain a target fault tree of which the target fault type is a child node from a fault tree set, where the target fault tree includes multiple leaf nodes, and the leaf nodes correspond to multiple fault causes;
the diagnosis module is used for diagnosing the child nodes of the target fault tree according to a preset traversal sequence to obtain a diagnosis result;
and the determining module is used for determining a fault reason corresponding to the fault according to the diagnosis result.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the fault diagnosis method of any one of claims 1 to 7.
10. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the fault diagnosis method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679890.XA CN114330138A (en) | 2021-12-31 | 2021-12-31 | Fault diagnosis method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679890.XA CN114330138A (en) | 2021-12-31 | 2021-12-31 | Fault diagnosis method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330138A true CN114330138A (en) | 2022-04-12 |
Family
ID=81022119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111679890.XA Pending CN114330138A (en) | 2021-12-31 | 2021-12-31 | Fault diagnosis method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330138A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115048095A (en) * | 2022-08-12 | 2022-09-13 | 广东粤港澳大湾区硬科技创新研究院 | Expert system fault diagnosis program generation method |
| CN115865630A (en) * | 2023-02-28 | 2023-03-28 | 广东名阳信息科技有限公司 | Network equipment fault diagnosis method and system based on deep learning |
| CN116010886A (en) * | 2022-12-22 | 2023-04-25 | 航安云创科技(北京)有限公司 | Security monitoring method, device, electronic equipment and storage medium |
| CN116067432A (en) * | 2023-03-06 | 2023-05-05 | 南京市特种设备安全监督检验研究院 | Escalator variable working condition fault diagnosis method |
| CN116069544A (en) * | 2023-04-06 | 2023-05-05 | 卡斯柯信号(北京)有限公司 | Verification method and device for intelligent diagnosis of signal equipment faults |
| CN117193252A (en) * | 2023-09-28 | 2023-12-08 | 广东百德朗科技有限公司 | Intelligent building remote operation and maintenance method and device based on data platform and electronic equipment |
-
2021
- 2021-12-31 CN CN202111679890.XA patent/CN114330138A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115048095A (en) * | 2022-08-12 | 2022-09-13 | 广东粤港澳大湾区硬科技创新研究院 | Expert system fault diagnosis program generation method |
| CN116010886A (en) * | 2022-12-22 | 2023-04-25 | 航安云创科技(北京)有限公司 | Security monitoring method, device, electronic equipment and storage medium |
| CN116010886B (en) * | 2022-12-22 | 2023-09-12 | 航安云创科技(北京)有限公司 | Security monitoring method, device, electronic equipment and storage medium |
| CN115865630A (en) * | 2023-02-28 | 2023-03-28 | 广东名阳信息科技有限公司 | Network equipment fault diagnosis method and system based on deep learning |
| CN116067432A (en) * | 2023-03-06 | 2023-05-05 | 南京市特种设备安全监督检验研究院 | Escalator variable working condition fault diagnosis method |
| CN116069544A (en) * | 2023-04-06 | 2023-05-05 | 卡斯柯信号(北京)有限公司 | Verification method and device for intelligent diagnosis of signal equipment faults |
| CN117193252A (en) * | 2023-09-28 | 2023-12-08 | 广东百德朗科技有限公司 | Intelligent building remote operation and maintenance method and device based on data platform and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114330138A (en) | Fault diagnosis method and device and electronic equipment | |
| CN109102189B (en) | Electrical equipment health management system and method | |
| KR100976443B1 (en) | Home-network error prediction system and home-network fault estimation method | |
| CN107862052A (en) | A kind of fault case storehouse, fault tree and fault spectrum construction method | |
| CN109800127A (en) | A kind of system fault diagnosis intelligence O&M method and system based on machine learning | |
| CN106992994A (en) | A kind of automatically-monitored method and system of cloud service | |
| CN107770797A (en) | A kind of association analysis method and system of wireless network alarm management | |
| CN103926490B (en) | A kind of power transformer error comprehensive diagnosis method with self-learning function | |
| CN101833324A (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN112087445A (en) | Electric power Internet of things security vulnerability assessment method fusing business security | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| CN110895495A (en) | Human error analysis method, system, computer device and storage medium | |
| CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
| CN115170344A (en) | Intelligent processing method and device, medium and equipment for operation events of regulation and control system | |
| CN103049365A (en) | Monitoring and evaluating method for information and application resource operating states | |
| CN102929241B (en) | Safe operation guide system of purified terephthalic acid device and application of safe operation guide system | |
| CN109263650A (en) | Identify the method, apparatus and the vehicles of manpower intervention | |
| CN113242213A (en) | Power communication backbone network node vulnerability diagnosis method | |
| CN117310500A (en) | Battery state classification model construction method and battery state classification method | |
| CN115520741A (en) | Elevator operation monitoring and early warning method and system based on neural network and storage medium | |
| CN115438093A (en) | Power communication equipment fault judgment method and detection system | |
| CN113726559A (en) | Artificial intelligence network-based security analysis early warning model | |
| CN114385403A (en) | Distributed cooperative fault diagnosis method based on double-layer knowledge graph framework | |
| CN113807462A (en) | AI-based network equipment fault reason positioning method and system | |
| CN113934862A (en) | Community security risk prediction method, device, electronic equipment and medium |
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 |