CN116610906A - Equipment fault diagnosis method and device, computer equipment and storage medium thereof - Google Patents
Equipment fault diagnosis method and device, computer equipment and storage medium thereof Download PDFInfo
- Publication number
- CN116610906A CN116610906A CN202310414499.XA CN202310414499A CN116610906A CN 116610906 A CN116610906 A CN 116610906A CN 202310414499 A CN202310414499 A CN 202310414499A CN 116610906 A CN116610906 A CN 116610906A
- Authority
- CN
- China
- Prior art keywords
- sensors
- sensor
- equipment
- detected
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000004088 simulation Methods 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims description 95
- 230000005540 biological transmission Effects 0.000 claims description 57
- 238000004590 computer program Methods 0.000 claims description 40
- 230000001364 causal effect Effects 0.000 claims description 39
- 238000010586 diagram Methods 0.000 claims description 32
- 230000001419 dependent effect Effects 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 208000037408 Device failure Diseases 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000017525 heat dissipation Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a device fault diagnosis method, a device, computer equipment and a storage medium thereof, and relates to the technical field of device parameter analysis. The method comprises the following steps: acquiring actual configuration parameters of each sensor in equipment to be detected; based on actual configuration parameters of each sensor in the equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors; and carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph. The application can accurately determine the fault cause of the equipment to be detected based on the actual configuration parameters of the sensors in the equipment to be detected.
Description
Technical Field
The present application relates to the field of device parameter analysis technologies, and in particular, to a device fault diagnosis method, a device, a computer device, and a storage medium thereof.
Background
Along with the increasing production demands, the complexity of various devices is increased, which also leads to the increasing probability of problems occurring in the devices during application; in order to ensure that the equipment can continuously run, the fault reasons of the equipment need to be determined in time so as to ensure the timely maintenance of the equipment.
In the prior art, mechanical performance data of equipment are generally required to be collected, and fault reasons are analyzed according to the mechanical performance data; wherein the mechanical performance data refers to data exhibited by the mechanical layer of the device, and can comprise vibration of the device, noise of the device and the like.
However, the analysis method of the fault cause in the prior art has low accuracy, and the actual fault cause of the equipment cannot be fully known.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an apparatus fault diagnosis method, apparatus, computer device, and storage medium thereof, capable of accurately acquiring an actual cause of a fault of an apparatus to be detected.
In a first aspect, the present application provides a method for diagnosing a device failure. The method comprises the following steps:
acquiring actual configuration parameters of each sensor in equipment to be detected;
based on actual configuration parameters of each sensor in the equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors;
and carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
In one embodiment, based on the configured target sensor dependency graph, predicting a failure cause of the device to be detected includes:
judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through a fault detection model;
if yes, predicting at least one fault reason corresponding to the equipment to be detected based on the configured target sensor dependency graph through a fault reason prediction network;
and generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
In one embodiment, the process of generating the target sensor dependency graph includes:
inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors; the input time of the observation signals of the sensors is different;
determining importance weights of the sensors and actual dependency relations among the sensors according to observation signals of the sensors and transmission results of the observation signals among the sensors;
and generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
In one embodiment, determining importance weights of the sensors according to the observation signals and transmission results of the observation signals among the sensors includes:
determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signals of each sensor and the transmission result of the observation signals among the sensors through a self-attention model;
and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
In one embodiment, determining the actual dependency relationship between the sensors according to the observation signals and the transmission results of the observation signals between the sensors includes:
based on the transmission result of the observation signal among the sensors, determining the dependence path of the observation signal among the sensors and the dependence value between the two sensors connected by the dependence path;
and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
In one embodiment, determining importance weights for each sensor based on the query vector matrix, the key vector matrix, and the value vector matrix corresponding to each sensor includes:
Determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor;
importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
In a second aspect, the application further provides a device fault diagnosis device. The device comprises:
the acquisition module is used for acquiring actual configuration parameters of each sensor in the equipment to be detected;
the configuration module is used for configuring simulation configuration parameters of each sensor in the target sensor dependency graph of the equipment to be detected based on the actual configuration parameters of each sensor in the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors;
and the diagnosis module is used for carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the device fault diagnosis method of any of the embodiments of the first aspect described above when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the apparatus failure diagnosis method of any of the embodiments of the first aspect described above.
In a fifth aspect, the present application also provides a computer program product. A computer program product comprising a computer program which, when executed by a processor, implements a device fault diagnosis method as in any of the embodiments of the first aspect described above.
According to the equipment fault diagnosis method, the equipment fault diagnosis device, the computer equipment and the storage medium thereof, the target sensor dependency graph of the simulation configuration parameters of each sensor is configured according to the actual configuration parameters of each sensor in the equipment to be detected, and then the equipment to be detected is subjected to fault diagnosis according to the target sensor dependency graph; because the simulation configuration parameters of each sensor in the target sensor dependency graph correspond to the actual configuration parameters of each sensor in the equipment to be detected, when the equipment to be detected is subjected to fault diagnosis, the actual running state of the equipment to be detected can be simulated according to the target sensor dependency graph, and the fault diagnosis result of the equipment to be detected can be determined; in the process of carrying out fault diagnosis on the equipment to be detected according to the target sensor dependency graph, mechanical performance data of the equipment to be detected is not needed, and the fault cause of the equipment to be detected can be accurately determined based on actual configuration parameters of each sensor in the equipment to be detected when the equipment to be detected is subjected to fault diagnosis.
Drawings
FIG. 1 is an application environment diagram of a device fault diagnosis method in one embodiment;
FIG. 2 is a flow chart of an apparatus fault diagnosis provided in an embodiment of the present application;
FIG. 3 is a flowchart of determining a fault diagnosis result of a device to be detected according to an embodiment of the present application;
FIG. 4 is a closed-loop diagram of causal relationship of a fault cause according to an embodiment of the present application;
FIG. 5 is a flow chart of generating a target sensor dependency graph according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a sensor transmission relationship according to an embodiment of the present application;
FIG. 7 is a schematic diagram of logic for determining importance weights according to an embodiment of the present application;
FIG. 8 is a flowchart illustrating steps of another method for diagnosing a device failure according to an embodiment of the present application;
fig. 9 is a block diagram of a first device fault diagnosis apparatus according to an embodiment of the present application;
fig. 10 is a block diagram of a second device fault diagnosis apparatus according to an embodiment of the present application;
fig. 11 is a block diagram of a third device fault diagnosis apparatus according to an embodiment of the present application;
fig. 12 is a block diagram of a fourth apparatus for diagnosing a device failure according to an embodiment of the present application;
fig. 13 is a block diagram of a fifth apparatus for diagnosing a device failure according to an embodiment of the present application;
Fig. 14 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. In the description of the present application, a description of the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Based on the above situation, the device fault diagnosis method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in FIG. 1. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing acquired data of the device fault diagnosis method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a device fault diagnosis method.
The application discloses a device fault diagnosis method, a device, computer equipment and a storage medium thereof.
In one embodiment, as shown in fig. 2, fig. 2 is a flowchart of an apparatus fault diagnosis provided by an embodiment of the present application, and an apparatus fault diagnosis method is provided, where the apparatus fault diagnosis method performed by the computer apparatus in fig. 1 may include the following steps:
step 201, obtaining actual configuration parameters of each sensor in the device to be detected.
It should be noted that, the actual configuration parameters are used to indicate one or more configuration parameters corresponding to each functional component in the operation process of the device to be detected, and the types of sensors corresponding to different functional components in the device to be detected are different, and the types of the sensors are also different due to the different types of the sensors.
For example, if the functional component in the device to be detected is a heating component, the sensor type corresponding to the heating component is a thermal sensor, and thus the actual configuration parameter type corresponding to the thermal sensor is a temperature parameter. Or if the functional component in the equipment to be detected is a motor component, the sensor type corresponding to the motor component is a voltage sensor, so that the actual configuration parameter type corresponding to the voltage sensor is a voltage parameter.
Further, in order to ensure that the actual configuration parameters of each sensor in the equipment to be detected can be successfully obtained, when the sensors are set for different functional components in the equipment to be detected, the sensors with the wireless transmitting devices can be preselected, so that when the actual configuration parameters of each sensor in the equipment to be detected need to be obtained, the actual configuration parameters corresponding to each sensor can be analyzed by receiving signals fed back by each sensor with the wireless transmitting devices.
Step 202, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of equipment to be detected based on actual configuration parameters of each sensor in the equipment to be detected; the target sensor dependency graph includes sensors configured with importance weights, and actual dependency relationships between the sensors.
It should be noted that, because the sensors included in the target sensor dependency graph correspond to the sensors in the to-be-detected device, after determining the actual configuration parameters of the sensors in the to-be-detected device, the simulation configuration parameters of the sensors in the target sensor dependency graph are set according to the corresponding relationship between the sensors in the target sensor dependency graph and the sensors in the to-be-detected device, so as to ensure that the simulation configuration parameters of the sensors in the target sensor dependency graph are the same as the actual configuration parameters of the corresponding sensors in the to-be-detected device.
For example, if the device to be detected includes three sensors, namely, a sensor a, a sensor B and a sensor C, and the target sensor dependency graph includes a sensor a corresponding to the sensor a, a sensor B corresponding to the sensor B and a sensor C corresponding to the sensor C; the actual configuration parameters corresponding to the sensor A, the sensor B and the sensor C of the equipment to be detected are as follows: parameter m, parameter n and parameter q; therefore, when configuring the simulation configuration parameters of each sensor in the target sensor dependency graph of the device to be detected based on the actual configuration parameters of each sensor in the device to be detected: since the sensor a corresponds to the sensor a and the actual configuration parameter of the sensor a is the parameter m, the simulation configuration parameter of the sensor a of the target sensor dependency graph is also set as the parameter m; since the sensor B corresponds to the sensor B and the actual configuration parameter of the sensor B is the parameter n, the simulation configuration parameter of the sensor B of the target sensor dependency graph is also set as the parameter n; since the sensor C corresponds to the sensor C and the actual configuration parameter of the sensor C is the parameter q, the simulation configuration parameter of the sensor C of the target sensor-dependent graph is also set as the parameter q.
Further, to ensure that the target sensor dependency graph includes importance weights of the sensors and actual dependency relationships between the sensors, fault diagnosis can be performed on the device to be detected according to the target sensor dependency graph, so generating the target sensor dependency graph may include the following:
and inputting observation signals to each sensor in the equipment to be detected, determining a dependent path between the sensors and a dependent value between two sensors connected with each dependent path, and determining an actual dependent relationship between the sensors according to the dependent path between the sensors and the dependent value between the two sensors connected with each dependent path. And determining a corresponding attention distribution matrix of each sensor through the input time of the observation signal and the transmission result of the observation signal among the sensors; and determining importance weights of the sensors according to the attention distribution matrixes corresponding to the sensors. And generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
And 203, performing fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
The fault diagnosis includes: judging whether the equipment to be detected has faults or not, and determining the fault reason of the equipment to be detected.
Specifically, when performing fault diagnosis on the equipment to be detected, the method comprises the following steps: inputting the configured target sensor dependency graph into a pre-trained fault detection model to obtain an output result of the fault detection model, and judging whether the equipment to be detected has faults or not according to the output result; if the equipment to be detected has no fault, stopping fault diagnosis of the equipment to be detected, and determining that the fault diagnosis result of the equipment to be detected is no fault; if the equipment to be detected has faults, inputting the configured target sensor dependency graph into a pre-trained fault cause prediction network to obtain a causal relationship closed loop graph corresponding to the fault cause of the equipment to be detected, wherein the causal relationship closed loop graph corresponding to the fault cause of the equipment to be detected is a fault diagnosis result of the equipment to be detected.
Further, the pre-trained fault detection model can be trained based on the historical sensor dependency graph of the equipment to be detected and the situation that whether the historical sensor dependency graph corresponds to the equipment to be detected fails or not, so that the fault detection model which can determine whether the equipment to be detected fails or not through inputting the target sensor dependency graph of the equipment to be detected is obtained.
Further, the pre-trained fault cause prediction network can train based on the historical sensor dependency graph of the equipment to be detected and the causal relation of the historical sensor dependency graph corresponding to the fault cause of the equipment to be detected, so as to obtain the fault cause prediction network by inputting the target sensor dependency graph of the equipment to be detected and outputting the causal relation closed-loop graph corresponding to the fault cause of the equipment to be detected.
According to the equipment fault diagnosis method, according to the actual configuration parameters of the sensors in the equipment to be detected, the target sensor dependency graph of the simulation configuration parameters of the sensors is configured, and then fault diagnosis is carried out on the equipment to be detected according to the target sensor dependency graph; because the simulation configuration parameters of each sensor in the target sensor dependency graph correspond to the actual configuration parameters of each sensor in the equipment to be detected, when the equipment to be detected is subjected to fault diagnosis, the actual running state of the equipment to be detected can be simulated according to the target sensor dependency graph, and the fault diagnosis result of the equipment to be detected can be determined; in the process of carrying out fault diagnosis on the equipment to be detected according to the target sensor dependency graph, mechanical performance data of the equipment to be detected is not needed, and the fault cause of the equipment to be detected can be accurately determined based on actual configuration parameters of each sensor in the equipment to be detected when the equipment to be detected is subjected to fault diagnosis.
Before determining the failure cause of the equipment to be detected, judging whether the equipment to be detected fails, if so, determining the failure cause of the equipment to be detected, wherein the failure cause of the equipment to be detected is more, so that the operation difficulty is higher when determining the failure cause of the equipment to be detected, and the failure cause of the equipment to be detected cannot be accurately judged; therefore, the terminal of this embodiment may determine whether the device to be detected has a fault in a manner shown in fig. 3, and determine a fault diagnosis result of the device to be detected, and specifically includes the following steps:
step 301, start.
Step 302, judging whether the equipment to be detected has a fault or not based on the configured target sensor dependency graph through the fault detection model, if not, executing step 303, and if so, executing step 304.
When judging whether the equipment to be detected has faults, the configured target sensor dependency graph can be input into a fault detection model, and the fault detection model can predict whether the equipment to be detected has faults according to the input configured target sensor dependency graph and output a prediction result; and determining the fault condition of the equipment to be detected according to the prediction result.
The training process of the fault detection model may include the following: acquiring a history sensor dependency graph configured based on history configuration parameters of equipment to be detected in advance, and determining whether equipment to be detected corresponding to each history sensor dependency graph has a fault or not; and training the candidate detection models by taking the historical sensor dependency graphs and the condition of whether the to-be-detected equipment corresponding to each historical sensor dependency graph is faulty as a training sample, and obtaining the trained fault detection model by carrying out parameter adjustment on the candidate detection models.
In one implementation manner of the application, whether the equipment to be detected has faults or not can be judged according to the predictor, specifically, the configured target sensor dependency graph is input into the predictor, and the predictor can perform fault analysis according to simulation configuration parameters of each sensor in the configured target sensor dependency graph, so as to determine whether the equipment to be detected has faults or not. It is understood that the predictor and the fault detection module are both the same function.
Step 303, determining that the fault diagnosis result of the device to be detected is fault-free.
It should be noted that, if the device to be detected has no fault, it means that the device to be detected does not need to predict the cause of the subsequent fault, so that the fault-free device can be directly used as the fault diagnosis result of the device to be detected.
And step 304, predicting at least one fault cause corresponding to the equipment to be detected based on the configured target sensor dependency graph through the fault cause prediction network.
When predicting at least one fault reason corresponding to the device to be detected, the configured target sensor dependency graph may be input to the fault reason prediction network, and the fault reason prediction network may output at least one fault reason corresponding to the device to be detected according to the configured target sensor dependency graph.
In one embodiment of the present application, by inputting the configured target sensor dependency graph to the failure cause prediction network, the failure cause prediction network may output at least one failure cause corresponding to the device to be detected and an accurate probability corresponding to each failure cause.
The training process of the failure cause prediction network may include the following contents: acquiring a history sensor dependency graph configured based on history configuration parameters of equipment to be detected in advance, and determining fault reasons of the equipment to be detected corresponding to each history sensor dependency graph; and training the candidate reason prediction network by taking the historical sensor dependency graphs and the fault reasons of the equipment to be detected corresponding to the historical sensor dependency graphs as training samples, and obtaining the trained fault reason prediction network by carrying out parameter adjustment on the candidate reason prediction network.
And 305, generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
It should be noted that, there is a causal relationship between the partial fault reasons of the device to be detected, and by using the causal relationship between the fault reasons, a causal relationship closed loop diagram corresponding to each fault reason can be generated according to the fault reason of the device to be detected.
As an example, the causal relationship of the cause of the equipment failure to be detected may be as follows: if the failure cause of the system to be detected is that the heat dissipation system does not work and the temperature of the motor is too high, wherein the cause of the motor temperature being too high is that the heat dissipation system does not pass, the causal relationship of the failure cause of the equipment to be detected can be determined as that the heat dissipation system does not work and the temperature of the motor is too high, so that the equipment to be detected fails.
In one embodiment of the present application, if the cause of the failure of the device to be detected includes: the heat dissipation system does not work, the motor temperature is too high, the motor voltage is insufficient, and the motor output power is insufficient; according to the causal relationship between the fault reasons, it can be determined that the failure of the heat dissipation system is the reason for the excessive temperature of the motor, and the insufficient voltage of the motor is the reason for the insufficient output power of the motor, so that the causal relationship closed-loop diagram corresponding to the fault reason of the equipment to be detected can be determined as shown in fig. 4.
In another embodiment of the application, when the fault cause prediction network is trained, a historical sensor dependency graph configured based on the historical configuration parameters of the equipment to be detected can be used for determining a causal relationship closed-loop graph of the equipment to be detected corresponding to each historical sensor dependency graph, the causal relationship closed-loop graph of the equipment to be detected corresponding to each historical sensor dependency graph and the historical sensor dependency graph are used as training samples, and the candidate cause prediction model is trained, so that parameter adjustment is carried out on the candidate cause prediction model, and the fault cause prediction model is obtained; therefore, if the equipment to be detected is determined to be faulty, the configured target sensor dependency graph is input into the fault cause prediction model, and then the causal relationship closed-loop graph corresponding to the fault cause of the equipment to be detected, which is output by the fault cause prediction model, can be obtained.
According to the equipment fault diagnosis method, whether the equipment to be detected has faults or not is predicted through the fault detection model, and the fault reason of the equipment to be detected which has faults is predicted through the fault prediction network, so that the accurate fault reason prediction of the equipment to be detected based on the configured target sensor dependency graph is ensured, and the fault detection accuracy of the equipment to be detected and the fault reason prediction accuracy of the equipment to be detected are ensured.
By collecting the mechanical performance data of the equipment to be detected, when the equipment to be detected is subjected to fault cause analysis, the mechanical performance data cannot fully and accurately reflect the actual running condition of the equipment to be detected, so that the accuracy of the obtained fault cause is lower when the equipment to be detected is subjected to fault cause analysis according to the mechanical performance data; based on this, the terminal of the present embodiment may generate the target sensor dependency graph in a manner as shown in fig. 5, and specifically includes the following steps:
step 501, inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors. And the input time of the observation signals of the sensors is different.
When an observation signal is input to a certain sensor in the device to be detected, the observation signal is transmitted to other sensors through a dependent path connected to the other sensor by the certain sensor, and a difference in a dependent value between two sensors connected to each dependent path may cause a change in a transmission result after transmission with respect to the observation signal. Therefore, by acquiring the transmission result of the observation signal after being transmitted among the sensors, the importance weight of each subsequent sensor and the determination of the actual dependency relationship among the sensors are realized.
In one embodiment of the present application, when a transmission result of an observation signal after transmission between the sensors is required to be obtained, after the observation signal is input to a sensor in the device to be detected, whether signal output exists in other sensors in the device to be detected is observed, and if so, the signal output is used as the transmission result of the observation signal after transmission between the sensors.
Step 502, determining importance weights of the sensors and actual dependency relations among the sensors according to observation signals of the sensors and transmission results of the observation signals among the sensors.
It should be noted that, determining the actual dependency relationship between the sensors may include the following steps: based on the transmission result of the observation signal among the sensors, determining the dependence path of the observation signal among the sensors and the dependence value between the two sensors connected by the dependence path; and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
In one embodiment of the present application, after an observation signal is input to a certain sensor in the device to be detected, the observation signal is transmitted to other sensors through a dependent path connected to the other sensor by the certain sensor, so that a dependent path existing between the certain sensor and the other sensors can be determined by determining a sensor that receives a transmission result after the observation signal is input to the sensor, and a dependent value between the two sensors can be determined by performing a ratio operation between the transmission result and the observation signal.
The range of the dependency value between the two sensors is [0,1], which means that if the dependency value between the two sensors is 1, the observation signal can be completely transmitted between the two sensors without change; if the dependency value between the two sensors is 0, this indicates that the observation signal cannot be transmitted between the two sensors.
For example, as shown in fig. 6, after the observation signal a is input to the sensor a, a transmission result B of the observation signal transmitted between the sensors is obtained from the sensor B; therefore, it can be determined that there is a dependent path between the sensor a and the sensor B, but there is no dependent path between the sensor a and the sensor C, and the signal value of the transmission result B is determined to be 0.5, and the signal value of the observation signal a is determined to be 1, and then the ratio operation is performed according to the transmission result B and the observation signal a, so that it can be determined that the dependent value between the two sensors is 0.5/1=0.5.
Wherein the actual dependencies include layer indexes between sensors.
It should be noted that, determining the importance weight of each sensor may include the following steps: determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signal and the transmission result of the observation signal among the sensors through a self-attention model; and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
Further illustratively, determining importance weights for each sensor based on the query vector matrix, the key vector matrix, and the value vector matrix corresponding to each sensor may include the steps of: determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor; importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
For example, as shown in fig. 7, at time T1, an observation signal is input to the sensor S1, and signals received by S2, S3, and S5 are used as transmission results of the observation signal at time T1 between the sensors; at the time T2, an observation signal is input to the sensor S3, the transmission result … … of the signals received by the S1 and the S2 as the observation signals at the time T2 among the sensors is at the time Tn, the observation signal is input to the sensor S2, and the signals received by the S1, the S3 and the S4 are used as the transmission result of the observation signals at the time Tn among the sensors; the observation signals at different moments (T1 moment and T2 moment … … Tn moment) and transmission results of the observation signals among the sensors are input into a self-attention model, and a query vector matrix Q, a key vector matrix K and a value vector matrix V corresponding to the sensors output by the self-attention model are obtained; carrying out normalization operation on the query vector matrix Q and the key vector matrix K based on the normalization exponential function to obtain an attention distribution matrix corresponding to the sensor; the importance weights of the sensors are determined by calculating the attention distribution matrix and the value vector matrix V based on matmul (a function) function.
In step 503, a target sensor dependency graph is generated according to the importance weights of the sensors and the actual dependency relationships among the sensors.
As an implementation, when it is desired to generate a target sensor dependency graph, a candidate sensor dependency graph may be constructed based on actual dependencies among the sensors; the candidate sensor dependency graph only contains the actual dependency relationship among the sensors, but the sensors in the candidate sensor dependency graph do not contain importance weights; therefore, the importance weights of the respective sensors are arranged in the corresponding sensors in the candidate sensor dependency graph, and the target sensor dependency graph is obtained.
According to the equipment fault diagnosis method, the importance weight of each sensor and the actual dependency relationship among the sensors are determined, and the target sensor dependency graph is generated according to the importance weight of each sensor and the actual dependency relationship among the sensors, so that the similarity of the target sensor dependency graph and equipment to be detected is ensured, and the accuracy of the fault diagnosis result of the equipment to be detected is improved according to the target sensor dependency graph.
In one embodiment of the present application, as shown in fig. 8, fig. 8 is a flowchart of steps of another method for diagnosing a device fault provided in the embodiment of the present application, and when diagnosing a device fault to be detected, the method may specifically include the following steps:
Step 801, obtaining actual configuration parameters of each sensor in the device to be detected.
Step 802, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of equipment to be detected based on actual configuration parameters of each sensor in the equipment to be detected; the target sensor dependency graph includes sensors configured with importance weights, and actual dependency relationships between the sensors.
Step 803, judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through the fault detection model. If not, go to step 804; if yes, go to step 805.
Step 804, determining that the fault diagnosis result of the device to be detected is fault-free.
And step 805, predicting at least one fault cause corresponding to the equipment to be detected based on the configured target sensor dependency graph through the fault cause prediction network.
And step 806, generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
According to the equipment fault diagnosis method, according to the actual configuration parameters of the sensors in the equipment to be detected, the target sensor dependency graph of the simulation configuration parameters of the sensors is configured, and then fault diagnosis is carried out on the equipment to be detected according to the target sensor dependency graph; because the simulation configuration parameters of each sensor in the target sensor dependency graph correspond to the actual configuration parameters of each sensor in the equipment to be detected, when the equipment to be detected is subjected to fault diagnosis, the actual running state of the equipment to be detected can be simulated according to the target sensor dependency graph, and the fault diagnosis result of the equipment to be detected can be determined; in the process of carrying out fault diagnosis on the equipment to be detected according to the target sensor dependency graph, mechanical performance data of the equipment to be detected is not needed, and the fault cause of the equipment to be detected can be accurately determined based on actual configuration parameters of each sensor in the equipment to be detected when the equipment to be detected is subjected to fault diagnosis.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an equipment fault diagnosis device for realizing the above related equipment fault diagnosis method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the device fault diagnosis device or devices provided below may refer to the limitation of the device fault diagnosis method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 9, fig. 9 is a block diagram of a first device fault diagnosis apparatus according to an embodiment of the present application, and provides a device fault diagnosis apparatus, including: an acquisition module 10, a configuration module 20, and a diagnostic module 30, wherein:
the acquiring module 10 is configured to acquire actual configuration parameters of each sensor in the device to be detected.
The configuration module 20 is configured to configure simulation configuration parameters of each sensor in the target sensor dependency graph of the device to be detected based on actual configuration parameters of each sensor in the device to be detected; the target sensor dependency graph includes sensors configured with importance weights, and actual dependency relationships between the sensors.
And the diagnosis module 30 is used for diagnosing faults of the equipment to be detected based on the configured target sensor dependency graph.
According to the equipment fault diagnosis device, according to the actual configuration parameters of the sensors in the equipment to be detected, the target sensor dependency graph of the simulation configuration parameters of the sensors is configured, and then fault diagnosis is carried out on the equipment to be detected according to the target sensor dependency graph; because the simulation configuration parameters of each sensor in the target sensor dependency graph correspond to the actual configuration parameters of each sensor in the equipment to be detected, when the equipment to be detected is subjected to fault diagnosis, the actual running state of the equipment to be detected can be simulated according to the target sensor dependency graph, and the fault diagnosis result of the equipment to be detected can be determined; in the process of carrying out fault diagnosis on the equipment to be detected according to the target sensor dependency graph, mechanical performance data of the equipment to be detected is not needed, and the fault cause of the equipment to be detected can be accurately determined based on actual configuration parameters of each sensor in the equipment to be detected when the equipment to be detected is subjected to fault diagnosis.
In one embodiment, as shown in fig. 10, fig. 10 is a block diagram of a second device fault diagnosis apparatus according to an embodiment of the present application, and provides a device fault diagnosis apparatus, where a diagnosis module 30 includes: an acquisition module 10, a configuration module 20, and a diagnostic module 30, wherein:
and a judging unit 31, configured to judge whether the device to be detected has a fault based on the configured target sensor dependency graph through the fault detection model.
And the prediction unit 32 is configured to predict, if yes, at least one fault cause corresponding to the device to be detected based on the configured target sensor dependency graph through the fault cause prediction network.
And a generating unit 33, configured to generate a causal relationship closed-loop graph corresponding to each failure cause according to the causal relationship between the failure causes, and take the causal relationship closed-loop graph as a failure diagnosis result of the device to be detected.
In one embodiment, as shown in fig. 11, fig. 11 is a block diagram of a third device fault diagnosis apparatus according to an embodiment of the present application, and provides a device fault diagnosis apparatus, where the device fault diagnosis apparatus further includes: an input module 40, a determination module 50, and a generation module 60, wherein:
An input module 40, configured to input an observation signal to each sensor in the device to be detected, and obtain a transmission result of the observation signal after transmission between the sensors; and the input time of the observation signals of the sensors is different.
The determining module 50 is configured to determine importance weights of the sensors and actual dependency relationships between the sensors according to the observation signals of the sensors and transmission results of the observation signals between the sensors.
The generating module 60 is configured to generate a target sensor dependency graph according to importance weights of the sensors and actual dependency relationships among the sensors.
In one embodiment, as shown in fig. 12, fig. 12 is a block diagram of a fourth device fault diagnosis apparatus according to an embodiment of the present application, and provides a device fault diagnosis apparatus, where a determining module 50 includes: a first determination unit 51 and a second determination unit 52, wherein:
the first determining unit 51 is configured to determine, according to the input time of the observation signal and the transmission result of the observation signal between the sensors, a query vector matrix, a key vector matrix, and a value vector matrix corresponding to the sensors through the self-attention model.
The second determining unit 52 is configured to determine importance weights of the sensors based on the query vector matrix, the key vector matrix, and the value vector matrix corresponding to the sensors.
The second determining unit is specifically configured to: determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor; importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
In one embodiment, as shown in fig. 13, fig. 13 is a block diagram of a fifth device fault diagnosis apparatus according to an embodiment of the present application, and provides a device fault diagnosis apparatus, where a determining module 50 includes: a third determination unit 53 and a fourth determination unit 54, wherein:
a third determining unit 53 for determining a dependent path of the observation signal between the sensors and a dependent value between the two sensors to which the dependent paths are connected, based on a transmission result of the observation signal between the sensors.
And a fourth determining unit 54 for determining an actual dependency relationship between the sensors according to the dependency paths between the sensors and the dependency values between the two sensors connected to the dependency paths.
The respective modules in the above-described device failure diagnosis apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 14. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a device fault diagnosis method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 14 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements are applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring actual configuration parameters of each sensor in equipment to be detected;
based on actual configuration parameters of each sensor in the equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors;
and carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
In one embodiment, the processor when executing the computer program further performs the steps of:
Judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through a fault detection model;
if yes, predicting at least one fault reason corresponding to the equipment to be detected based on the configured target sensor dependency graph through a fault reason prediction network;
and generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
In one embodiment, the processor when executing the computer program further performs the steps of:
inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors; the input time of the observation signals of the sensors is different;
determining importance weights of the sensors and actual dependency relations among the sensors according to observation signals of the sensors and transmission results of the observation signals among the sensors;
and generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
In one embodiment, the processor when executing the computer program further performs the steps of:
Determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signal and the transmission result of the observation signal among the sensors through a self-attention model;
and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
In one embodiment, the processor when executing the computer program further performs the steps of:
based on the transmission result of the observation signal among the sensors, determining the dependence path of the observation signal among the sensors and the dependence value between the two sensors connected by the dependence path;
and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor;
importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring actual configuration parameters of each sensor in equipment to be detected;
based on actual configuration parameters of each sensor in the equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors;
and carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through a fault detection model;
if yes, predicting at least one fault reason corresponding to the equipment to be detected based on the configured target sensor dependency graph through a fault reason prediction network;
and generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors; the input time of the observation signals of the sensors is different;
determining importance weights of the sensors and actual dependency relations among the sensors according to observation signals of the sensors and transmission results of the observation signals among the sensors;
and generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signal and the transmission result of the observation signal among the sensors through a self-attention model;
and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Based on the transmission result of the observation signal among the sensors, determining the dependence path of the observation signal among the sensors and the dependence value between the two sensors connected by the dependence path;
and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor;
importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
acquiring actual configuration parameters of each sensor in equipment to be detected;
based on actual configuration parameters of each sensor in the equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises sensors configured with importance weights and actual dependency relations among the sensors;
And carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through a fault detection model;
if yes, predicting at least one fault reason corresponding to the equipment to be detected based on the configured target sensor dependency graph through a fault reason prediction network;
and generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors; the input time of the observation signals of the sensors is different;
determining importance weights of the sensors and actual dependency relations among the sensors according to observation signals of the sensors and transmission results of the observation signals among the sensors;
And generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signal and the transmission result of the observation signal among the sensors through a self-attention model;
and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
In one embodiment, the computer program when executed by the processor further performs the steps of:
based on the transmission result of the observation signal among the sensors, determining the dependence path of the observation signal among the sensors and the dependence value between the two sensors connected by the dependence path;
and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor;
Importance weights of the sensors are determined based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method of diagnosing a device fault, the method comprising:
acquiring actual configuration parameters of each sensor in equipment to be detected;
based on actual configuration parameters of each sensor in equipment to be detected, configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected; the target sensor dependency graph comprises the sensors configured with importance weights and actual dependency relations among the sensors;
And carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
2. The method according to claim 1, wherein the predicting the cause of the failure of the device to be detected based on the configured target sensor dependency graph comprises:
judging whether the equipment to be detected has faults or not based on the configured target sensor dependency graph through a fault detection model;
if yes, predicting at least one fault reason corresponding to the equipment to be detected based on the configured target sensor dependency graph through a fault reason prediction network;
and generating a causal relation closed-loop diagram corresponding to each fault cause according to the causal relation among the fault causes, and taking the causal relation closed-loop diagram as a fault diagnosis result of the equipment to be detected.
3. The method of claim 1, wherein the generating of the target sensor dependency graph comprises:
inputting observation signals to each sensor in the equipment to be detected, and acquiring transmission results of the observation signals after transmission among the sensors; the input time of the observation signals of the sensors is different;
Determining importance weights of the sensors and actual dependency relations among the sensors according to the observation signals of the sensors and transmission results of the observation signals among the sensors;
and generating a target sensor dependency graph according to the importance weights of the sensors and the actual dependency relations among the sensors.
4. A method according to claim 3, wherein said determining importance weights for each sensor based on said observation signal and the transmission of said observation signal between said sensors comprises:
determining a query vector matrix, a key vector matrix and a value vector matrix corresponding to each sensor according to the input time of the observation signals of each sensor and the transmission result of the observation signals among the sensors through a self-attention model;
and determining importance weights of the sensors based on the query vector matrix, the key vector matrix and the value vector matrix corresponding to the sensors.
5. A method according to claim 3, wherein said determining the actual dependency between the sensors based on the observed signal and the transmission of the observed signal between the sensors comprises:
Determining a dependent path of the observation signal between the sensors and a dependent value between two sensors connected by each dependent path based on a transmission result of the observation signal between the sensors;
and determining the actual dependency relationship among the sensors according to the dependency paths among the sensors and the dependency values among the two sensors connected by the dependency paths.
6. The method of claim 4, wherein the determining importance weights for each sensor based on the query vector matrix, the key vector matrix, and the value vector matrix for each sensor comprises:
determining an attention distribution matrix corresponding to each sensor according to the query vector matrix and the key vector matrix corresponding to each sensor;
and determining importance weights of the sensors based on the attention distribution matrix and the value vector matrix corresponding to the sensors.
7. An apparatus fault diagnosis device, characterized in that the device comprises:
the acquisition module is used for acquiring actual configuration parameters of each sensor in the equipment to be detected;
the configuration module is used for configuring simulation configuration parameters of each sensor in a target sensor dependency graph of the equipment to be detected based on actual configuration parameters of each sensor in the equipment to be detected; the target sensor dependency graph comprises the sensors configured with importance weights and actual dependency relations among the sensors;
And the diagnosis module is used for carrying out fault diagnosis on the equipment to be detected based on the configured target sensor dependency graph.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310414499.XA CN116610906B (en) | 2023-04-11 | 2023-04-11 | Equipment fault diagnosis method and device, computer equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310414499.XA CN116610906B (en) | 2023-04-11 | 2023-04-11 | Equipment fault diagnosis method and device, computer equipment and storage medium thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116610906A true CN116610906A (en) | 2023-08-18 |
| CN116610906B CN116610906B (en) | 2024-05-14 |
Family
ID=87684420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310414499.XA Active CN116610906B (en) | 2023-04-11 | 2023-04-11 | Equipment fault diagnosis method and device, computer equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116610906B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023028A (en) * | 2012-12-17 | 2013-04-03 | 江苏省电力公司 | Rapid grid failure positioning method based on dependency graph of entities |
| US20150095136A1 (en) * | 2013-10-02 | 2015-04-02 | Turn Inc. | Adaptive fuzzy fallback stratified sampling for fast reporting and forecasting |
| US20190042870A1 (en) * | 2017-12-28 | 2019-02-07 | Yen-Kuang Chen | Multi-domain convolutional neural network |
| US20200401470A1 (en) * | 2019-06-21 | 2020-12-24 | Palo Alto Research Center Incorporated | Method and system for performing automated root cause analysis of anomaly events in high-dimensional sensor data |
| US20220091883A1 (en) * | 2020-09-21 | 2022-03-24 | Applied Materials, Inc. | Dynamic scheduling based on task dependencies |
| CN114556248A (en) * | 2019-08-09 | 2022-05-27 | 康佩迪有限责任公司 | Method for determining a sensor configuration |
| CN115348159A (en) * | 2022-08-09 | 2022-11-15 | 国家电网有限公司信息通信分公司 | Micro-service fault positioning method and device based on self-encoder and service dependency graph |
| CN115664928A (en) * | 2022-09-19 | 2023-01-31 | 清华大学 | Interpretable graph-based root cause positioning method and device |
| CN115688871A (en) * | 2022-09-20 | 2023-02-03 | 中国科学院计算技术研究所 | Multi-element time sequence prediction method and system based on pre-training enhancement |
| CN115758086A (en) * | 2022-11-29 | 2023-03-07 | 西南科技大学 | Method, device and equipment for detecting faults of cigarette cut-tobacco drier and readable storage medium |
-
2023
- 2023-04-11 CN CN202310414499.XA patent/CN116610906B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023028A (en) * | 2012-12-17 | 2013-04-03 | 江苏省电力公司 | Rapid grid failure positioning method based on dependency graph of entities |
| US20150095136A1 (en) * | 2013-10-02 | 2015-04-02 | Turn Inc. | Adaptive fuzzy fallback stratified sampling for fast reporting and forecasting |
| US20190042870A1 (en) * | 2017-12-28 | 2019-02-07 | Yen-Kuang Chen | Multi-domain convolutional neural network |
| US20200401470A1 (en) * | 2019-06-21 | 2020-12-24 | Palo Alto Research Center Incorporated | Method and system for performing automated root cause analysis of anomaly events in high-dimensional sensor data |
| CN114556248A (en) * | 2019-08-09 | 2022-05-27 | 康佩迪有限责任公司 | Method for determining a sensor configuration |
| US20220091883A1 (en) * | 2020-09-21 | 2022-03-24 | Applied Materials, Inc. | Dynamic scheduling based on task dependencies |
| CN115348159A (en) * | 2022-08-09 | 2022-11-15 | 国家电网有限公司信息通信分公司 | Micro-service fault positioning method and device based on self-encoder and service dependency graph |
| CN115664928A (en) * | 2022-09-19 | 2023-01-31 | 清华大学 | Interpretable graph-based root cause positioning method and device |
| CN115688871A (en) * | 2022-09-20 | 2023-02-03 | 中国科学院计算技术研究所 | Multi-element time sequence prediction method and system based on pre-training enhancement |
| CN115758086A (en) * | 2022-11-29 | 2023-03-07 | 西南科技大学 | Method, device and equipment for detecting faults of cigarette cut-tobacco drier and readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| CESARE ALIPPI 等: "Learning Causal Dependencies to Detect and Diagnose Faults in Sensor Networks", 《2014 IEEE SYMPOSIUM ON INTELLIGENT EMBEDDED SYSTEM(IES)》, pages 34 - 41 * |
| MIAO HE 等: "A Dependency Graph Approach for Fault Detection and Localization Towards Secure Smart Grid", 《IEEE TRANSACTIONS ON SMART GRID》, vol. 2, no. 2, pages 342 - 351, XP011323852, DOI: 10.1109/TSG.2011.2129544 * |
| 陈伟: "基于过电压在线监测系统的高压电网输电线路故障定位研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, pages 042 - 243 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116610906B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schlegel et al. | Towards a rigorous evaluation of XAI methods on time series | |
| Chen et al. | Software defect number prediction: Unsupervised vs supervised methods | |
| Zajkowski | The method of solution of equations with coefficients that contain measurement errors, using artificial neural network | |
| US8726203B1 (en) | System and method for generating virtual test benches | |
| CN111061293B (en) | Multi-parameter coupled aircraft fault positioning method, aircraft and storage medium | |
| CN113487019A (en) | Circuit fault diagnosis method and device, computer equipment and storage medium | |
| CN116089870A (en) | Industrial equipment fault prediction method and device based on meta-learning under small sample condition | |
| CN108231189B (en) | Data processing method and disease diagnosis device based on double-deep neural learning network | |
| CN112926259A (en) | Method for predicting junction temperature of semiconductor device based on RBF neural network model | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN115795928A (en) | Accelerated degradation test data processing method and device based on gamma process | |
| CN113808132B (en) | Three-dimensional network model quality detection method and device and computer equipment | |
| CN114881343A (en) | Short-term load prediction method and device of power system based on feature selection | |
| CN118133728A (en) | Circuit generating method, circuit generating device, computer apparatus, storage medium, and program product | |
| CN116610906B (en) | Equipment fault diagnosis method and device, computer equipment and storage medium thereof | |
| CN116628564B (en) | Model training method and system for detecting generator state | |
| CN114610645B (en) | Task reliability and testability joint determination method and device and computer equipment | |
| Ferrell et al. | Modeling and performance considerations for automated fault isolation in complex systems | |
| CN113011748A (en) | Recommendation effect evaluation method and device, electronic equipment and readable storage medium | |
| CN117891566B (en) | Reliability evaluation method, device, equipment, medium and product of intelligent software | |
| Singh et al. | Hybrid physics-infused 1D-CNN based deep learning framework for diesel engine fault diagnostics | |
| CN117937477B (en) | Method and device for predicting reactive power boundary value of generator set and computer equipment | |
| CN118093385A (en) | Training of code quality evaluation model, and code quality evaluation method and device | |
| WO2020054599A1 (en) | Model generator, prediction device, model generation method, prediction method, and program | |
| CN117130909A (en) | Test analysis method, apparatus, device, storage medium, and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |