CN107545355B - Fault reason diagnosis method and device - Google Patents
Fault reason diagnosis method and device Download PDFInfo
- Publication number
- CN107545355B CN107545355B CN201710488106.4A CN201710488106A CN107545355B CN 107545355 B CN107545355 B CN 107545355B CN 201710488106 A CN201710488106 A CN 201710488106A CN 107545355 B CN107545355 B CN 107545355B
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- correlation
- item set
- frequent item
- 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.)
- Active
Links
Images
Abstract
The application provides a fault cause diagnosis method and a device, wherein the method comprises the following steps: when a first device included in a tested object fails, determining a failure name of the failure; inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions; and returning the inquired fault frequent item set to inform the fault reason of the first equipment with the fault. The method combines the business logic and the historical data, can diagnose the fault reason of the large-scale system or the complete equipment more accurately, intelligently and comprehensively, is suitable for the scene lacking experts, breaks the professional barrier of fault reason diagnosis, and reduces the requirement on professional knowledge of managers.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for diagnosing a fault cause.
Background
For some large systems, the fault is often macroscopic and system-level, while the fault cause is component-level and material-level, and there are many possible causes for a fault phenomenon, which makes fault location difficult.
The Wind Tunnel (Wind Tunnel) system, i.e. a Wind Tunnel laboratory, is a pipeline-shaped experimental device which is used for generating and controlling airflow in an artificial mode, is used for simulating the flowing condition of air around an aircraft or an entity, and can measure the effect of the airflow on the entity and observe physical phenomena. The flow field control is a core link of the whole wind tunnel test, and the aim is to ensure the accuracy and stability of the Mach number within a certain error range. The loss of mach number is equivalent to a system-level fault and relates to a plurality of components such as the rotating speed of a compressor, the angle of a stator blade, the profile of a spray pipe, a secondary throat, the opening degree of a central body and the like.
At present, the fault cause can be diagnosed through professional knowledge and business experience of management personnel, namely business logic. However, the method is highly subjective, depends on experts, and may miss, and once a manager with insufficient experience or insufficient professional knowledge encounters, it is easy to cause inaccurate diagnosis of the fault cause and mislead the fault exception handling.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for diagnosing a fault cause, so as to provide a simpler, more accurate, more intelligent, and more comprehensive method for diagnosing a fault cause of a large-scale system or a complete set of equipment, so as to solve the problems that the requirement for professional knowledge of an administrator is high and the diagnosis is easy to make mistakes in the process of manually diagnosing the fault cause.
Specifically, the method is realized through the following technical scheme:
in a first aspect of the present application, a fault cause diagnosis method is provided, including:
when a first device included in a tested object fails, determining a failure name of the failure;
inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions;
and returning the inquired fault frequent item set to inform the fault reason of the first equipment with the fault.
In a second aspect of the present application, a fault cause diagnosis apparatus is provided, which has a function of implementing the above method. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules or units corresponding to the above functions.
In one possible implementation, the apparatus includes:
a failure name determination unit configured to determine a failure name of a failure when a first device included in a measured object fails;
the fault reason searching unit is used for inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions;
and the fault reason returning unit is used for returning the inquired fault frequent item set so as to inform the fault reason of the fault of the first equipment.
In another possible implementation manner, the apparatus may include a processor, a memory, and a bus, where the processor and the memory are connected to each other through a bus system; the processor executes the fault cause diagnosis method shown in the first aspect of the present application by reading the logic instructions stored in the memory.
According to the technical scheme, the method and the system have the advantages that the service logic and the historical data are combined, the fault reason of the large-scale system or the complete equipment can be diagnosed more accurately, intelligently and comprehensively, the method and the system are suitable for scenes lacking of experts, the professional barrier of fault reason diagnosis is broken, and the requirement on professional knowledge of managers is lowered.
Drawings
FIG. 1 is a flow chart of a first method for diagnosing a cause of a fault provided herein;
FIG. 2 is a schematic view of a first method for diagnosing a cause of a fault according to the present disclosure;
FIG. 3 is a schematic view of a second method for diagnosing a cause of a fault according to the present application;
FIG. 4 is a flow chart of a second method for diagnosing a cause of a fault provided herein;
FIG. 5 is a block diagram of functional blocks of the apparatus provided herein;
fig. 6 is a diagram of the hardware architecture of the device shown in fig. 5 provided herein.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
According to the method and the device, the defect of fault reason diagnosis based on business logic is overcome, and when the device breaks down, other devices and parameters related to the broken down device can be displayed rapidly, so that exception handling is facilitated.
The method provided by the application can be applied to a computer or a server with computing power, and is used for diagnosing the fault reason of a large-scale system or complete equipment, wherein the common large-scale system or complete equipment comprises a wind-driven system, a power grid system and the like. For convenience of description, a large-scale system or a complete set of equipment will be hereinafter collectively referred to as a measured object.
The present application proposes two failure cause diagnosis methods, and first, a first failure cause diagnosis method is described below.
Referring to fig. 1, fig. 1 is a flowchart of a first fault cause diagnosis method provided in the present application. As shown in fig. 1, the process may include the following steps:
step 101: when a first device included in the object to be tested fails, the failure name of the failure is determined.
Step 102: inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions.
In the method, the fault frequent item set is obtained by mining historical change data of each equipment parameter when the tested object has a fault. For example, in a wind tunnel system, when a component of a tunnel body has a fault a, the conditions that the total temperature is too high, the parameters of a heat exchanger are abnormal, and the power of a compressor is too high occur, and a fault frequent item set corresponding to the fault a can be obtained by recording abnormal performances of the three parameters when the fault a occurs.
In practical applications, the set of frequent fault terms in the wind tunnel system is shown in table 1 below, and the set of frequent fault terms in the grid system is shown in table 2 below. It can be seen from tables 1 and 2 that the same type of fault can correspond to a plurality of fault frequency items, for example, as can be seen from table 1, when a surge condition (i.e. periodic oscillation of the medium in the fluid machine and its pipes) occurs, the phenomena of small inlet flow, cascade flow stall, and periodic oscillation of the airflow along the axial direction occur with 90% probability, and the phenomena of shaft vibration, shaft displacement, and key phase occur with 75% probability.
TABLE 1 Fault frenquency itemset in wind tunnel System
TABLE 2 fault frequent itemset in grid system
Step 103: and returning the inquired fault frequent item set to inform the fault reason of the fault of the first equipment.
The fault frequent item set records equipment parameters related to the fault and the change condition of the equipment parameters, and correspondingly, the changed equipment parameters may also be the reasons causing the fault, so that the manager can be informed of the reason of the fault of the first equipment by returning the inquired fault frequent item set.
As an embodiment, in the present application, a possible failure source may be further determined by the device to which the device parameter recorded in the inquired failure frequent item set belongs. For example, as can be seen from the first entry in table 1, one of the frequent failure items in the "surge condition" is that "the inlet flow is small, the cascade flows stalls, and the airflow oscillates periodically in the axial direction", which means that when the inlet flow is less than a certain value, the cascade flows stalls, and the airflow oscillates periodically in the axial direction after the cascade stalls are intensified, so that surge occurs; it can be concluded that this failure is probably due to excessive pipe network resistance, which is one of the possible sources of failure.
In practical application, a manager can perform exception handling according to related parameters recorded in a set of returned fault frequent items. For example, when a returned fault frequently appears in the wind tunnel system, a pressure increase, a main rotating speed increase and a hole wall temperature increase may be caused, so that the fault can be dealt with by adjusting the heat exchanger and reducing the pressure or the rotating speed.
As can be seen from the flow shown in fig. 1, the idea of the first fault cause diagnosis method can be shown in fig. 2, each device included in the tested object may have multiple types of faults, such as fault a, fault B, and fault C, when a certain device fails, the fault name can be quickly resolved by the method, the fault frequent item set corresponding to the fault name is searched from the fault frequent item set of the device according to the fault name, and the searched fault frequent item set composed of related device parameters is ranked, recommended, and displayed according to the probability that the fault frequent item set may occur, which is helpful for the manager to quickly and conveniently find the fault cause.
The fault cause diagnosis method needs historical data of the target fault equipment, and when the historical data of the target fault equipment is less, the corresponding fault frequent item set may not be searched. In order to remedy the defect, the second fault cause diagnosis method is provided, and the idea of the method can be seen in fig. 3, when a certain device has a fault, similar devices with high association degree with the fault device are firstly searched, and fault cause diagnosis of the fault device is realized by mining fault frequent item sets of the similar devices.
The second failure cause diagnosis method provided by the present application is not dependent on the first failure cause diagnosis method, and may be implemented in cooperation with the first failure cause diagnosis method, for example, when a failure frequent item set corresponding to a failure name is not found in a failure frequent item set of a first device stored in advance, or may be implemented separately, and the purpose of diagnosing the failure cause of the failed device can be achieved.
The flow of the second fault cause diagnosis method provided by the present application is described below with reference to fig. 4, and the flow may include the following steps:
step 401: when a first device included in the object to be tested fails, the failure name of the failure is determined.
Step 402: a correlation between the first device and other devices comprised by the object under test is obtained.
Step 403: and screening N second devices with the correlation with the first device ranked in the top N bits.
Where N is an integer of 1 or more.
Step 404: and inquiring the fault frequent item set corresponding to the fault name from the pre-stored fault frequent item sets of the N second devices.
Step 405: and returning the inquired fault frequent item set to inform the fault reason of the fault of the N second devices.
Since the screened N second devices are N devices highly correlated with the first device, the reason why the second device has the fault can be returned as a reference for the reason why the first device has the fault.
In step 402, the correlation between the devices, that is, the degree of correlation between the computing devices, may be calculated in advance or in real time when a fault occurs, and the specific calculation method is as follows:
for each of the other devices included in the system under test, except the first device, performing the following operations:
1) values of parameters included by the device and values of parameters included by the first device are obtained.
In the tested system, each device has unequal number of parameters, and part of important parameters can be extracted for analysis. The values of the parameters obtained here may include real-time parameter values of the device and the first device, and may also include historical parameter values of the device and the first device.
2) And calculating the correlation between the parameters included in the equipment and the parameters included in the first equipment according to the acquired numerical values of the parameters to obtain a correlation matrix.
Optionally, the correlation between each two parameters may be calculated by calculating a correlation coefficient, mutual information, or euclidean distance between each two parameters.
The correlation coefficient value is between-1 and 1, the correlation coefficient can be positive, negative or zero, the positive correlation coefficient represents that two parameters change in the same direction, the negative correlation coefficient represents that two parameters change in the opposite directions, the zero correlation coefficient represents that no correlation exists between the two parameters, and the larger the absolute value of the correlation coefficient is, the stronger the correlation between the parameters is.
The value of the mutual information is larger than 0, and the larger the mutual information is, the stronger the relevance between the representation parameters is.
The Euclidean distance is greater than 0, and the greater the Euclidean distance is, the stronger the relevance between the expression parameters is.
Here, the correlation coefficient is taken as an example to explain how to calculate the correlation between two parameters by calculating the correlation coefficient between the two parameters.
Assuming that there are a parameter X and a parameter Y, the correlation between these two parameters can be calculated by the following formula:
wherein Cov (X, Y) is the covariance of X and Y, Var [ X ] is the variance of X, and Var [ Y ] is the variance of Y. The correlation coefficient value is between-1 and 1, and a larger absolute value indicates a stronger correlation between the two parameters. A negative correlation coefficient represents a negative correlation and a positive correlation coefficient represents a positive correlation.
Assuming that a measured object comprises a device 1, a device 2 and a device 3, the device 1 comprises three parameters a1, a2 and a3, the device 2 comprises three parameters a4, a5 and a6, and the device 3 comprises four parameters a7, a8, a9 and a10, a correlation matrix shown in the following table 3 can be organized by calculating the correlation between two parameters of different devices.
TABLE 3 correlation matrix
3) And obtaining a first partial correlation between the equipment and the first equipment according to the obtained correlation matrix.
After the correlation matrix among the parameters is calculated, a comprehensive index capable of representing the correlation among the devices can be obtained according to the correlation matrix. There are many ways to calculate the comprehensive index, and two methods are briefly listed here:
the first method comprises the following steps: and carrying out weighted average on the absolute values of the elements included in the correlation matrix, and taking the obtained weighted average as the first partial correlation between the equipment and the first equipment.
Taking Table 3 as an example, for the correlation matrix between device 2 and device 1
Assuming that the weight of each element is 1, the absolute value of each element included in the matrix is weighted and averaged, and the first partial correlation is 0.53.
Similarly, for the correlation matrix between device 3 and device 1
Assuming that the weight of each element is 1, the absolute value of each element included in the matrix is weighted and averaged to obtain the weighted averageThe first partial correlation is 0.36.
Comparing the first partial correlations between device 1 and devices 2 and 3, respectively, it can be concluded that device 1 has a higher correlation with device 2.
And the second method comprises the following steps: and counting the number of elements with the absolute value larger than a set threshold value, calculating the ratio of the counted number of elements to the total number of elements included in the correlation matrix, and taking the ratio as the first partial correlation between the equipment and the first equipment.
Also taking Table 3 as an example, for the correlation matrix between device 2 and device 1
Assuming that the threshold is set to 0.5, the number of elements in the matrix whose absolute value is greater than 0.5 is 4, and the total number of elements included in the matrix is 9, the first partial correlation is 4/9 ═ 0.45.
Similarly, for the correlation matrix between device 3 and device 1
Assuming that the threshold is set to 0.5, the number of elements in the matrix whose absolute value is greater than 0.5 is 4, the total number of elements in the matrix is 12, and the first partial correlation is 4/12-0.42.
Comparing the first partial correlations between device 1 and devices 2 and 3, respectively, it can be concluded that device 1 has a higher correlation with device 2.
4) And acquiring a second part of correlation between the equipment and the first equipment, wherein the second part of correlation is configured in advance based on business logic between the equipment and the first equipment.
Taking a wind tunnel system as an example, it is assumed that the device 1 in the above table 3 is a heavy main compressor of the wind tunnel system, the device 2 is a component of the tunnel body, and the device 3 is a heat exchanger. Since the main compressor directly works on the cavern loop to affect the cavern temperature, the main compressor should have a higher correlation with a certain component of the cavern (e.g., the second correlation between the main compressor and the component of the cavern loop can be set to 0.5) and a lower correlation with the heat exchanger (e.g., the second correlation between the main compressor and the component of the cavern loop can be set to 0.3) from the aspect of service logic.
5) A weighted average of the first partial correlation and the second partial correlation is calculated as the correlation between the device and the first device.
Taking the above example as a support, in the step 4), the first partial correlation between the device 1 and the device 2 and the first partial correlation between the device 1 and the device 3 are obtained to be 0.53 and 0.36 through the first matrix synthesis index calculation method; acquiring that the correlation of the second part between the equipment 1 and the equipment 2 is 0.5 and the correlation of the second part between the equipment 1 and the equipment 3 is 0.3 in the step 5); assuming that the weight of the first partial correlation is 0.6 and the weight of the second partial correlation is 0.4, it can be obtained:
the correlation between device 1 and device 2 is: 0.56 × 0.6+0.5 × 0.4 ═ 0.536;
the correlation between device 1 and device 2 is: 0.43 × 0.6+0.3 × 0.4 ═ 0.378.
Thus, device 1 has a higher correlation with device 2 than device 3, i.e. the source of the fault is more likely to be located on device 2.
In summary, the fault cause diagnosis method provided by the application combines the service logic and the historical data, and can diagnose the fault cause of the large-scale system or the complete equipment more accurately, intelligently and comprehensively. The method is suitable for scenes lacking experts, breaks through the professional barrier of fault cause diagnosis, and reduces the requirement on professional knowledge of managers.
The methods provided herein are described above. The apparatus provided in the present application is described below.
Referring to fig. 5, fig. 5 is a functional block diagram of a failure cause diagnosis apparatus provided in the present application, which may be applied to a computer or a server with computing power. As shown in fig. 5, the apparatus may include the following units:
a failure name determining unit 501, configured to determine a failure name of a failure when a failure occurs in a first device included in a measured object.
A fault cause searching unit 502, configured to query a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first device; and the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions.
A failure reason returning unit 503, configured to return the queried failure frequent item set to notify the failure reason of the failure of the first device.
In one embodiment, the fault cause searching unit 502 may be further configured to, when a fault frequent item set corresponding to the fault name is not queried in a fault frequent item set of a first device stored in advance, obtain a correlation between the first device and another device included in the measured object; screening N second devices with the first N-bit correlation between the second devices and the first device; inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the N pieces of second equipment;
correspondingly, the failure cause returning unit 503 may be further configured to return the queried failure frequent item set to notify the failure cause of the failure of the N second devices.
In one embodiment, the apparatus may further include a correlation calculation unit 504; the correlation calculation unit 504 may obtain the correlation between the first device and other devices included in the object to be measured by: for each of the other devices, performing the following: acquiring the numerical value of the parameter included by the equipment and the numerical value of the parameter included by the first equipment; according to the obtained numerical value of the parameter, calculating the correlation between the parameter included in the equipment and the parameter included in the first equipment to obtain a correlation matrix; obtaining a first partial correlation between the equipment and the first equipment according to the correlation matrix; acquiring a second part of correlation between the equipment and the first equipment, wherein the second part of correlation is configured in advance based on business logic between the equipment and the first equipment; calculating a weighted average of the first partial correlation and the second partial correlation as a correlation between the device and the first device.
In one embodiment, when obtaining the first partial correlation between the device and the first device according to the correlation matrix, the correlation calculation unit 504 is specifically configured to: carrying out weighted average on absolute values of elements included in the correlation matrix, and taking the obtained weighted average as a first partial correlation between the equipment and the first equipment; or, counting the number of elements whose absolute value is greater than a set threshold included in the correlation matrix, calculating a ratio of the counted number of elements to the total number of elements included in the correlation matrix, and taking the ratio as the first partial correlation between the device and the first device.
In one embodiment, the measured object may be a wind tunnel system or a power grid system.
It should be noted that the division of the unit in the embodiment of the present invention is schematic, and is only a logic function division, and there may be another division manner in actual implementation. The functional units in the embodiments of the present application 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 description of the apparatus shown in fig. 5 is thus completed.
Correspondingly, the application also provides a hardware structure of the device shown in fig. 5. Referring to fig. 6, fig. 6 is a schematic diagram of a hardware structure of the apparatus shown in fig. 5 provided in the present application, where the apparatus includes: a processor 601, a memory 602, and a bus 603; wherein the processor 601 and the memory 602 communicate with each other via a bus 603.
The processor 601 may be a Central Processing Unit (CPU) or a Graphics Processing Unit (GPU); the memory 602 may be a non-volatile memory (non-volatile memory), and the memory 602 stores therein fault cause diagnosis logic instructions, and the processor 601 may execute the fault cause diagnosis logic instructions stored in the memory 602 to implement the above fault cause diagnosis method, which is described with reference to the flowcharts shown in fig. 1 and 4.
Up to this point, the description of the hardware configuration shown in fig. 6 is completed.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (6)
1. A fault cause diagnosis method, comprising:
when a first device included in a tested object fails, determining a failure name of the failure;
inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions;
returning the inquired fault frequent item set to inform the fault reason of the fault of the first equipment;
the method further comprises the following steps:
if the fault frequent item set corresponding to the fault name is not inquired in the pre-stored fault frequent item set of the first equipment, then
Acquiring correlation between first equipment and other equipment included in the measured object;
screening N second devices with the first N-bit correlation between the second devices and the first device;
inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the N pieces of second equipment;
returning the inquired fault frequent item set to inform the fault reason of the fault of the N second devices;
the correlation between the first device and other devices included in the object under test is obtained by:
for each of the other devices, performing the following:
acquiring the numerical value of the parameter included by the equipment and the numerical value of the parameter included by the first equipment;
according to the obtained numerical value of the parameter, calculating the correlation between the parameter included in the equipment and the parameter included in the first equipment to obtain a correlation matrix;
obtaining a first partial correlation between the equipment and the first equipment according to the correlation matrix;
acquiring a second part of correlation between the equipment and the first equipment, wherein the second part of correlation is configured in advance based on business logic between the equipment and the first equipment;
calculating a weighted average of the first partial correlation and the second partial correlation as a correlation between the device and the first device.
2. The method of claim 1, wherein obtaining the first partial correlation between the device and the first device according to the correlation matrix comprises:
carrying out weighted average on absolute values of elements included in the correlation matrix, and taking the obtained weighted average as a first partial correlation between the equipment and the first equipment; or
And counting the number of elements of which the absolute value is greater than a set threshold value, calculating the ratio of the counted number of elements to the total number of the elements included in the correlation matrix, and taking the ratio as the first partial correlation between the equipment and the first equipment.
3. The method of claim 1, wherein the object under test is a wind tunnel system or a power grid system.
4. A failure cause diagnosis apparatus characterized by comprising:
a failure name determination unit configured to determine a failure name of a failure when a first device included in a measured object fails;
the fault reason searching unit is used for inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the first equipment; the fault frequent item set is used for recording equipment parameters related to faults and equipment parameter change conditions;
a fault reason returning unit, configured to return the queried fault frequent item set to notify the fault reason of the fault occurring in the first device;
the fault cause searching unit is further configured to acquire a correlation between the first device and other devices included in the object to be tested when a fault frequent item set corresponding to the fault name is not queried in a pre-stored fault frequent item set of the first device; screening N second devices with the first N-bit correlation between the second devices and the first device; inquiring a fault frequent item set corresponding to the fault name from a pre-stored fault frequent item set of the N pieces of second equipment;
the fault reason returning unit is further configured to return the queried fault frequent item set to notify the fault reason of the fault occurring in the N second devices;
the apparatus further comprises a correlation calculation unit; the correlation calculation unit obtains a correlation between the first device and other devices included in the object to be measured by:
for each of the other devices, performing the following:
acquiring the numerical value of the parameter included by the equipment and the numerical value of the parameter included by the first equipment;
according to the obtained numerical value of the parameter, calculating the correlation between the parameter included in the equipment and the parameter included in the first equipment to obtain a correlation matrix;
obtaining a first partial correlation between the equipment and the first equipment according to the correlation matrix;
acquiring a second part of correlation between the equipment and the first equipment, wherein the second part of correlation is configured in advance based on business logic between the equipment and the first equipment;
calculating a weighted average of the first partial correlation and the second partial correlation as a correlation between the device and the first device.
5. The apparatus according to claim 4, wherein when obtaining the first partial correlation between the device and the first device according to the correlation matrix, the correlation calculation unit is specifically configured to:
carrying out weighted average on absolute values of elements included in the correlation matrix, and taking the obtained weighted average as a first partial correlation between the equipment and the first equipment; or
And counting the number of elements of which the absolute value is greater than a set threshold value, calculating the ratio of the counted number of elements to the total number of the elements included in the correlation matrix, and taking the ratio as the first partial correlation between the equipment and the first equipment.
6. The device of claim 4, wherein the object under test is a wind tunnel system or a power grid system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710488106.4A CN107545355B (en) | 2017-06-23 | 2017-06-23 | Fault reason diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710488106.4A CN107545355B (en) | 2017-06-23 | 2017-06-23 | Fault reason diagnosis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107545355A CN107545355A (en) | 2018-01-05 |
| CN107545355B true CN107545355B (en) | 2020-06-09 |
Family
ID=60970173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710488106.4A Active CN107545355B (en) | 2017-06-23 | 2017-06-23 | Fault reason diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107545355B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110531723B (en) * | 2019-09-12 | 2022-07-05 | 东北大学 | Visual analysis system and method for fault state of mineral processing equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101494572A (en) * | 2009-03-10 | 2009-07-29 | 中国电信股份有限公司 | Remote management method and system for equipment alarm information |
| CN105699760A (en) * | 2016-01-22 | 2016-06-22 | 国网冀北电力有限公司电力科学研究院 | Electric energy metering equipment and method for analyzing operating condition of power utilization information collection equipment |
| CN106651189A (en) * | 2016-12-27 | 2017-05-10 | 广东电网有限责任公司惠州供电局 | Transformer state evaluation method based on multilayer compound rule |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2894529B1 (en) * | 2014-01-08 | 2019-10-23 | Manitowoc Crane Companies, LLC | Remote diagnostic system |
-
2017
- 2017-06-23 CN CN201710488106.4A patent/CN107545355B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101494572A (en) * | 2009-03-10 | 2009-07-29 | 中国电信股份有限公司 | Remote management method and system for equipment alarm information |
| CN105699760A (en) * | 2016-01-22 | 2016-06-22 | 国网冀北电力有限公司电力科学研究院 | Electric energy metering equipment and method for analyzing operating condition of power utilization information collection equipment |
| CN106651189A (en) * | 2016-12-27 | 2017-05-10 | 广东电网有限责任公司惠州供电局 | Transformer state evaluation method based on multilayer compound rule |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107545355A (en) | 2018-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108683530B (en) | Data analysis method and device for multi-dimensional data and storage medium | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| JP5808605B2 (en) | Abnormality detection / diagnosis method and abnormality detection / diagnosis system | |
| JP5510760B2 (en) | Computer system and rule generation method | |
| CN110535702A (en) | A kind of alarm information processing method and device | |
| CN106094570B (en) | A kind of aero-engine complete machine health evaluating method under variable working condition based on this distance of operating mode's switch and paddy | |
| CN108304350B (en) | Fan index prediction and fault early warning method based on big data set neighbor strategy | |
| EP3477412A1 (en) | System fault isolation and ambiguity resolution | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| US20150235141A1 (en) | Automatic fault detection and diagnosis in complex physical systems | |
| CN116450399B (en) | Fault diagnosis and root cause positioning method for micro service system | |
| EP3584657B1 (en) | Risk assessment device, risk assessment method, and risk assessment program | |
| CN107710089A (en) | Shop equipment diagnostic device and shop equipment diagnostic method | |
| CN113946952A (en) | Method and device for generating fan twin body and electronic equipment | |
| CN111638988A (en) | Cloud host fault intelligent prediction method based on deep learning | |
| EP3598258B1 (en) | Risk assessment device, risk assessment system, risk assessment method, and risk assessment program | |
| US9104199B2 (en) | Engine monitoring | |
| CN112862347A (en) | Equipment abnormity monitoring method and system based on federal learning, storage medium and terminal | |
| CN107545355B (en) | Fault reason diagnosis method and device | |
| CN116010456A (en) | Equipment processing method, server and rail transit system | |
| JP2017157186A (en) | Equipment state estimating method, equipment state estimating device, and data providing device | |
| WO2017046906A1 (en) | Data analysis device and analysis method | |
| CN103970979A (en) | Aero-engine baseline calculation method, aero-engine condition monitoring method and aero-engine baseline monitoring system | |
| WO2023072724A1 (en) | System, apparatus and method for monitoring condition of an asset in technical installation | |
| TW201913255A (en) | Method for detecting and diagnosing an abnormal process |
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 |