CN110988563A - UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium - Google Patents
UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110988563A CN110988563A CN201911340569.1A CN201911340569A CN110988563A CN 110988563 A CN110988563 A CN 110988563A CN 201911340569 A CN201911340569 A CN 201911340569A CN 110988563 A CN110988563 A CN 110988563A
- Authority
- CN
- China
- Prior art keywords
- data
- ups
- fault
- working
- state
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000009418 renovation Methods 0.000 claims abstract description 33
- 239000000203 mixture Substances 0.000 claims abstract description 31
- 230000002427 irreversible effect Effects 0.000 claims abstract description 28
- 230000006870 function Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 abstract description 7
- 230000002035 prolonged effect Effects 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 4
- 238000013024 troubleshooting Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a UPS (uninterrupted power supply) fault detection method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data; detecting the working state of the UPS based on the Gaussian mixture model, and outputting a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state; and when the detected working state is the normal working state, judging whether the first working data is intermittent fault data or not based on the xgboost model, and when the first working data is judged to be the intermittent fault data, continuously judging whether the second working data at the previous moment is the intermittent fault data or not, and outputting the fault type and the renovation suggestion corresponding to the UPS. The fault types can be effectively distinguished, the fault grade refined fault types are set, the faults are predicted in advance, the occurrence of irreversible faults is avoided, and the service life of equipment is prolonged.
Description
Technical Field
The invention relates to the technical field of UPS (uninterrupted power supply) fault detection, in particular to a UPS fault detection method, a device, equipment and a storage medium.
Background
Failure Prediction and Health Management (PHM) has been widely used in recent years for failure diagnosis and failure prediction of various electronic devices: for example, fault diagnosis and prognosis, i.e., fault diagnosis of electronic systems, especially with a focus on pre-diagnosis; and objective and reasonable system health state evaluation is given according to the diagnosis or monitoring information, so that a proper decision is made to carry out health management on the system.
At present, the fault detection technology of the UPS system is almost a method of manual experience detection, for example, after a machine of the UPS system fails, the UPS system is manually tested to find out the cause of the problem and replace the corresponding component, but once the equipment of the UPS system fails, the corresponding database is likely to have a data loss problem, and meanwhile, the difficulty of troubleshooting of the UPS system is high, and the service life of the equipment is greatly reduced due to the abnormality of part of components each time.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method, an apparatus, a device and a storage medium for detecting a UPS fault, which can effectively distinguish fault types, establish a refined fault type of a fault level, predict a fault in advance, avoid occurrence of an irreversible fault, and improve the service life of the device.
The embodiment of the invention provides a UPS fault detection method, which comprises the following steps:
acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data;
detecting the working state of the UPS based on a Gaussian mixture model, and outputting a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
and when the working state is detected to be a normal working state, judging whether the first working data is intermittent fault data or not based on an xgboost model, and when the first working data is judged to be the intermittent fault data, continuously judging whether the second working data at the previous moment is the intermittent fault data or not, and outputting a fault type and a renovation suggestion corresponding to the UPS.
Preferably, the step of obtaining the operation data of the UPS is preceded by:
acquiring a data set generated by third working data of the UPS at the historical time;
fitting the data set based on a Gaussian mixture algorithm to construct a Gaussian mixture model;
fitting the data set based on an xgboost algorithm to construct an xgboost model.
Preferably, the fault types include a primary fault, a secondary fault, and a tertiary fault.
Preferably, the operating state of the UPS is detected based on a gaussian mixture model, and a fault type and a renovation opinion corresponding to the UPS are output, specifically:
inputting the first working data into a mixed Gaussian model to calculate a probability density value of the first working data through a probability density function;
detecting the working state of the UPS through the probability density value of the first working data; when the probability density value of the first working data is smaller than a set threshold value, the working state of the UPS is an irreversible fault state, and when the probability density value of the first working data is larger than or equal to the set threshold value, the working state of the UPS is a normal data state;
when the working state is judged to be an irreversible fault state, outputting the UPS fault type as a primary fault, and judging the renovation suggestion as immediate shutdown maintenance;
and when the working state is judged to be the normal working state, outputting the UPS as the state health, and inputting the first working data into an xgboost model for detection.
Preferably, when it is detected that the operating state is a normal operating state, determining whether the first operating data is intermittent fault data based on an xgboost model, and when it is determined that the first operating data is the intermittent fault data, continuously determining whether the second operating data at the previous time is the intermittent fault data, and outputting a fault type and a renovation opinion corresponding to the UPS, specifically:
when the working state of the UPS is detected to be a normal working state, inputting the first working data into an xgboost model to calculate a score probability value of the first working data at a leaf node of each cart classification tree of the xgboost model;
judging whether the score probability value of the first working data is smaller than a set threshold value or not;
when the score probability value of the first working data is judged to be not smaller than the set threshold value, judging that the first working data is not intermittent fault data, and outputting the UPS as state health;
when the score probability value of the first working data is judged to be smaller than a set threshold value, judging that the first working data is intermittent fault data, and continuously judging whether the second working data at the previous moment is intermittent fault data;
when the second working data is judged to be intermittent fault data, outputting a secondary fault of which the fault type corresponding to the UPS is continuous intermittent fault data, and making a renovation suggestion that maintenance is arranged;
and when the second working data is judged not to be intermittent fault data, outputting a tertiary fault of which the fault type corresponding to the UPS is the intermittent fault data, and judging the renovation opinion to be a recording state.
In a second aspect, an embodiment of the present invention further provides a UPS failure detection apparatus, including:
the UPS comprises a first working data acquisition unit, a second working data acquisition unit and a control unit, wherein the first working data acquisition unit is used for acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data;
the working state detection unit is used for detecting the working state of the UPS based on a Gaussian mixture model and outputting a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
and the fault type and renovation opinion output unit is used for judging whether the first working data is intermittent fault data or not based on an xgboost model when the working state is detected to be a normal working state, continuously judging whether the second working data at the previous moment is intermittent fault data or not when the first working data is judged to be the intermittent fault data, and outputting a fault type and a renovation opinion corresponding to the UPS.
Preferably, the method further comprises the following steps:
the data set acquisition unit is used for acquiring a data set generated by third working data of the UPS at the historical moment;
the Gaussian mixture model construction unit is used for fitting the data set based on a Gaussian mixture algorithm to construct a Gaussian mixture model;
and the xgboost model construction unit is used for fitting the data set based on the xgboost algorithm to construct the xgboost model.
Preferably, the fault types include a primary fault, a secondary fault, and a tertiary fault.
Preferably, the working state detecting unit specifically includes:
the first calculation module is used for inputting the first working data into a mixed Gaussian model so as to calculate a probability density value of the first working data through a probability density function;
the first detection module is used for detecting the working state of the UPS through the probability density value of the first working data; when the probability density value of the first working data is smaller than a set threshold value, the working state of the UPS is an irreversible fault state, and when the probability density value of the first working data is larger than or equal to the set threshold value, the working state of the UPS is a normal data state;
the first judgment module is used for outputting the UPS fault type as a primary fault when the working state is judged to be the irreversible fault state, and the renovation suggestion is immediate shutdown maintenance;
and the output module is used for outputting the UPS as state health when the working state is judged to be the normal working state, and inputting the first working data into the xgboost model for detection.
Preferably, the fault type and truing opinion output unit specifically includes:
the second calculation module is used for inputting the first working data into an xgboost model when the working state of the UPS is detected to be a normal working state so as to calculate the score probability value of the first working data at the leaf node of each cart classification tree in the xgboost model;
the second judgment module is used for judging whether the score probability value of the first working data is smaller than a set threshold value or not;
the third judging module is used for judging that the first working data is not intermittent fault data and outputting the UPS as state health when the score probability value of the first working data is judged to be not smaller than the set threshold value;
the fourth judging module is used for judging that the first working data is intermittent fault data when the score probability value of the first working data is smaller than the set threshold value, and continuously judging whether the second working data at the previous moment is intermittent fault data;
a fifth judging module, configured to, when it is judged that the second working data is intermittent fault data, output a secondary fault of which the fault type corresponding to the UPS is continuous intermittent fault data, and the renovation opinion is to arrange maintenance;
and the sixth judging module is used for outputting the third-level fault of which the fault type corresponding to the UPS is intermittent fault data and the renovation opinion is a recording state when the second working data is judged not to be the intermittent fault data.
The embodiment of the present invention further provides a UPS failure detection apparatus, which includes a processor, a memory, and a computer program stored in the memory, where the computer program is executable by the processor to implement the UPS failure detection method according to the above embodiment.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the UPS fault detection method according to the above embodiment.
In the above embodiment, the normal operating state and the irreversible operating state of the UPS are detected based on the gaussian mixture model, and then, for the UPS in the normal operating state, based on the xgboost model and the logic judgment, it is detected whether the acquired operating data of the UPS is intermittent fault data or continuous intermittent fault data, so that the fault type and the repair suggestion corresponding to the UPS are output according to the detection result, the fault type can be effectively distinguished, a fault level refined fault type is established, the fault is predicted in advance, the occurrence of the irreversible fault is avoided, the service life of the equipment is prolonged, and the maintenance is performed in advance according to the corresponding prediction, so that the problem of data loss is avoided, and meanwhile, the problem of high difficulty in troubleshooting is solved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a UPS failure detection method according to a first embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a UPS failure detection apparatus according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a first embodiment of the present invention provides a UPS failure detection method, which can be implemented by a UPS failure detection apparatus, and in particular, implemented by one or more processors in the UPS failure detection apparatus, and at least includes the following steps:
s101, acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data.
S102, detecting the working state of the UPS based on the Gaussian mixture model, and outputting the fault type and the renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
in this embodiment, the gaussian mixture model is constructed by fitting a data set generated by third operation data of the UPS at the historical time based on a gaussian mixture algorithm (using a likelihood function and an E-M algorithm), specifically, the gaussian mixture model is represented by the likelihood function:
wherein, p (y)n(ii) a μ, Σ) is a probability density function of the sample distribution, specifically comprising the steps of:
1. because the likelihood function can not be solved directly, an E-M algorithm is required to be converted into an iterative function to solve a maximized Q function, and the expression of the maximized Q function is as follows:
wherein, γt,kIs ytSamples belong to K models, T is the number of samples, K is K Gaussian models, E (γ)t,k|yt,μi,Σi,πi) Is an estimate of γ; wherein, E (γ)t,k|yt,μi,Σi,πi) The expression of (a) is:
2. and (3) solving partial derivatives of the mu, sigma and pi in the Q function to obtain three parameters of the mu, sigma and pi of the Gaussian mixture model, wherein the expressions of the mu, sigma and pi are respectively as follows:
3. substituting the data set into a joint probability density function for fitting to obtain a Gaussian mixture model, wherein the probability density function is as follows:
the expression of the Gaussian mixture model is:
wherein, pikIs a weight, uiIs mean value, ΣiThe variance.
In this embodiment, the fault types include a primary fault, a secondary fault, and a tertiary fault, and the detecting the operating state of the UPS based on the gaussian mixture model and outputting the fault type and the repair opinion corresponding to the UPS specifically includes:
inputting the first working data into a mixed Gaussian model to calculate a probability density value of the first working data through a probability density function;
detecting the working state of the UPS through the probability density value of the first working data; when the probability density value of the first working data is smaller than a set threshold value, the working state of the UPS is an irreversible fault state, and when the probability density value of the first working data is larger than or equal to the set threshold value, the working state of the UPS is a normal data state;
when the working state is judged to be an irreversible fault state, outputting the UPS fault type as a primary fault, and judging the renovation suggestion as immediate shutdown maintenance;
and when the working state is judged to be the normal working state, outputting the UPS as the state health, and inputting the first working data into an xgboost model for detection.
S103, when the working state is detected to be the normal working state, whether the first working data is intermittent fault data or not is judged based on an xgboost model, when the first working data is judged to be the intermittent fault data, whether the second working data at the previous moment is the intermittent fault data or not is continuously judged, and the fault type and the renovation suggestion corresponding to the UPS are output.
In this embodiment, intermittent fault data refers to data generated by a UPS fault that persists for a limited period of time without any remedial maintenance activities and then recovers itself to perform the desired function. The continuous intermittent fault data means that the UPS always has intermittent faults, the continuous intermittent faults and the irreversible faults have correlation, and the continuous intermittent faults can cause the irreversible faults. The irreversible fault state is that the UPS is damaged and can be recovered to work only through repairability maintenance activities, the irreversible fault state needs to be repaired manually by simple understanding, the fault level is high, intermittent fault data can work after the occurrence of the irreversible fault state, and the fault level is low.
In this embodiment, the xgboost model is constructed based on fitting a data set generated by third operating data of the UPS at the historical time based on an xgboost algorithm, and specifically, an optimal xgboost model is constructed by minimizing a loss function through the established xgboost loss function:
wherein T represents the number of leaf nodes of the tree model, omega represents the weight of the current leaf node, gamma and lambda represent penalty coefficients, and C is a regular term.
In this embodiment, the specific steps of constructing the xgboost model are as follows:
1. because the above equation cannot be solved directly, the target function needs to be obtained by expanding the above equation by using a taylor algorithm:
wherein n is the number of sample points
2. The objective function of the above formula is that the traversal of the sample point is converted into the traversal of the leaf node:
wherein T is the number of leaf nodes
3. Simplifying the above formula, ijCoefficient is expressed as Gj、Hj. And to omegajTaking the derivative, when the derivative is zero, when ωjThe corresponding loss function has a minimum value, corresponding to the optimal xgboost model:
4. establishing an xgboost number model, and using an objective function corresponding to the optimal tree model of the formula:and as a tree building basis, judging the score of the target function before and after node splitting:
wherein,the score of the left sub-tree after splitting,the right sub-tree score after the split is obtained,score before splitting.
Therefore, when the working state is detected to be a normal working state, whether the first working data is intermittent fault data is judged based on an xgboost model, and when the first working data is judged to be the intermittent fault data, whether the second working data at the previous moment is the intermittent fault data is continuously judged, and a fault type and a renovation suggestion corresponding to the UPS are output, which specifically includes the following steps:
when the working state of the UPS is detected to be a normal working state, inputting the first working data into an xgboost model to calculate a score probability value of the first working data at a leaf node of each cart classification tree of the xgboost model;
judging whether the score probability value of the first working data is smaller than a set threshold value or not;
when the score probability value of the first working data is judged to be not smaller than the set threshold value, judging that the first working data is not intermittent fault data, and outputting the UPS as state health;
when the score probability value of the first working data is judged to be smaller than a set threshold value, judging that the first working data is intermittent fault data, and continuously judging whether the second working data at the previous moment is intermittent fault data;
when the second working data is judged to be intermittent fault data, outputting a secondary fault of which the fault type corresponding to the UPS is continuous intermittent fault data, and making a renovation suggestion that maintenance is arranged;
and when the second working data is judged not to be intermittent fault data, outputting a tertiary fault of which the fault type corresponding to the UPS is the intermittent fault data, and judging the renovation opinion to be a recording state.
For example, the xgboost model obtains a plurality of cart classification trees, calculates a score of the leaf node of the first working data on each cart classification tree, maps the score to an interval (0, 1) through softmax normalization, corresponds to the probability value of the first working data, and is normal working data when the probability value is greater than 0.5 and is intermittent fault data when the probability value is less than 0.5.
In summary, in this embodiment, the normal operating state and the irreversible operating state of the UPS are detected based on the gaussian mixture model, and then, for the UPS in the normal operating state, based on the xgboost model and the logic judgment, it is detected whether the acquired operating data of the UPS is intermittent fault data or continuous intermittent fault data, so that the fault type and the repair suggestion corresponding to the UPS are output according to the detection result, the fault type can be effectively distinguished, a fault-level refined fault type is established, the fault is predicted in advance, the occurrence of the irreversible fault is avoided, the service life of the equipment is prolonged, the maintenance is performed in advance according to the corresponding prediction, the problem of data loss is avoided, and meanwhile, the problem of difficulty in troubleshooting is solved.
Second embodiment of the invention:
referring to fig. 2, a second embodiment of the present invention further provides a UPS failure detection apparatus, including:
a first working data obtaining unit 100, configured to obtain first working data of a UPS at a current time; wherein the first working data comprises fault data and normal working data;
a working state detection unit 200, configured to detect a working state of the UPS based on a gaussian mixture model, and output a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
a fault type and truing opinion output unit 300, configured to, when it is detected that the operating state is the normal operating state, determine whether the first operating data is intermittent fault data based on an xgboost model, and when it is determined that the first operating data is the intermittent fault data, continue to determine whether the second operating data at the previous time is the intermittent fault data, and output a fault type and a truing opinion corresponding to the UPS.
Preferably, the method further comprises the following steps:
the data set acquisition unit is used for acquiring a data set generated by third working data of the UPS at the historical moment;
the Gaussian mixture model construction unit is used for fitting the data set based on a Gaussian mixture algorithm to construct a Gaussian mixture model;
and the xgboost model construction unit is used for fitting the data set based on the xgboost algorithm to construct the xgboost model.
Preferably, the fault types include a primary fault, a secondary fault, and a tertiary fault.
Preferably, the working state detecting unit 200 specifically includes:
the first calculation module is used for inputting the first working data into a mixed Gaussian model so as to calculate a probability density value of the first working data through a probability density function;
the first detection module is used for detecting the working state of the UPS through the probability density value of the first working data; when the probability density value of the first working data is smaller than a set threshold value, the working state of the UPS is an irreversible fault state, and when the probability density value of the first working data is larger than or equal to the set threshold value, the working state of the UPS is a normal data state;
the first judgment module is used for outputting the UPS fault type as a primary fault when the working state is judged to be the irreversible fault state, and the renovation suggestion is immediate shutdown maintenance;
and the output module is used for outputting the UPS as state health when the working state is judged to be the normal working state, and inputting the first working data into the xgboost model for detection.
Preferably, the failure type and truing opinion output unit 300 specifically includes:
the second calculation module is used for inputting the first working data into an xgboost model when the working state of the UPS is detected to be a normal working state so as to calculate the score probability value of the first working data at the leaf node of each cart classification tree in the xgboost model;
the second judgment module is used for judging whether the score probability value of the first working data is smaller than a set threshold value or not;
the third judging module is used for judging that the first working data is not intermittent fault data and outputting the UPS as state health when the score probability value of the first working data is judged to be not smaller than the set threshold value;
the fourth judging module is used for judging that the first working data is intermittent fault data when the score probability value of the first working data is smaller than the set threshold value, and continuously judging whether the second working data at the previous moment is intermittent fault data;
a fifth judging module, configured to, when it is judged that the second working data is intermittent fault data, output a secondary fault of which the fault type corresponding to the UPS is continuous intermittent fault data, and the renovation opinion is to arrange maintenance;
and the sixth judging module is used for outputting the third-level fault of which the fault type corresponding to the UPS is intermittent fault data and the renovation opinion is a recording state when the second working data is judged not to be the intermittent fault data.
The third embodiment of the present invention also provides a UPS failure detection apparatus, which includes a processor, a memory, and a computer program stored in the memory, and the computer program is executable by the processor to implement the UPS failure detection method according to the above-described embodiment.
The fourth embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the UPS fault detection method according to the above embodiment.
Illustratively, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program in the UPS fault detection apparatus.
The UPS fault detection device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a UPS failure detection apparatus and does not constitute a limitation of a UPS failure detection apparatus and may include more or fewer components than shown, or some components in combination, or different components, for example, the UPS failure detection apparatus may also include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the control center of the UPS failure detection apparatus may be connected to various portions of the overall UPS failure detection apparatus using various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the UPS fault detection apparatus by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the UPS failure detection apparatus integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (9)
1. A UPS fault detection method is characterized by comprising the following steps:
acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data;
detecting the working state of the UPS based on the Gaussian mixture model according to the first working data, and outputting a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
and when the working state is detected to be a normal working state, judging whether the first working data is intermittent fault data or not based on an xgboost model, and when the first working data is judged to be the intermittent fault data, continuously judging whether the second working data at the previous moment is the intermittent fault data or not, and outputting a fault type and a renovation suggestion corresponding to the UPS.
2. The UPS fault detection method of claim 1, wherein the step of obtaining operational data for the UPS is preceded by the step of:
acquiring a data set generated by third working data of the UPS at the historical time;
fitting the data set based on a Gaussian mixture algorithm to construct a Gaussian mixture model;
fitting the data set based on an xgboost algorithm to construct an xgboost model.
3. The UPS fault detection method of claim 2, wherein the fault types include primary, secondary, and tertiary faults.
4. The UPS fault detection method according to claim 3, wherein the operating state of the UPS is detected based on a gaussian mixture model, and the fault type and the repair opinion corresponding to the UPS are output, specifically:
inputting the first working data into a mixed Gaussian model to calculate a probability density value of the first working data through a probability density function;
detecting the working state of the UPS through the probability density value of the first working data; when the probability density value of the first working data is smaller than a set threshold value, the working state of the UPS is an irreversible fault state, and when the probability density value of the first working data is larger than or equal to the set threshold value, the working state of the UPS is a normal data state;
when the working state is judged to be an irreversible fault state, outputting the UPS fault type as a primary fault, and judging the renovation suggestion as immediate shutdown maintenance;
and when the working state is judged to be the normal working state, outputting the UPS as the state health, and inputting the first working data into an xgboost model for detection.
5. The UPS fault detection method according to claim 4, wherein when the operating state is detected to be a normal operating state, it is determined whether the first operating data is intermittent fault data based on an xgboost model, and when the first operating data is determined to be intermittent fault data, it is continuously determined whether the second operating data at the previous time is intermittent fault data, and a fault type and a dressing suggestion corresponding to the UPS are output, specifically:
when the working state of the UPS is detected to be a normal working state, inputting the first working data into an xgboost model to calculate a score probability value of the first working data at a leaf node of each cart classification tree of the xgboost model;
judging whether the score probability value of the first working data is smaller than a set threshold value or not;
when the score probability value of the first working data is judged to be not smaller than a set threshold value, judging that the UPS is not intermittent fault data, and outputting that the UPS is in a healthy state;
when the score probability value of the first working data is judged to be smaller than a set threshold value, judging that the first working data is intermittent fault data, and continuously judging whether the second working data at the previous moment is intermittent fault data;
when the second working data is judged to be intermittent fault data, outputting a secondary fault of which the fault type corresponding to the UPS is continuous intermittent fault data, and arranging maintenance according to the renovation suggestion;
and when the second working data is judged not to be intermittent fault data, outputting a tertiary fault of which the fault type corresponding to the UPS is the intermittent fault data, and judging the renovation opinion to be a recording state.
6. A UPS failure detection apparatus, comprising:
the UPS comprises a first working data acquisition unit, a second working data acquisition unit and a control unit, wherein the first working data acquisition unit is used for acquiring first working data of the UPS at the current moment; wherein the first working data comprises fault data and normal working data;
the working state detection unit is used for detecting the working state of the UPS based on a Gaussian mixture model and outputting a fault type and a renovation suggestion corresponding to the UPS; the working state comprises an irreversible fault state and a normal working state;
and the fault type and renovation opinion output unit is used for judging whether the first working data is intermittent fault data or not based on an xgboost model when the working state is detected to be a normal working state, continuously judging whether the second working data at the previous moment is intermittent fault data or not when the first working data is judged to be the intermittent fault data, and outputting a fault type and a renovation opinion corresponding to the UPS.
7. The UPS fault detection apparatus of claim 6, further comprising:
the data set acquisition unit is used for acquiring a data set generated by third working data of the UPS at the historical moment;
the Gaussian mixture model construction unit is used for fitting the data set based on a Gaussian mixture algorithm to construct a Gaussian mixture model;
and the xgboost model construction unit is used for fitting the data set based on the xgboost algorithm to construct the xgboost model.
8. A UPS failure detection apparatus comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the UPS failure detection method of any of claims 1 to 5 when executing the computer program.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the UPS failure detection method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911340569.1A CN110988563B (en) | 2019-12-23 | 2019-12-23 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911340569.1A CN110988563B (en) | 2019-12-23 | 2019-12-23 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110988563A true CN110988563A (en) | 2020-04-10 |
CN110988563B CN110988563B (en) | 2022-04-01 |
Family
ID=70075854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911340569.1A Active CN110988563B (en) | 2019-12-23 | 2019-12-23 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110988563B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112559279A (en) * | 2020-11-10 | 2021-03-26 | 深圳前海有电物联科技有限公司 | Uninterruptible power supply system fault prediction method, equipment and computer readable storage medium |
CN113325308A (en) * | 2021-04-13 | 2021-08-31 | 北京中大科慧科技发展有限公司 | Power supply fault detection method for data center |
CN113687259A (en) * | 2021-09-23 | 2021-11-23 | 北京中大科慧科技发展有限公司 | Machine room UPS detection method and system for data center |
WO2023201532A1 (en) * | 2022-04-19 | 2023-10-26 | 宁德时代新能源科技股份有限公司 | Abnormal battery cell identification method and apparatus, electronic device, and storage medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015121176A1 (en) * | 2014-02-11 | 2015-08-20 | Ge Aviation Systems Limited | Method of identifying anomalies |
CN105912843A (en) * | 2016-04-07 | 2016-08-31 | 福建师范大学 | Unsupervised fault prediction method on basis of dual-view method and particle filter method |
CN106597245A (en) * | 2016-11-04 | 2017-04-26 | 山东科技大学 | IGBT fault monitoring device and method |
CN107132310A (en) * | 2017-03-28 | 2017-09-05 | 浙江大学 | Transformer equipment health status method of discrimination based on gauss hybrid models |
US20180076658A1 (en) * | 2016-09-13 | 2018-03-15 | General Electric Company | Isolated parallel ups system with fault location detection |
CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
CN108460397A (en) * | 2017-12-26 | 2018-08-28 | 东软集团股份有限公司 | Analysis method, device, storage medium and the electronic equipment of equipment fault type |
CN108802525A (en) * | 2018-06-06 | 2018-11-13 | 浙江宇天科技股份有限公司 | Equipment fault intelligent Forecasting based on small sample |
CN109190670A (en) * | 2018-08-02 | 2019-01-11 | 大连理工大学 | A kind of charging pile failure prediction method based on expansible boosted tree |
CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
CN109635873A (en) * | 2018-12-19 | 2019-04-16 | 佛山科学技术学院 | A kind of UPS failure prediction method |
CN110135492A (en) * | 2019-05-13 | 2019-08-16 | 山东大学 | Equipment fault diagnosis and method for detecting abnormality and system based on more Gauss models |
CN110298497A (en) * | 2019-06-11 | 2019-10-01 | 武汉蓝智科技有限公司 | Manufacturing forecast maintenance system and its application method based on big data |
CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
-
2019
- 2019-12-23 CN CN201911340569.1A patent/CN110988563B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015121176A1 (en) * | 2014-02-11 | 2015-08-20 | Ge Aviation Systems Limited | Method of identifying anomalies |
CN105912843A (en) * | 2016-04-07 | 2016-08-31 | 福建师范大学 | Unsupervised fault prediction method on basis of dual-view method and particle filter method |
US20180076658A1 (en) * | 2016-09-13 | 2018-03-15 | General Electric Company | Isolated parallel ups system with fault location detection |
CN106597245A (en) * | 2016-11-04 | 2017-04-26 | 山东科技大学 | IGBT fault monitoring device and method |
CN107132310A (en) * | 2017-03-28 | 2017-09-05 | 浙江大学 | Transformer equipment health status method of discrimination based on gauss hybrid models |
CN108460397A (en) * | 2017-12-26 | 2018-08-28 | 东软集团股份有限公司 | Analysis method, device, storage medium and the electronic equipment of equipment fault type |
CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
CN108802525A (en) * | 2018-06-06 | 2018-11-13 | 浙江宇天科技股份有限公司 | Equipment fault intelligent Forecasting based on small sample |
CN109190670A (en) * | 2018-08-02 | 2019-01-11 | 大连理工大学 | A kind of charging pile failure prediction method based on expansible boosted tree |
CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
CN109635873A (en) * | 2018-12-19 | 2019-04-16 | 佛山科学技术学院 | A kind of UPS failure prediction method |
CN110135492A (en) * | 2019-05-13 | 2019-08-16 | 山东大学 | Equipment fault diagnosis and method for detecting abnormality and system based on more Gauss models |
CN110298497A (en) * | 2019-06-11 | 2019-10-01 | 武汉蓝智科技有限公司 | Manufacturing forecast maintenance system and its application method based on big data |
CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
Non-Patent Citations (8)
Title |
---|
BO WANG ET AL.: "The applications of XGBoost in Fault Diagnosis of Power Networks", 《2019 IEEE INNOVATIVE SMART GRID TECHNOLOGIES - ASIA (ISGT ASIA)》 * |
MINGHUA CHEN ET AL.: "XGBoost-Based Algorithm Interpretation and Application on Post-Fault Transient Stability Status Prediction of Power System", 《IEEE ACCESS》 * |
周叶 等: "《基于新异类检测和支持向量机的水电机组诊断技术》", 30 June 2015, 世界图书出版广东有限公司 * |
李杰: "《工业人工智能》", 31 July 2019, 上海交通大学出版社 * |
罗婵纯 等: "基于高斯混合模型的汽轮机转轴故障诊断方法", 《华电技术》 * |
赵洪山 等: "应用深度自编码网络和XGBoost的风电机组发电机故障诊断", 《电力系统自动化》 * |
邸帅: "风电机组关键部件故障预测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
郭慧东 等: "基于数据挖掘的风电机组变桨系统劣化状态在线辨识方法", 《中国电机工程学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112559279A (en) * | 2020-11-10 | 2021-03-26 | 深圳前海有电物联科技有限公司 | Uninterruptible power supply system fault prediction method, equipment and computer readable storage medium |
CN113325308A (en) * | 2021-04-13 | 2021-08-31 | 北京中大科慧科技发展有限公司 | Power supply fault detection method for data center |
CN113325308B (en) * | 2021-04-13 | 2023-02-17 | 北京中大科慧科技发展有限公司 | Power supply fault detection method for data center |
CN113687259A (en) * | 2021-09-23 | 2021-11-23 | 北京中大科慧科技发展有限公司 | Machine room UPS detection method and system for data center |
CN113687259B (en) * | 2021-09-23 | 2023-11-24 | 北京中大科慧科技发展有限公司 | Machine room UPS detection method and system for data center |
WO2023201532A1 (en) * | 2022-04-19 | 2023-10-26 | 宁德时代新能源科技股份有限公司 | Abnormal battery cell identification method and apparatus, electronic device, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110988563B (en) | 2022-04-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110988563B (en) | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium | |
US11746753B2 (en) | Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium | |
CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
CN107944721B (en) | Universal machine learning method, device and system based on data mining | |
CN110837852A (en) | Fault diagnosis method and device for rolling mill gearbox and terminal equipment | |
CN115936658A (en) | Power equipment abnormality detection method, system and readable storage medium | |
CN108009063B (en) | Method for detecting fault threshold of electronic equipment | |
CN110264055B (en) | Component hazard assessment method, device, equipment and computer-readable storage medium | |
CN117318069A (en) | Power supply system fault self-healing method and system | |
CN113487182B (en) | Device health state evaluation method, device, computer device and medium | |
CN111126492A (en) | Method and device for determining fault type of photovoltaic power grid | |
CN116860562B (en) | Method and system for monitoring data quality of data center | |
CN107977626B (en) | Grouping method for electronic equipment working data | |
CN113987027A (en) | Equipment state determination method, device and medium based on fault prediction | |
CN108009582B (en) | Method for setting standard working index of electronic equipment | |
CN117909864A (en) | Power failure prediction system and method | |
CN110348005B (en) | Distribution network equipment state data processing method and device, computer equipment and medium | |
CN113204280B (en) | Method, system, equipment and medium for diagnosing power failure | |
CN111008119A (en) | Method, device, equipment and medium for updating hard disk prediction model | |
CN113486583B (en) | Method and device for evaluating health of equipment, computer equipment and computer readable storage medium | |
CN113986618B (en) | Cluster brain fracture automatic repair method, system, device and storage medium | |
CN113608953B (en) | Test data generation method and device, electronic equipment and readable storage medium | |
CN112906914B (en) | Rail transit IT equipment fault analysis method and device and electronic equipment | |
CN117439899B (en) | Communication machine room inspection method and system based on big data | |
JP2019164762A (en) | Information processing device, machine learning device and system |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Peng Yanqing Inventor after: Chen Hongyu Inventor before: Chen Hongyu Inventor before: Peng Yanqing |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |