CN113283510B - Secondary equipment health condition analysis method based on full-service mixed data - Google Patents
Secondary equipment health condition analysis method based on full-service mixed data Download PDFInfo
- Publication number
- CN113283510B CN113283510B CN202110593619.8A CN202110593619A CN113283510B CN 113283510 B CN113283510 B CN 113283510B CN 202110593619 A CN202110593619 A CN 202110593619A CN 113283510 B CN113283510 B CN 113283510B
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- full
- fault type
- service mixed
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to a secondary equipment health condition analysis method based on full-service mixed data, belongs to the technical field of secondary equipment health condition analysis, and solves the problem that the prior art cannot realize real-time online analysis of the secondary equipment health condition based on the full-service mixed data. The method comprises the following steps: collecting full-service mixed data of secondary equipment to be analyzed in real time; the full-service mixed data comprises equipment numbers and equipment state monitoring data of the secondary equipment; the equipment state monitoring data comprise equipment self-checking information, a pressing plate, a fixed value, a communication state, power supply voltage, light intensity, equipment temperature, equipment differential flow conditions, internal state monitoring and equipment operation state data; compliance detection is carried out on all-service mixed data acquired in real time, and feature data is generated; and selecting a matched fault type determining model based on the equipment temperature, processing characteristic data by the selected fault type determining model, and outputting a fault type and health condition analysis result.
Description
Technical Field
The invention relates to the technical field of secondary equipment health condition analysis, in particular to a secondary equipment health condition analysis method based on full-service mixed data.
Background
In the working process of the intelligent substation, secondary equipment is utilized to monitor, measure, control, protect and regulate primary equipment in the power system. Abnormal information can be found by combing and judging the information collected by the secondary equipment, so that the analysis of the health state of the secondary equipment in the relay protection equipment is realized. Particularly, after the national power grid enterprise standard relay protection information specification is released, a unified data standard is provided for implementation of online operation and maintenance, and a foundation is laid for intelligent analysis of the health state of secondary equipment.
At present, the health condition analysis of relay protection secondary equipment is mainly realized based on long-term data accumulation and depends on an offline evaluation mode. The drawbacks of this approach are: firstly, the health condition of the secondary equipment cannot be obtained in real time, and the power grid fault can be found in real time; second, the state change of the secondary devices in the station cannot be quickly perceived. Due to the defects, the risk of the operation of the power grid is greatly increased, and meanwhile, scheduling and monitoring personnel cannot make timely defect elimination, overhaul and scheduling decisions, so that the safe and stable operation of the power grid is seriously threatened.
In addition, the lack of a real-time online analysis method for the health condition of the secondary equipment based on the full-service mixed data in the prior art results in poor accuracy of the real-time online analysis of the health condition of the secondary equipment, and the method cannot be practically applied.
Disclosure of Invention
In view of the above analysis, the embodiment of the invention aims to provide a method for analyzing the health condition of secondary equipment based on full-service mixed data, which is used for solving the problem that the prior art cannot realize real-time online analysis of the health condition of the secondary equipment based on the full-service mixed data.
The invention discloses a secondary equipment health condition analysis method based on full-service mixed data, which comprises the following steps:
collecting full-service mixed data of secondary equipment to be analyzed in real time; the full-service mixed data comprises equipment numbers and equipment state monitoring data of secondary equipment; the equipment state monitoring data comprise equipment self-checking information, a pressing plate, a fixed value, a communication state, power supply voltage, light intensity, equipment temperature, equipment differential flow conditions, internal state monitoring and equipment operation state data;
compliance detection is carried out on all-service mixed data acquired in real time, and feature data is generated based on the detected all-service mixed data; the characteristic data and the equipment number have a mapping relation;
selecting a matched fault type determining model based on the equipment temperature in the full-service mixed data, and receiving and processing the characteristic data and outputting the fault type corresponding to the full-service mixed data by the selected fault type determining model;
and outputting a health condition analysis result matched with the fault type corresponding to the full-service mixed data.
Based on the further improvement of the scheme, the equipment number and the equipment technical parameter of the secondary equipment have a mapping relation;
compliance detection is performed on all-service mixed data acquired in real time, and the method comprises the following steps:
acquiring equipment technical parameters of secondary equipment to be analyzed based on a mapping relation between equipment numbers and the equipment technical parameters;
judging whether the data type and the data format of each data in the all-service mixed data are correct or not based on the acquired technical parameters of the equipment, and if so, passing the compliance detection; otherwise, compliance detection is not passed.
Based on the further improvement of the above scheme, the generating feature data based on the full-service mixed data after the detection is passed includes:
if the equipment temperature is in the normal working range, sequentially storing each data except the equipment temperature in the equipment state monitoring data as matrix elements into a characteristic matrix to form characteristic data;
if the equipment temperature is abnormal, each data of the equipment state monitoring data is sequentially stored into a characteristic matrix as matrix elements to form characteristic data.
Based on a further improvement of the above solution, selecting a matched fault type determination model based on device temperatures in the all-service hybrid data includes:
if the equipment temperature of the secondary equipment is in the normal working range, the selected fault type determining model is a fault type determining model when the temperature is normal;
if the equipment temperature of the secondary equipment is abnormal, the selected fault type determining model is a fault type determining model when the temperature is abnormal.
Based on a further improvement of the above scheme, the fault type determination model is trained and tested by performing the following operations:
collecting static data and full-service mixed data of full life cycles of a plurality of secondary devices with the same layout positions as the secondary devices to be analyzed, extracting the full-service mixed data when various fault types occur in the full life cycles, and constructing a sample library;
classifying the full-service mixed data in the sample library and the corresponding fault types based on the equipment temperature to form a sample set when the equipment temperature is normal and the equipment temperature is abnormal;
and generating characteristic data based on the full-service mixed data in the sample set, taking the characteristic data as input, taking the corresponding fault type as output, training and testing a fault type determination model matched with the characteristic data.
Based on a further improvement of the above scheme, the sample set at normal temperature of the device includes: full-service mixed data of which the equipment temperature is in a normal working range and fault types corresponding to the full-service mixed data at the moment;
a sample set at device temperature anomaly comprising: full-service mixed data with equipment temperature in a normal working range and fault types corresponding to the full-service mixed data at the moment.
Based on the further improvement of the above scheme, the outputting the health condition analysis result matched with the fault type corresponding to the all-service mixed data includes:
and obtaining the health condition matched with the fault type corresponding to the full-service mixed data by inquiring the fault type-health condition relation table, and outputting the health condition as an analysis result.
Based on further improvement of the above scheme, the fault type-health condition relation table is used for storing health conditions corresponding to each fault type, and the health conditions corresponding to each fault type are determined based on importance degrees of the fault types.
Based on the further improvement of the scheme, the fault types comprise secondary equipment hardware faults, secondary equipment software faults, secondary equipment hardware alarms, secondary equipment software alarms and detection type state quantity serious deviation and no faults.
Based on a further improvement of the scheme, the fault type determining model is realized based on a neural network model or a Bayesian network classification model.
Compared with the prior art, the invention has at least one of the following beneficial effects:
on the one hand, the method for analyzing the health condition of the secondary equipment based on the full-service mixed data can realize real-time online analysis of the health condition of the secondary equipment based on the full-service mixed data, can quickly acquire the health condition score of the secondary equipment, is convenient for scheduling and monitoring personnel to know the health condition of the secondary equipment in time, and makes corresponding control instructions based on the health condition of the secondary equipment.
On the other hand, in order to further improve the accuracy of fault type identification, the invention respectively constructs the characteristic data and the fault type determining model which are adapted to different data characteristics from the equipment temperature dimension, so that the pertinence of the fault type determining process is stronger, the effect of fault type determination is better, the fault type corresponding to the full-service mixed data can be identified more quickly and accurately, the health condition of the secondary equipment is evaluated based on the fault type, and the analysis result of the health condition of the secondary equipment is obtained.
In the invention, the technical schemes can be mutually combined to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, like reference numerals being used to refer to like parts throughout the several views.
Fig. 1 is a flowchart of a method for analyzing the health status of a secondary device based on full-service hybrid data in an embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and together with the description serve to explain the principles of the invention, and are not intended to limit the scope of the invention.
The invention discloses a secondary equipment health condition analysis method based on full-service mixed data, wherein a flow chart is shown in fig. 1, and the method comprises the following steps:
step S1: collecting full-service mixed data of secondary equipment to be analyzed in real time;
the secondary equipment is auxiliary equipment for monitoring, measuring, controlling, protecting and adjusting primary equipment in the power system. Illustratively, the secondary device to be analyzed in the present embodiment may include the following types: protection device, measurement and control device, AC/DC power supply in station, and stabilizing equipment.
Preferably, the full-service hybrid data in the present embodiment includes the device number and the device status monitoring data of the secondary device;
it should be noted that each secondary device has a unique device number; because the static data of the secondary equipment is used in the subsequent health condition analysis process, and the static data of a fixed secondary equipment is fixed information, in order to reduce the data quantity of data transmission and the data transmission pressure, the static data of the secondary equipment and the mapping relation between the equipment number and the static data are maintained in a background system; preferably, the static data at least comprises equipment technical parameters, wherein the equipment technical parameters are used for describing relevant technical parameters when the secondary equipment works normally. In addition, in order to facilitate the user to more fully understand the related information of the secondary device, the static data may further include information such as a device name, a device manufacturer, a device model, and a device version.
Preferably, the device state monitoring data in the present embodiment includes device self-checking information, a pressing plate, a fixed value, a communication state, a power supply voltage, a light intensity, a device temperature, a device differential flow condition, an internal state monitoring, and a device operation state; the fixed value, the power supply voltage, the light intensity, the equipment temperature and the differential flow of the device are analog quantities, and the other are switching quantities. In order to better evaluate the health condition of the secondary device, in the actual implementation process, the device state monitoring data may further include one or more of SV sampling data anomaly, GOOSE data anomaly, SV signal on-off, GOOSE signal on-off, time tick signal, port state monitoring, and CPU usage (%). By monitoring whether the data are normal or not, the fault type of the secondary equipment can be judged.
It should be noted that, each data in the device status monitoring data may be obtained by an existing collection manner, which is not described herein.
In order to reduce the influence of the data type and the data format error on the subsequent process of the full-service mixed data, the step of compliance detection is further added in this embodiment, as shown in step S2.
Step S2: and carrying out compliance detection on the full-service mixed data acquired in real time, and generating characteristic data based on the full-service mixed data after detection.
Preferably, the procedure of compliance detection in this embodiment is as follows:
judging whether the data type and the data format of the equipment state monitoring data in the all-service mixed data are correct or not based on the equipment technical parameters of the secondary equipment, and if so, passing the compliance detection; otherwise, the compliance detection is not passed, and at this time, the corresponding data or report platform needs to be re-acquired for confirmation by the technician.
Specifically, since the technical parameters of the device include the data type and the data format of each device state monitoring data, the correctness of the data type and the data format can be determined by correspondingly comparing the device state monitoring data with the information in the technical parameters of the device.
After passing the compliance detection, the characteristic data can be generated; considering that the equipment temperature is an important indicator that affects whether the secondary equipment can normally operate, the embodiment evaluates the health condition of the secondary equipment when the equipment temperature is normal and the equipment temperature is abnormal. Preferably, the feature data may be generated by performing the following operations:
if the equipment temperature is in the normal working range, sequentially storing each data except the equipment temperature in the equipment state monitoring data as matrix elements into a characteristic matrix to form characteristic data;
if the equipment temperature is abnormal, each data of the equipment state monitoring data is sequentially stored into a characteristic matrix as matrix elements to form characteristic data;
it should be noted that, the above feature data has a one-to-one mapping relationship with the device number of the secondary device, so as to ensure the association relationship between the feature data and the secondary device.
Step S3: selecting a matched fault type determining model based on the equipment temperature, and receiving and processing characteristic data and outputting fault types corresponding to full-service mixed data by the selected fault type determining model;
in order to improve the accuracy of the analysis result of the fault type determination model, in this embodiment, starting from the dimension of the equipment temperature, fault type determination models adapted to different data features are respectively constructed, and the method includes:
1) Model for determining fault type at normal temperature: the temperature of the equipment is in the normal working range;
2) Model for determining fault type at abnormal temperature: the device temperature is abnormal.
Therefore, the selected fault type determining model is determined through the equipment temperature, and the characteristic data is input into the corresponding fault type determining model so as to obtain the fault type corresponding to the full-service mixed data.
Both of the above fault type determination models can be trained by:
collecting static data and full-service mixed data of full life cycles of a plurality of secondary devices with the same layout positions as the secondary devices to be analyzed, extracting the full-service mixed data when various fault types occur in the full life cycles, and constructing a sample library;
classifying the full-service mixed data in the sample library and the corresponding fault types based on the equipment temperature to form two types of sample sets;
1) Full-service mixed data of which the equipment temperature is in a normal working range and fault types corresponding to the full-service mixed data at the moment;
the sample set is used for training and testing a fault type determination model when the equipment is normal in temperature;
2) Full-service mixed data with abnormal equipment temperature and fault types corresponding to the full-service mixed data at the moment;
the sample set is used to train and test a fault type determination model when the temperature of the device is abnormal.
In the training and testing process, feature data is generated based on the full-service mixed data in the sample set, the feature data is taken as input, the corresponding fault type is taken as output, and the fault type determining model matched with the feature data is trained and tested.
It should be noted that, to ensure reliability and stability of the fault type determination model, the number of samples in the sample set used in training and testing the fault type determination model should be sufficiently large, and needs to include the case when there is no fault.
Because the monitoring data are not independent but mutually influenced, the corresponding relation between the monitoring data and the fault type is difficult to clear by establishing a mathematical model. Therefore, the embodiment adopts the mode of determining the model by analyzing the influence relationship between the monitoring data and the fault type to determine the corresponding relationship between the monitoring data and the fault type, so as to avoid detailed analysis of the relationship between the monitoring data and the fault type.
By analyzing the fault types that can be indicated by the device state monitoring data, the present embodiment selects the following common fault types of the secondary devices: the secondary equipment hardware fault, the secondary equipment software fault, the secondary equipment hardware alarm, the secondary equipment software alarm and the detection type state quantity have serious deviation and no fault.
Specifically, the hardware failure of the secondary device and the hardware alarm of the secondary device are all related to the hardware of the secondary device, and the difference is that: the secondary equipment can be normally used when the hardware of the secondary equipment alarms, but the secondary equipment is prompted to have partial problems so as to draw the attention of the user; when the hardware of the secondary equipment fails, the secondary equipment cannot be used normally and needs to be replaced in time, so that more serious influence is avoided. It should be noted that, the hardware fault of the secondary device and the hardware alarm of the secondary device are all related to the information such as the communication state, the power supply voltage, the light intensity, the device temperature, the port state monitoring, the device running state, the CPU usage (%), etc., so that whether the secondary device belongs to the hardware fault of the secondary device or the hardware alarm of the secondary device can be obtained through the data.
The secondary equipment software fault and the secondary equipment software alarm are related to the secondary equipment software, and the difference is that: when secondary equipment software alarms, partial protection functions are locked, and the secondary equipment partial functions can be normally used, but a user is prompted that partial problems exist in the secondary equipment so as to draw the attention of the user; when the secondary equipment software fails, the software on the secondary equipment cannot normally run, and needs to be updated and reloaded or updated in time, so that more serious influence is avoided. It should be noted that, the fault of the secondary equipment software and the alarm of the secondary equipment software are all related to the information of the self-checking information of the device, the pressing plate, the fixed value, the communication state, the differential flow state of the device, the internal state monitoring, the running state of the device and the like, so that whether the secondary equipment belongs to the fault of the secondary equipment software or the alarm of the secondary equipment software can be obtained through the data.
The serious deviation of the detection type state quantity is related to the information of the device self-checking information, the fixed value, the device differential flow condition, the internal state monitoring, the device running state and the like, so that whether the secondary equipment belongs to the detection type state quantity or not can be obtained through the data.
If the equipment state monitoring data are normal, the secondary equipment is fault-free.
In addition, the fault type can also comprise network faults, and whether the secondary equipment belongs to the network faults is determined by analyzing SV sampling data abnormality, GOOSE data abnormality, SV signal on-off and GOOSE signal on-off.
Preferably, in order to improve the accuracy of the fault type determining model, the fault type determining model can be updated based on the feature data corresponding to the all-service mixed data acquired in real time and the fault type.
For example, the fault type determination model may be implemented based on a neural network model or a bayesian network classification model.
Step S4: and outputting a health condition analysis result matched with the fault type corresponding to the full-service mixed data.
A fault type-health condition relationship table is constructed for storing health conditions corresponding to each fault type, and the health conditions corresponding to each fault type are expressed by scores, and the health condition scores corresponding to each fault type are determined based on the importance degree of the fault type.
By executing step S3, the fault type corresponding to the full-service hybrid data may be determined, and the health condition matching the fault type corresponding to the full-service hybrid data may be obtained by querying the fault type-health condition relation table, and the health condition may be output as an analysis result.
The method for analyzing the health condition of the secondary equipment based on the full-service mixed data can realize real-time online analysis of the health condition of the secondary equipment based on the full-service mixed data, can quickly acquire the health condition score of the secondary equipment, is convenient for scheduling and monitoring personnel to know the health condition of the secondary equipment in time, and makes corresponding control instructions based on the health condition of the secondary equipment. In addition, from the equipment temperature dimension, the method and the device construct the characteristic data and the fault type determining model which are adapted to different data characteristics, so that the pertinence of the fault type determining process is stronger, the fault type determining effect is better, the fault type corresponding to the full-service mixed data can be recognized more quickly and accurately, the health condition of the secondary equipment is evaluated based on the fault type, and the health condition analysis result is obtained.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (5)
1. The secondary equipment health condition analysis method based on the full-service mixed data is characterized by comprising the following steps of:
collecting full-service mixed data of secondary equipment to be analyzed in real time; the full-service mixed data comprises equipment numbers and equipment state monitoring data of secondary equipment; the equipment state monitoring data comprise equipment self-checking information, a pressing plate, a fixed value, a communication state, power supply voltage, light intensity, equipment temperature, equipment differential flow conditions, internal state monitoring and equipment operation state data;
compliance detection is carried out on all-service mixed data acquired in real time, and feature data is generated based on the detected all-service mixed data; the characteristic data and the equipment number have a mapping relation;
the generating feature data based on the full-service mixed data after the detection is passed comprises the following steps:
if the equipment temperature is in the normal working range, sequentially storing each data except the equipment temperature in the equipment state monitoring data as matrix elements into a characteristic matrix to form characteristic data;
if the equipment temperature is abnormal, each data of the equipment state monitoring data is sequentially stored into a characteristic matrix as matrix elements to form characteristic data;
selecting a matched fault type determining model based on the equipment temperature, and receiving and processing the characteristic data and outputting fault types corresponding to the full-service mixed data by the selected fault type determining model; the feature data and the equipment number of the secondary equipment have a one-to-one mapping relation;
selecting a matched fault type determination model based on device temperatures in the full service mix data, comprising:
if the equipment temperature of the secondary equipment is in the normal working range, the selected fault type determining model is a fault type determining model when the temperature is normal;
if the equipment temperature of the secondary equipment is abnormal, the selected fault type determining model is a fault type determining model when the temperature is abnormal;
the fault type determination model is trained and tested by performing the following operations:
collecting static data and full-service mixed data of full life cycles of a plurality of secondary devices with the same layout positions as the secondary devices to be analyzed, extracting the full-service mixed data when various fault types occur in the full life cycles, and constructing a sample library;
classifying the full-service mixed data in the sample library and the corresponding fault types based on the equipment temperature to form a sample set when the equipment temperature is normal and the equipment temperature is abnormal;
generating feature data based on the full-service mixed data in the sample set, taking the feature data as input, taking the corresponding fault type as output training, and testing a fault type determining model matched with the feature data;
a sample set at normal temperature of the device, comprising: full-service mixed data of which the equipment temperature is in a normal working range and fault types corresponding to the full-service mixed data at the moment;
a sample set at device temperature anomaly comprising: full-service mixed data of which the equipment temperature is in an abnormal working range and fault types corresponding to the full-service mixed data at the moment;
outputting a health condition analysis result matched with the fault type corresponding to the full-service mixed data; and obtaining the health condition matched with the fault type corresponding to the full-service mixed data by inquiring the fault type-health condition relation table, and outputting the health condition as an analysis result.
2. The method for analyzing the health condition of the secondary equipment based on the full-service mixed data according to claim 1, wherein the equipment number has a mapping relation with the equipment technical parameter of the secondary equipment;
compliance detection is performed on all-service mixed data acquired in real time, and the method comprises the following steps:
acquiring equipment technical parameters of secondary equipment to be analyzed based on a mapping relation between equipment numbers and the equipment technical parameters;
judging whether the data type and the data format of each data in the all-service mixed data are correct or not based on the acquired technical parameters of the equipment, and if so, passing the compliance detection; otherwise, compliance detection is not passed.
3. The method for analyzing the health status of the secondary device based on the full-service hybrid data according to claim 1 or 2, wherein the fault type-health status relation table is used for storing health status corresponding to each fault type, and the health status corresponding to each fault type is determined based on importance degree of the fault type.
4. The method for analyzing the health of the secondary equipment based on the full-service mixed data according to claim 3, wherein the fault type comprises a secondary equipment hardware fault, a secondary equipment software fault, a secondary equipment hardware alarm, a secondary equipment software alarm, a serious deviation of a detection type state quantity and no fault.
5. The full-service hybrid data-based secondary device health analysis method of claim 1, wherein said fault type determination model is implemented based on a neural network model or a bayesian network classification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593619.8A CN113283510B (en) | 2021-05-28 | 2021-05-28 | Secondary equipment health condition analysis method based on full-service mixed data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593619.8A CN113283510B (en) | 2021-05-28 | 2021-05-28 | Secondary equipment health condition analysis method based on full-service mixed data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283510A CN113283510A (en) | 2021-08-20 |
| CN113283510B true CN113283510B (en) | 2023-05-30 |
Family
ID=77282395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110593619.8A Active CN113283510B (en) | 2021-05-28 | 2021-05-28 | Secondary equipment health condition analysis method based on full-service mixed data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283510B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115047281B (en) * | 2022-08-11 | 2023-01-20 | 广东电网有限责任公司佛山供电局 | Intelligent detection system of power grid secondary equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320126A (en) * | 2015-10-21 | 2016-02-10 | 中国南方电网有限责任公司 | Secondary equipment hidden danger excavation method based on big data technology |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5421913B2 (en) * | 2007-08-03 | 2014-02-19 | スマートシグナル・コーポレーション | Fuzzy classification method for fault pattern matching cross-reference for related applications |
| CN103454516B (en) * | 2013-05-06 | 2015-10-28 | 国家电网公司 | Intelligent transformer substation secondary equipment health state diagnostic method |
| CN106197758B (en) * | 2016-06-29 | 2019-06-28 | 广东美的厨房电器制造有限公司 | The fault detection method and device of temperature sensing circuit |
| US20200250584A1 (en) * | 2019-01-31 | 2020-08-06 | Marketech International Corp. | Modeling method for smart prognostics and health management system and computer program product thereof |
| CN109933881A (en) * | 2019-03-06 | 2019-06-25 | 武汉大学 | A kind of Fault Diagnosis of Power Electronic Circuits method based on optimization deepness belief network |
| US20210062764A1 (en) * | 2019-08-20 | 2021-03-04 | Raytheon Company | Effector health monitor system and methods for same |
| CN111488947B (en) * | 2020-04-28 | 2024-02-02 | 深圳力维智联技术有限公司 | Fault detection method and device for power system equipment |
-
2021
- 2021-05-28 CN CN202110593619.8A patent/CN113283510B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320126A (en) * | 2015-10-21 | 2016-02-10 | 中国南方电网有限责任公司 | Secondary equipment hidden danger excavation method based on big data technology |
Non-Patent Citations (1)
| Title |
|---|
| 智能变电站二次设备多维度故障诊断与定位系统方案设计;张历;辛明勇;高吉普;王宇;胡星;张成模;;自动化与仪器仪表(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283510A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112101764B (en) | Ship technical condition comprehensive evaluation system based on state monitoring | |
| BR112013026307B1 (en) | DYNAMIC EVALUATION SYSTEM FOR MONITORING HIGH VOLTAGE ELECTRICAL COMPONENTS AND METHOD FOR EVALUATION OF AT LEAST ONE HIGH VOLTAGE ELECTRICAL COMPONENT | |
| CN107069960B (en) | Online defect diagnosis method for secondary operation and maintenance management system | |
| CN111738631B (en) | Instrument management system, management platform, industrial instrument and method | |
| CN114721352B (en) | State monitoring and fault diagnosis method and system of DCS (distributed control system) | |
| CN110174878A (en) | A kind of unmanned intelligence equipment is healthy and ensures integrated management general-purpose system | |
| CN113283510B (en) | Secondary equipment health condition analysis method based on full-service mixed data | |
| CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
| JP2012018623A (en) | Abnormality data analysis system | |
| CN114255784A (en) | Substation equipment fault diagnosis method based on voiceprint recognition and related device | |
| KR20140051678A (en) | Apparatus and method for fault management of smart devices | |
| CN116184265A (en) | Lightning arrester leakage current detection method and system based on multi-classification SVM | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN106644436B (en) | A kind of assessment method of breaker mechanic property | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN107273984A (en) | A kind of oil for electric power chemical supervision management method and system | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN108760285A (en) | A kind of solenoid valve on-line detecting system and method | |
| CN116186976A (en) | Verification method and verification system for accuracy of data collected by equipment platform sensor | |
| CN105548939B (en) | A kind of voltage transformer thermodynamic state verification method | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| CN110398791A (en) | A kind of intelligent base measuring tank of achievable self diagnosis | |
| CN115754866B (en) | Relay protection tester full life cycle monitoring and early warning system and method | |
| CN116362694B (en) | Test management system for boiler pressure vessel |
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 |