CN113098132A - Improved machine learning fault diagnosis system based on group intelligent optimization - Google Patents
Improved machine learning fault diagnosis system based on group intelligent optimization Download PDFInfo
- Publication number
- CN113098132A CN113098132A CN202110354540.XA CN202110354540A CN113098132A CN 113098132 A CN113098132 A CN 113098132A CN 202110354540 A CN202110354540 A CN 202110354540A CN 113098132 A CN113098132 A CN 113098132A
- Authority
- CN
- China
- Prior art keywords
- fault
- unit
- data
- machine learning
- processing unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an improved machine learning fault diagnosis system based on group intelligent optimization, and relates to the technical field of machine fault diagnosis. Including main control unit, its characterized in that, main control unit's output electric connection has preprocessing unit, preprocessing unit's output electric connection has the failure analysis unit, the output electric connection of failure analysis unit has the sensing unit, main control unit's output electric connection has central processing unit, the inside electricity of central processing unit is connected with signal processing unit, signal processing unit's output radio connection has remote failure early warning and intelligent maintenance center. The abnormality inside the equipment is detected through a temperature sensor, a sound sensor and a vibration sensor in the sensing unit, then the abnormality is processed through the preprocessing unit, if the abnormality is detected, the abnormality can be quickly responded, and the failure analysis unit can accurately detect the reason of the abnormality, so that the later-stage maintenance is facilitated.
Description
Technical Field
The invention relates to the technical field of machine fault diagnosis, in particular to an improved machine learning fault diagnosis system based on group intelligent optimization.
Background
The mechanical equipment monitoring data enters a big data era at present, and the monitoring data has the following characteristics: (1) the data capacity is large, the manual analysis of experts and professionals is not practical, and meanwhile, the sharing performance is poor, and a huge database needs to be established for sharing; (2) the low density, equipment is in the in-service process, and normal state data is often many, leads to the fault data kind less. Therefore, how to effectively mine the potential value behind the big data of the machine becomes a leading edge and a research hotspot for guaranteeing the safe operation of equipment under the drive of the big data. The Federal learning is used as distributed machine learning, can perform data sharing under the condition that a database is not established, and has a good effect on fault diagnosis of mechanical fault big data. In recent years, the consumption proportion of electric energy in the whole energy industry increases year by year, and ensuring the safe and stable operation of a power grid is an important condition for maintaining and promoting economic development. The transformer is an important device in a power grid, is an important carrier for realizing electric energy conversion and reducing electric energy loss, finds out fault hidden dangers of the transformer in time, ensures safe operation of the transformer and can effectively reduce the occurrence probability of power grid faults.
With the development of data mining technology and machine learning technology, intelligent fault diagnosis technology for distribution transformers is gradually researched and applied. However, in the prior art, the accuracy rate is low when the fault of the distribution transformer is diagnosed, the fault cannot be found and eliminated in time, and the influence is brought to the power supply of people.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides an improved machine learning fault diagnosis system based on group intelligent optimization, which has the advantages of timely finding and removing faults and the like, and solves the problem of low accuracy in diagnosis of the faults of the distribution transformer.
(II) technical scheme
In order to realize the purpose of timely finding and removing the fault, the invention provides the following technical scheme: an improved machine learning fault diagnosis system based on swarm intelligence optimization comprises a main controller, wherein the output end of the main controller is electrically connected with a preprocessing unit, the output end of the preprocessing unit is electrically connected with a fault analysis unit, the output end of the fault analysis unit is electrically connected with a sensing unit, the output end of the main controller is electrically connected with a central processing unit, the internal part of the central processing unit is electrically connected with a signal processing unit, the output end of the signal processing unit is in radio connection with a remote fault early warning and intelligent maintenance center, and the output end of the remote fault early warning and intelligent maintenance center is connected with a cloud server through a wireless network;
the central processing unit is used for monitoring high-frequency vibration, internal temperature and edge calculation gateways of the distribution transformer equipment, embedding a machine learning algorithm, knowing the running load state of the distribution transformer equipment according to the read characteristic value historical data of the vibration sensor, the temperature sensor and the volume sensor of the Internet of things, analyzing the data by using an intelligent algorithm according to the characteristics of the sensors, predicting faults such as unbalance, misalignment, looseness, line aging and the like, and uploading the characteristic value data and a primary analysis result to the data cloud server of the Internet of things;
the fault acquisition unit is used for acquiring fault data, and can adopt the following two modes: obtaining structured data from the structured field; and extracting characteristic information from the unstructured data to judge fault content, wherein the fault acquisition unit is connected with the fault analysis unit.
As a preferred technical scheme of the invention, the main controller is used for acquiring and monitoring equipment information, a single chip microcomputer chip is arranged in the main controller, and the single chip microcomputer chip adopts a chip with the model of STM32F103RCT 6.
As a preferred technical solution of the present invention, the preprocessing unit is configured to perform unified processing on the collected fault information, and includes: data cleaning, data integration, data transformation and data reduction, and acquisition and pretreatment of each data information.
As a preferred technical solution of the present invention, the fault analysis unit includes a preliminary detection module for detecting a circuit and a temperature inside the device; the fault analysis module is used for analyzing the reason of the equipment fault and troubleshooting the fault; and the fault confirmation module is used for diagnosing the fault reason according to the relation map established by machine learning and the abnormal stack marking data.
As a preferred technical solution of the present invention, the sensing unit includes a temperature sensor, a sound sensor, and a vibration sensor, and the temperature sensor, the sound sensor, and the vibration sensor are all electrically connected to the sensing unit through the feature extraction unit.
As a preferred technical solution of the present invention, the signal processing unit may perform wireless communication and information transmission by using a wireless communication module, such as GPRS, 3G, and 4G, wifi.
As a preferred technical solution of the present invention, a storage module is arranged inside the cloud server, and the storage module is used for storing and recording the number and types of damage to the device.
(III) advantageous effects
Compared with the prior art, the invention provides an improved machine learning fault diagnosis system based on group intelligent optimization, which has the following beneficial effects:
1. this improve machine learning fault diagnosis system based on crowd's intelligence optimization comes the inside unusual of check out test set through temperature sensor, sound sensor and the vibration sensor among the sensing unit, then handles through the preprocessing unit, if the trouble can be quick react, the reason that detects the trouble that the fault analysis unit can be accurate is favorable to the maintenance in later stage.
2. This improve machine learning fault diagnosis system based on crowd's intelligence optimization utilizes intelligent algorithm to carry out the analysis to data through central processing unit, to the prediction of faults such as unbalance, centering, not hard up, circuit ageing, upload characteristic value data and preliminary analysis result to thing networking data cloud ware, be favorable to backing up later stage maintenance damage data, notice people that can be quick through remote fault early warning and intelligent maintenance center are maintained moreover and are maintained, avoid influencing the supply of equipment in the circuit.
Drawings
FIG. 1 is a block diagram of the system 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 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.
Example (b):
including main control unit, its characterized in that, main control unit's output electric connection has preprocessing unit, main control unit is used for acquireing and monitors equipment information, and main control unit's inside is provided with the singlechip chip, and the singlechip chip adopts the model to be STM32F103RCT 6's chip, preprocessing unit's output electric connection has the fault analysis unit, preprocessing unit is to carry out unified processing with the fault information who has gathered, include: the data analysis system comprises a data cleaning unit, a data integration unit, a data transformation unit, a data reduction unit, a fault analysis unit and a data processing unit, wherein the data cleaning unit, the data integration unit, the data transformation unit and the data reduction unit are used for collecting and preprocessing data information, the output end of the fault analysis unit is electrically connected with a sensing unit, the sensing unit comprises a temperature sensor, a sound sensor and a vibration sensor, the temperature sensor, the sound sensor and the vibration sensor are electrically connected with the sensing unit through a feature extraction unit, and the fault analysis unit comprises a primary detection module used for detecting a circuit and temperature in equipment; the fault analysis module is used for analyzing the reason of the equipment fault and troubleshooting the fault; the fault diagnosis system comprises a fault confirmation module, a central processing unit, a signal processing unit, a wireless communication module and a remote fault early warning and intelligent maintenance center, wherein the fault confirmation module is used for diagnosing fault reasons according to a relation map established by machine learning and abnormal stack labeling data, the output end of a main controller is electrically connected with the central processing unit, the central processing unit is electrically connected with the signal processing unit, the signal processing unit can adopt GPRS, 3G and 4G, wifi to carry out wireless communication and information transmission through the wireless communication module, the output end of the signal processing unit is in wireless connection with the remote fault early warning and intelligent maintenance center, the output end of the remote fault early warning and intelligent maintenance center is connected with a cloud server through a wireless network, a storage module is arranged in the cloud server;
the central processing unit is used for monitoring high-frequency vibration, internal temperature and edge calculation gateways of the distribution transformer equipment, embedding a machine learning algorithm, knowing the running load state of the distribution transformer equipment according to the read characteristic value historical data of the vibration sensor, the temperature sensor and the volume sensor of the Internet of things, analyzing the data by using an intelligent algorithm according to the characteristics of the sensors, predicting faults such as unbalance, misalignment, looseness, line aging and the like, and uploading the characteristic value data and a primary analysis result to the data cloud server of the Internet of things;
the fault acquisition unit is used for acquiring fault data, and can adopt the following two modes: obtaining structured data from the structured field; and extracting characteristic information from the unstructured data to judge fault content, wherein the fault acquisition unit is connected with the fault analysis unit.
The principle and the effect of the invention are as follows: the abnormality in the equipment is detected through a temperature sensor, a sound sensor and a vibration sensor in the sensing unit, and then the abnormality is processed through the preprocessing unit, if the abnormality occurs, the abnormality can be quickly responded, and the failure analysis unit can accurately detect the cause of the abnormality, so that the later maintenance is facilitated; utilize intelligent algorithm to carry out the analysis to data through central processing unit, to the prediction of faults such as unbalance, centering, not hard up, circuit ageing, upload characteristic value data and preliminary analysis result to thing networking data cloud ware, be favorable to backing up later stage maintenance damage data, notice people that can be quick through remote trouble early warning and intelligent maintenance center are maintained moreover and are maintained, avoid influencing the supply of equipment in the circuit.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. An improved machine learning fault diagnosis system based on swarm intelligence optimization comprises a main controller and is characterized in that the output end of the main controller is electrically connected with a preprocessing unit, the output end of the preprocessing unit is electrically connected with a fault analysis unit, the output end of the fault analysis unit is electrically connected with a sensing unit, the output end of the main controller is electrically connected with a central processing unit, the internal part of the central processing unit is electrically connected with a signal processing unit, the output end of the signal processing unit is in radio connection with a remote fault early warning and intelligent maintenance center, and the output end of the remote fault early warning and intelligent maintenance center is connected with a cloud server through a wireless network;
the central processing unit is used for monitoring high-frequency vibration, internal temperature and edge calculation gateways of the distribution transformer equipment, embedding a machine learning algorithm, knowing the running load state of the distribution transformer equipment according to the read characteristic value historical data of the vibration sensor, the temperature sensor and the volume sensor of the Internet of things, analyzing the data by using an intelligent algorithm according to the characteristics of the sensors, predicting faults such as unbalance, misalignment, looseness, line aging and the like, and uploading the characteristic value data and a primary analysis result to the data cloud server of the Internet of things;
the fault acquisition unit is used for acquiring fault data, and can adopt the following two modes: obtaining structured data from the structured field; and extracting characteristic information from the unstructured data to judge fault content, wherein the fault acquisition unit is connected with the fault analysis unit.
2. The improved machine learning fault diagnosis system based on swarm intelligence optimization according to claim 1, wherein the main controller is used for obtaining and monitoring equipment information, a single chip microcomputer chip is arranged inside the main controller, and the single chip microcomputer chip is a chip with a model number of STM32F103RCT 6.
3. The system of claim 1, wherein the preprocessing unit is configured to uniformly process the collected fault information, and comprises: data cleaning, data integration, data transformation and data reduction, and acquisition and pretreatment of each data information.
4. The improved machine learning fault diagnosis system based on group intelligent optimization according to claim 1, wherein the fault analysis unit comprises a preliminary detection module for detecting the circuit and temperature inside the equipment; the fault analysis module is used for analyzing the reason of the equipment fault and troubleshooting the fault; and the fault confirmation module is used for diagnosing the fault reason according to the relation map established by machine learning and the abnormal stack marking data.
5. The improved machine learning fault diagnosis system based on group intelligence optimization of claim 1, wherein the sensing unit comprises a temperature sensor, a sound sensor and a vibration sensor, and the temperature sensor, the sound sensor and the vibration sensor are all electrically connected with the sensing unit through the feature extraction unit.
6. The improved machine learning fault diagnosis system based on group intelligence optimization of claim 1, wherein the signal processing unit can use GPRS, 3G, 4G, wifi for wireless communication and information transmission through a wireless communication module.
7. The improved machine learning fault diagnosis system based on group intelligent optimization according to claim 1, wherein a storage module is arranged inside the cloud server, and the storage module is used for storing and recording the number and types of equipment damages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110354540.XA CN113098132A (en) | 2021-04-01 | 2021-04-01 | Improved machine learning fault diagnosis system based on group intelligent optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110354540.XA CN113098132A (en) | 2021-04-01 | 2021-04-01 | Improved machine learning fault diagnosis system based on group intelligent optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113098132A true CN113098132A (en) | 2021-07-09 |
Family
ID=76672600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110354540.XA Pending CN113098132A (en) | 2021-04-01 | 2021-04-01 | Improved machine learning fault diagnosis system based on group intelligent optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113098132A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251331A (en) * | 2023-11-17 | 2023-12-19 | 常州满旺半导体科技有限公司 | Chip performance data supervision and transmission system and method based on Internet of things |
-
2021
- 2021-04-01 CN CN202110354540.XA patent/CN113098132A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251331A (en) * | 2023-11-17 | 2023-12-19 | 常州满旺半导体科技有限公司 | Chip performance data supervision and transmission system and method based on Internet of things |
| CN117251331B (en) * | 2023-11-17 | 2024-01-26 | 常州满旺半导体科技有限公司 | Chip performance data supervision and transmission system and method based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101149416B (en) | Power cable insulation state monitoring and life span management system | |
| CN104386449B (en) | On-line checking intelligent protection device is taken turns end to end for mining belt conveyer | |
| CN114069856B (en) | Remote monitoring system and method for electric automobile charging facility | |
| CN108347352B (en) | Method for diagnosing performance of information system and equipment in power system | |
| CN113466597A (en) | Intelligent detection method for equipment state of rail transit power supply system | |
| CN205157637U (en) | Generator carbon brush current distribution monitoring system | |
| CN114510979A (en) | Underwater equipment inspection system and method based on edge calculation | |
| CN113098132A (en) | Improved machine learning fault diagnosis system based on group intelligent optimization | |
| CN212323930U (en) | Motor intelligence fortune dimension system | |
| CN117614487A (en) | Beidou system-based transmission line communication method and system | |
| CN112180268A (en) | Rapid detection method for retired power battery | |
| CN116381380A (en) | Dynamic fault supervision system for intelligent substation fault recorder | |
| CN116488351A (en) | Low-voltage distribution box remote monitoring method and system based on Internet of things | |
| CN107807325B (en) | Railway track circuit reliability analysis system and method based on multi-state theory | |
| CN114660504B (en) | Insulation monitoring loop detection method and device, electronic equipment and storage medium | |
| CN107342627B (en) | On-line equipment monitoring device of power distribution station and use method | |
| CN111983295B (en) | Equipment fault prediction method and system | |
| CN114264902A (en) | Method and system for monitoring working state of lightning protection box, electronic equipment and storage medium | |
| CN114035555A (en) | PLC controller fault detection system | |
| CN202383267U (en) | Storage battery state wireless network sensor node for DC (direct current) screen of transformer station | |
| CN111986469A (en) | Intelligent diagnosis method for field terminal fault | |
| CN113642478A (en) | Intelligent operation and maintenance platform | |
| CN211086964U (en) | Remote equipment vibration management system based on Internet of things | |
| CN203551731U (en) | Insulation online testing device for insulator | |
| CN220912359U (en) | Intelligent online monitoring system for comprehensive parameters of transformer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |