CN112329821A - Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification - Google Patents
Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification Download PDFInfo
- Publication number
- CN112329821A CN112329821A CN202011146437.8A CN202011146437A CN112329821A CN 112329821 A CN112329821 A CN 112329821A CN 202011146437 A CN202011146437 A CN 202011146437A CN 112329821 A CN112329821 A CN 112329821A
- Authority
- CN
- China
- Prior art keywords
- node
- layer
- module
- temperature
- sound
- 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.)
- Withdrawn
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
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Protection Of Transformers (AREA)
Abstract
The invention discloses an intelligent diagnosis system of a power transformer and a diagnosis method based on decision tree classification; belongs to the field of intelligent diagnosis of power equipment; the technical key points are as follows: the method comprises the following steps: the device comprises a temperature monitoring module, a sound monitoring module, a current monitoring module, a data acquisition and storage module, a fault diagnosis module and a display and query module; the temperature monitoring module is used for measuring temperature signals of the transformer iron core, the secondary winding and the insulating medium; the sound monitoring module is used for measuring sound signals of the transformer iron core, the secondary winding and the insulating medium; the current monitoring module is used for measuring a current signal of the secondary side of the mutual inductor. By adopting the intelligent diagnosis system of the power transformer and the diagnosis method based on decision tree classification, the diagnosis efficiency and the diagnosis precision can be greatly improved.
Description
Technical Field
The invention belongs to the field of intelligent diagnosis of power equipment, and relates to an intelligent diagnosis system of a power transformer and a diagnosis method based on decision tree classification.
Background
The mutual inductor is mainly used for realizing standardization and miniaturization of measuring instruments, protective equipment and automatic control equipment. Meanwhile, the mutual inductor can be used for isolating a high-voltage system so as to ensure the safety of people and equipment. Therefore, fault diagnosis of the transformer is particularly important.
For diagnostic studies of transformers, the prior art is as follows:
CN105487037A a transformer fault diagnosis method based on electrical parameters, which is characterized in that three bus operating temperatures of a transformer incoming line, secondary side voltages of three voltage transformers, and secondary side currents of three current transformers are monitored, when the three bus operating temperatures of the transformer incoming line are normal, secondary side voltages of different voltage transformers in the same switch cabinet are compared, and if the secondary side voltage of one of the voltage transformers is abnormal compared with the secondary side voltages of other voltage transformers, it is determined that the voltage transformers have faults. And comparing the secondary side currents of different current transformers in the same switch cabinet, and judging that the current transformers have faults if the secondary side current of one current transformer is abnormal compared with the secondary side currents of other current transformers. The invention can have accurate diagnosis effect on the fault of the mutual inductor, realize early diagnosis and fault finding of the fault of the mutual inductor and ensure the normal operation of the mutual inductor.
CN105675044A is a temperature-based transformer fault diagnosis method, which is characterized in that the temperature-based transformer fault diagnosis method is as follows: the temperature of the mutual inductor, the temperatures of two connectors of an outlet wire at the secondary side of the mutual inductor and the temperatures of three buses of inlet wires of different mutual inductors are monitored, the temperature data are analyzed to obtain different characteristics of the temperature data, the temperature data of the three buses are used as comparison temperature characteristics for judging operation loads, temperature influence factors of the current operation loads of the electric power system on the operation of the mutual inductor are eliminated, and faults of the mutual inductor are judged according to the different characteristics obtained by analyzing the temperature data. The invention can have accurate diagnosis effect on the insulation fault of the mutual inductor, the loosening fault of the joint of the mutual inductor and the internal fault of the mutual inductor, realize early diagnosis and fault finding of the fault of the mutual inductor and ensure the normal operation of the mutual inductor.
However, the above fault diagnosis technique has a poor effect in analyzing a deep fault with a complicated structure, and has a high requirement on the operator's ability.
Therefore, a new technical route is needed to solve the diagnosis effect and the diagnosis efficiency of the transformer.
Disclosure of Invention
The invention aims to provide an intelligent diagnosis system for a power transformer, aiming at the defects of the prior art. The system can monitor the temperature, the sound and the current of key parts such as the iron core, the secondary winding and the insulating medium of the power transformer in real time through the temperature monitoring module, the sound monitoring module and the current monitoring module, and transmits monitoring data to the data acquisition and storage module through the communication module, so that the current distribution, the change condition and the historical change trend of the temperature, the sound and the current of the transformer are obtained, and finally, the intelligent diagnosis of the power transformer is realized through the fault diagnosis module.
It is another object of the present invention to provide a diagnostic method based on decision tree classification to overcome the disadvantages of the prior art.
The technical scheme adopted by the invention is as follows:
a power transformer intelligent diagnostic system comprising: the device comprises a temperature monitoring module, a sound monitoring module, a current monitoring module, a data acquisition and storage module, a fault diagnosis module and a display and query module;
the temperature monitoring module is used for measuring temperature signals of the transformer iron core, the secondary winding and the insulating medium;
the sound monitoring module is used for measuring sound signals of the transformer iron core, the secondary winding and the insulating medium;
the current monitoring module is used for measuring a current signal of the secondary side of the mutual inductor;
the output ends of the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the input end of the data acquisition and storage module;
the data acquisition and storage module is bidirectionally connected with the fault diagnosis module, namely the output end of the data acquisition and storage module is connected with the input end of the fault diagnosis module, and the output end of the fault diagnosis module is connected with the input end of the data acquisition and storage module;
the display and query module and the storage module are connected with the fault diagnosis module in a bidirectional mode, namely the output end of the data acquisition and storage module is connected with the input end of the display and query module, and the output end of the display and query module is connected with the input end of the data acquisition and storage module.
Further, still include: a communication module; the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the data acquisition and storage module through a communication module;
the system can monitor the temperature, the sound and the current of the iron core, the secondary winding and the insulating medium of the power transformer in real time through the temperature monitoring module, the sound monitoring module and the current monitoring module, and transmit monitoring data to the data acquisition and storage module through the communication module, so that the current distribution, the change condition and the historical change trend of the temperature, the sound and the current of the transformer are obtained, and finally, the intelligent diagnosis of the power transformer is realized through the fault diagnosis module;
the result diagnosed by the fault diagnosis module is transmitted to the data acquisition and storage module and then is transmitted to the display and query module;
meanwhile, the display and query module can also be connected with the data acquisition and storage module to query the data stored in the data acquisition and storage module: the temperature monitoring module, the sound monitoring module and the current monitoring module detect signals, and the fault diagnosis module diagnoses results.
Furthermore, the temperature monitoring module is a fiber bragg grating temperature sensor which is arranged on an iron core, a secondary winding and an insulating medium of the power transformer, converts the acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits the monitoring data to the data acquisition and storage module through the communication module.
Furthermore, the sound monitoring module is a sound sensor which is arranged on an iron core, a secondary winding and an insulating medium of the power transformer, converts the acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits the monitoring data to the data acquisition and storage module through the communication module.
Further, the current monitoring module is an ammeter which is arranged on the secondary side of the power transformer, converts the acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits the monitoring data to the data acquisition and storage module through the communication module.
Further, the data acquisition and storage module adopts a personal computer and/or a cloud storage server; the data acquisition and storage module is used for storing information acquired by the fiber grating temperature sensor, the sound sensor and the ammeter;
the acquired information is synchronously uploaded to a cloud storage server, so that the personal computer is prevented from generating faults during operation, and the loss of monitoring data is prevented; meanwhile, by connecting the cloud storage server, the staff can access and analyze the stored data at any time, any place and any equipment.
Further, the display and query module is a notebook computer, a mobile phone and an IPAD.
A diagnosis method based on decision tree classification adopts the power mutual inductor intelligent diagnosis system, wherein a mutual inductor calculation model is stored in a fault diagnosis module, and the mutual inductor calculation model is a calculation model based on decision tree classification;
the method comprises the following steps:
firstly, learning and training a mutual inductor calculation model through an artificial intelligence algorithm;
and secondly, transmitting the temperature, sound and current data in the data acquisition and storage module to a fault diagnosis module in real time for analysis, thereby realizing the monitoring of real-time data in the operation of the equipment and completing the fault diagnosis in real time.
Furthermore, a mutual inductor calculation model (machine learning model) of the fault diagnosis module adopts a CLS algorithm which is a decision tree classification algorithm and adopts a tree building mode of recursion from top to bottom;
in the decision tree generated by the CLS algorithm, a node corresponds to an attribute of an object to be classified, an arc (i.e., a trunk) drawn by a certain node corresponds to a value of the attribute, and a leaf node corresponds to a classification result.
Further, the attributes of the object to be classified include: the sound of the mutual inductor, the secondary side current, the temperature of a secondary winding, the temperature of an iron core and the temperature of an insulating medium;
the value ranges of the characteristic attributes, namely the arcs led out by the nodes are respectively as follows:
value (secondary side current) { secondary side current is normal, secondary side current is abnormal };
value (secondary winding temperature) { secondary winding temperature is normal, secondary winding temperature is abnormal };
value (temperature at the iron core) { temperature at the iron core is normal and temperature at the iron core is abnormal };
value (insulating medium temperature) { insulating medium temperature is normal, insulating medium temperature is abnormal };
value (transformer sound) { transformer has abnormal sound, transformer has no abnormal sound };
the initial attribute table is AttrList ═ (current, temperature, abnormal sound).
Further, the mutual inductor calculation model of the application comprises a five-layer structure:
a first layer, comprising a node: a first-tier first node;
second tier, comprising 2 nodes: a second level first node, a second level second node;
a third layer, comprising 2 nodes: a third layer of first nodes and a third layer of second nodes;
a fourth layer comprising 4 nodes: a fourth level first node, a fourth level second node;
a fifth layer comprising: 2 nodes: a fifth layer first node, a fifth layer second node; (ii) a
Mutual inductor sound information is input into the first node of the first layer, and the nodes of the first layer generate 2 new node trees:
the judgment criterion of the node tree of the first layer first node-the second layer first node is as follows: the sound of the mutual inductor is normal, and the first node of the second layer is: outputting a result E, wherein the first node of the second layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first layer first node-the second layer second node is as follows: when the sound of the mutual inductor is abnormal, a second node of a second layer is input secondary side current information;
the second level second node generates 2 new node trees:
the judgment criterion of the node tree of the second layer second node-the third layer first node is as follows: the secondary side current is normal, and the third layer first node is input insulation temperature information;
the judgment criterion of the node tree of the second layer second node-the third layer second node is as follows: the secondary side current is abnormal, and a second node of a third layer is input iron core temperature information;
the third level first node generates 2 new node trees:
the judgment criterion of the node tree of the third layer first node-the fourth layer first node is as follows: the insulation temperature is normal, and the fourth layer first node is: outputting a result D; the first node of the fourth layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first node of the third layer to the second node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth layer second node is: outputting a result C; the second node of the fourth layer does not generate a new node tree any more;
the third layer of second nodes generates 2 new node trees:
the judgment criterion of the node tree of the third layer second node-the fourth layer third node is as follows: the temperature of the iron core is normal, and the third node of the fourth layer is as follows: outputting a result A; the fourth layer third node does not generate a new node tree any more;
the judgment criterion of the node tree of the third layer second node-the fourth node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth node of the fourth layer is input secondary winding temperature information;
the fourth node of the fourth layer generates 2 new node trees:
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer first node is as follows: the temperature of the secondary winding is normal, and a fifth layer first node is as follows: outputting a result D; the fifth layer first node does not generate a new node tree any more;
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer second node is as follows: secondary winding temperature anomaly, fifth layer second node: outputting a result B; the fifth layer second node does not generate a new node tree any more;
the application has the advantages that:
firstly, the system can monitor the temperature, sound and current of the iron core, the secondary winding and the insulating medium of the power transformer in real time through the temperature monitoring module, the sound monitoring module and the current monitoring module, and transmit monitoring data to the data acquisition and storage module through the communication module, so that the current distribution and change conditions and historical change trend of the temperature, sound and current of the transformer are obtained, and finally, the intelligent diagnosis of the power transformer is realized through the fault diagnosis module; the result diagnosed by the fault diagnosis module is transmitted to the data acquisition and storage module and then is transmitted to the display and query module 6; meanwhile, the display and query module can also be connected with the data acquisition and storage module to query the data stored in the data acquisition and storage module: the temperature monitoring module, the sound monitoring module and the current monitoring module detect signals, and the fault diagnosis module diagnoses results.
Secondly, data are collected through the sensor, the collected data are analyzed and compared, the fault type of the mutual inductor is obtained, and the problem that the fault type cannot be judged due to the fact that experience of workers is not rich in the prior art is solved.
Thirdly, an intelligent diagnosis method based on a decision tree is provided, and particularly, a decision tree calculation model with a 5-layer structure is provided, so that the fault diagnosis efficiency is greatly improved.
Drawings
The invention will be further described in detail with reference to examples of embodiments shown in the drawings to which, however, the invention is not restricted.
Fig. 1 is a design diagram of an intelligent diagnostic system for a power transformer according to embodiment 1.
Fig. 2 is a schematic diagram of learning example set T composed of 5 examples of embodiment 1.
Fig. 3 is a schematic diagram of generating a fault classification decision tree by applying the CLS algorithm in embodiment 1.
The reference numerals in fig. 1-3 are illustrated as follows:
the device comprises a temperature monitoring module 1, a sound monitoring module 2, a current monitoring module 3, a data acquisition and storage module 4, a fault diagnosis module 5 and a display and query module 6.
Detailed Description
the temperature monitoring module is used for measuring temperature signals of the transformer iron core, the secondary winding and the insulating medium;
the sound monitoring module is used for measuring sound signals of the transformer iron core, the secondary winding and the insulating medium;
the current monitoring module is used for measuring current signals of the two sides of the mutual inductor;
the output ends of the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the input end of the data acquisition and storage module;
the data acquisition and storage module is bidirectionally connected with the fault diagnosis module, namely the output end of the data acquisition and storage module is connected with the input end of the fault diagnosis module, and the output end of the fault diagnosis module is connected with the input end of the data acquisition and storage module;
the display and query module and the storage module are connected with the fault diagnosis module in a bidirectional mode, namely the output end of the data acquisition and storage module is connected with the input end of the display and query module, and the output end of the display and query module is connected with the input end of the data acquisition and storage module.
Further comprising: a communication module; the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the data acquisition and storage module through a communication module; the communication module adopts a power line carrier technology. The power carrier technology is integrated and then embedded into each power transformer, and the purpose of high-speed transmission of digital signals is achieved by adopting a carrier mode through taking an erected low-voltage power line as a medium for information transmission, so that communication among power transformer devices is achieved. And simultaneously, a spread spectrum communication technology is adopted to overcome the interference problem in a communication channel.
The system can monitor the temperature, the sound and the current of the iron core, the secondary winding and the insulating medium of the power transformer in real time through the temperature monitoring module, the sound monitoring module and the current monitoring module, and transmit monitoring data to the data acquisition and storage module through the communication module, so that the current distribution, the change condition and the historical change trend of the temperature, the sound and the current of the transformer are obtained, and finally, the intelligent diagnosis of the power transformer is realized through the fault diagnosis module; the result diagnosed by the fault diagnosis module is transmitted to the data acquisition and storage module and then is transmitted to the display and query module 6; meanwhile, the display and query module can also be connected with the data acquisition and storage module to query the data stored in the data acquisition and storage module: the temperature monitoring module, the sound monitoring module and the current monitoring module detect signals, and the fault diagnosis module diagnoses results.
The temperature monitoring module is a fiber bragg grating temperature sensor which is arranged on an iron core, a secondary winding and an insulating medium of the power transformer, converts acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits monitoring data to the data acquisition and storage module through the communication module.
The sound monitoring module is a sound sensor which is arranged on an iron core, a secondary winding and an insulating medium of the power transformer, converts acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits monitoring data to the data acquisition and storage module through the communication module.
The current monitoring module is an ammeter which is arranged on the secondary side of the power transformer, converts the acquired analog signals into digital signals through a high-speed high-precision analog-to-digital converter, and transmits the monitoring data to the data acquisition and storage module through the communication module.
The data acquisition and storage module adopts a personal computer and/or a cloud storage server; the data acquisition and storage module is used for storing information acquired by the fiber grating temperature sensor, the sound sensor and the ammeter;
the acquired information is synchronously uploaded to a cloud storage server, so that the personal computer is prevented from generating faults during operation, and the loss of monitoring data is prevented; meanwhile, by connecting the cloud storage server, the staff can access and analyze the stored data at any time, any place and any equipment.
The display and query module is a notebook computer, a mobile phone and an IPAD.
A power transformer intelligent diagnosis method adopts the power transformer intelligent diagnosis system of embodiment 1, a transformer calculation model is stored in a fault diagnosis module, and the transformer calculation model is subjected to learning training through an artificial intelligence algorithm; the temperature, sound and current data in the data acquisition and storage module are transmitted to the fault diagnosis module in real time for analysis, so that the real-time data can be monitored during the operation of the equipment, and the fault diagnosis can be completed in real time.
The mutual inductor calculation model (machine learning model) of the fault diagnosis module adopts a CLS algorithm which is a decision tree classification algorithm and adopts a tree building mode of recursion from top to bottom;
in the decision tree generated by the CLS algorithm, nodes correspond to the attributes of the objects to be classified, arcs drawn by a certain node correspond to the value of the attribute, and leaf nodes correspond to the classification result.
Specifically, the method is divided into: the mutual inductor calculation model adopts the following decision tree:
(1) the structure comprises a five-layer structure, wherein a first layer comprises a node: a first-tier first node;
second tier, comprising 2 nodes: a second level first node, a second level second node;
a third layer, comprising 2 nodes: a third layer of first nodes and a third layer of second nodes;
a fourth layer comprising 4 nodes: a fourth level first node, a fourth level second node;
a fifth layer comprising: 2 nodes: a fifth layer first node, a fifth layer second node; (ii) a
Mutual inductor sound information is input into the first node of the first layer, and the nodes of the first layer generate 2 new node trees:
the judgment criterion of the node tree of the first layer first node-the second layer first node is as follows: the sound of the mutual inductor is normal, and the first node of the second layer is: outputting a result E, wherein the first node of the second layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first layer first node-the second layer second node is as follows: when the sound of the mutual inductor is abnormal, a second node of a second layer is input secondary side current information;
the second level second node generates 2 new node trees:
the judgment criterion of the node tree of the second layer second node-the third layer first node is as follows: the secondary side current is normal, and the third layer first node is input insulation temperature information;
the judgment criterion of the node tree of the second layer second node-the third layer second node is as follows: the secondary side current is abnormal, and a second node of a third layer is input iron core temperature information;
the third level first node generates 2 new node trees:
the judgment criterion of the node tree of the third layer first node-the fourth layer first node is as follows: the insulation temperature is normal, and the fourth layer first node is: outputting a result D; the first node of the fourth layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first node of the third layer to the second node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth layer second node is: outputting a result C; the second node of the fourth layer does not generate a new node tree any more;
the third layer of second nodes generates 2 new node trees:
the judgment criterion of the node tree of the third layer second node-the fourth layer third node is as follows: the temperature of the iron core is normal, and the third node of the fourth layer is as follows: outputting a result A; the fourth layer third node does not generate a new node tree any more;
the judgment criterion of the node tree of the third layer second node-the fourth node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth node of the fourth layer is input secondary winding temperature information;
the fourth node of the fourth layer generates 2 new node trees:
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer first node is as follows: the temperature of the secondary winding is normal, and a fifth layer first node is as follows: outputting a result D; the fifth layer first node does not generate a new node tree any more;
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer second node is as follows: secondary winding temperature anomaly, fifth layer second node: outputting a result B; the fifth level second node no longer generates a new node tree.
Specifically, the transformer calculation model is set as follows:
the method comprises the following steps of carrying out fault classification on the transformer according to the characteristic attributes of key parts of the power transformer, wherein the three classification characteristic attributes are respectively as follows: current, temperature and abnormal sound; the classification results are: A. b, C, D, E are provided.
The value ranges of the characteristic attributes are respectively as follows:
value (current) { secondary side current is normal, secondary side current is abnormal }
Value (temperature) } secondary winding temperature is normal, secondary winding temperature is abnormal, iron core temperature is normal, iron core temperature is abnormal, insulating medium temperature is normal, and insulating medium temperature is abnormal
Value (abnormal sound) } (abnormal sound of mutual inductor, no abnormal sound of mutual inductor) }
The initial attribute table is Attrlist ═ (current, temperature, abnormal sound)
Example diagnostic results:
the above-mentioned embodiments are only for convenience of description, and are not intended to limit the present invention in any way, and those skilled in the art will understand that the technical features of the present invention can be modified or changed by other equivalent embodiments without departing from the scope of the present invention.
Claims (10)
1. An intelligent diagnostic system for a power transformer, comprising: the device comprises a temperature monitoring module, a sound monitoring module, a current monitoring module, a data acquisition and storage module, a fault diagnosis module and a display and query module;
the temperature monitoring module is used for measuring temperature signals of the transformer iron core, the secondary winding and the insulating medium;
the sound monitoring module is used for measuring sound signals of the transformer iron core, the secondary winding and the insulating medium;
the current monitoring module is used for measuring a current signal of the secondary side of the mutual inductor;
the output ends of the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the input end of the data acquisition and storage module;
the data acquisition and storage module is bidirectionally connected with the fault diagnosis module, namely the output end of the data acquisition and storage module is connected with the input end of the fault diagnosis module, and the output end of the fault diagnosis module is connected with the input end of the data acquisition and storage module;
the display and query module and the storage module are connected with the fault diagnosis module in a bidirectional mode, namely the output end of the data acquisition and storage module is connected with the input end of the display and query module, and the output end of the display and query module is connected with the input end of the data acquisition and storage module.
2. The intelligent diagnosis system for the power transformer according to claim 1, further comprising: a communication module; the temperature monitoring module, the sound monitoring module and the current monitoring module are connected with the data acquisition and storage module through a communication module;
the system can monitor the temperature, the sound and the current of the iron core, the secondary winding and the insulating medium of the power transformer in real time through the temperature monitoring module, the sound monitoring module and the current monitoring module, and transmit monitoring data to the data acquisition and storage module through the communication module, so that the current distribution, the change condition and the historical change trend of the temperature, the sound and the current of the transformer are obtained, and finally, the intelligent diagnosis of the power transformer is realized through the fault diagnosis module;
the result diagnosed by the fault diagnosis module is transmitted to the data acquisition and storage module and then is transmitted to the display and query module;
meanwhile, the display and query module can also be connected with the data acquisition and storage module to query the data stored in the data acquisition and storage module: the temperature monitoring module, the sound monitoring module and the current monitoring module detect signals, and the fault diagnosis module diagnoses results.
3. The intelligent diagnosis system for the power transformer of claim 1, wherein the temperature monitoring module is a fiber bragg grating temperature sensor, the fiber bragg grating temperature sensor is arranged on an iron core, a secondary winding and an insulating medium of the power transformer, the acquired analog signal is converted into a digital signal through a high-speed high-precision analog-to-digital converter, and the monitoring data is transmitted to the data acquisition and storage module through the communication module.
4. The intelligent diagnosis system for the power transformer according to claim 1, 2 or 3, wherein the sound monitoring module is a sound sensor, the sound sensor is arranged on the iron core, the secondary winding and the insulating medium of the power transformer, converts the acquired analog signal into a digital signal through a high-speed high-precision analog-to-digital converter, and transmits the monitoring data to the data acquisition and storage module through the communication module.
5. The intelligent diagnosis system for the power transformer as claimed in claim 4, wherein the current monitoring module is an ammeter, the ammeter is arranged at the secondary side of the power transformer, the acquired analog signal is converted into a digital signal through a high-speed high-precision analog-to-digital converter, and the monitoring data is transmitted to the data acquisition and storage module through the communication module.
6. The intelligent diagnosis system for the power transformer of claim 5, wherein the data acquisition and storage module adopts a personal computer and/or a cloud storage server; the data acquisition and storage module is used for storing information acquired by the fiber grating temperature sensor, the sound sensor and the ammeter;
the acquired information is synchronously uploaded to a cloud storage server, so that the personal computer is prevented from generating faults during operation, and the loss of monitoring data is prevented; meanwhile, by connecting the cloud storage server, the staff can access and analyze the stored data at any time, any place and any equipment.
7. The intelligent diagnosis system for the power transformer of claim 6, wherein the display and query module is a notebook computer, a mobile phone, or an IPAD.
8. A diagnosis method based on decision tree classification, characterized in that the power transformer intelligent diagnosis system according to any one of claims 1 to 7 is adopted to diagnose the power transformer, the fault diagnosis module stores a transformer calculation model, and the transformer calculation model is a calculation model based on decision tree classification.
9. The decision tree classification-based diagnosis method according to claim 8, wherein a mutual inductor calculation model of the fault diagnosis module adopts a CLS algorithm and adopts a tree building mode from top to bottom in a recursion manner;
in the decision tree generated by the CLS algorithm, a node corresponds to the attribute of an object to be classified, an arc (i.e., a trunk) drawn by a certain node corresponds to the value of the attribute, and a leaf node corresponds to the result of classification:
the attributes of the objects to be classified include: the sound of the mutual inductor, the secondary side current, the temperature of a secondary winding, the temperature of an iron core and the temperature of an insulating medium;
the value ranges of the characteristic attributes, namely the arcs led out by the nodes are respectively as follows:
value (secondary side current) { secondary side current is normal, secondary side current is abnormal };
value (secondary winding temperature) { secondary winding temperature is normal, secondary winding temperature is abnormal };
value (temperature at the iron core) { temperature at the iron core is normal and temperature at the iron core is abnormal };
value (insulating medium temperature) { insulating medium temperature is normal, insulating medium temperature is abnormal };
value (transformer sound) { transformer has abnormal sound, transformer has no abnormal sound };
the initial attribute table is AttrList ═ (current, temperature, abnormal sound).
10. The decision tree classification-based diagnostic method according to claim 8, wherein the mutual inductor computational model comprises a five-layer structure:
a first layer, comprising a node: a first-tier first node;
second tier, comprising 2 nodes: a second level first node, a second level second node;
a third layer, comprising 2 nodes: a third layer of first nodes and a third layer of second nodes;
a fourth layer comprising 4 nodes: a fourth level first node, a fourth level second node;
a fifth layer comprising: 2 nodes: a fifth layer first node, a fifth layer second node; (ii) a
Mutual inductor sound information is input into the first node of the first layer, and the nodes of the first layer generate 2 new node trees:
the judgment criterion of the node tree of the first layer first node-the second layer first node is as follows: the sound of the mutual inductor is normal, and the first node of the second layer is: outputting a result E, wherein the first node of the second layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first layer first node-the second layer second node is as follows: when the sound of the mutual inductor is abnormal, a second node of a second layer is input secondary side current information;
the second level second node generates 2 new node trees:
the judgment criterion of the node tree of the second layer second node-the third layer first node is as follows: the secondary side current is normal, and the third layer first node is input insulation temperature information;
the judgment criterion of the node tree of the second layer second node-the third layer second node is as follows: the secondary side current is abnormal, and a second node of a third layer is input iron core temperature information;
the third level first node generates 2 new node trees:
the judgment criterion of the node tree of the third layer first node-the fourth layer first node is as follows: the insulation temperature is normal, and the fourth layer first node is: outputting a result D; the first node of the fourth layer does not generate a new node tree any more;
the judgment criterion of the node tree of the first node of the third layer to the second node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth layer second node is: outputting a result C; the second node of the fourth layer does not generate a new node tree any more;
the third layer of second nodes generates 2 new node trees:
the judgment criterion of the node tree of the third layer second node-the fourth layer third node is as follows: the temperature of the iron core is normal, and the third node of the fourth layer is as follows: outputting a result A; the fourth layer third node does not generate a new node tree any more;
the judgment criterion of the node tree of the third layer second node-the fourth node of the fourth layer is as follows: the insulation temperature is abnormal, and the fourth node of the fourth layer is input secondary winding temperature information;
the fourth node of the fourth layer generates 2 new node trees:
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer first node is as follows: the temperature of the secondary winding is normal, and a fifth layer first node is as follows: outputting a result D; the fifth layer first node does not generate a new node tree any more;
the judgment criterion of the node tree of the fourth layer fourth node-the fifth layer second node is as follows: secondary winding temperature anomaly, fifth layer second node: outputting a result B; the fifth level second node no longer generates a new node tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011146437.8A CN112329821A (en) | 2020-10-23 | 2020-10-23 | Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011146437.8A CN112329821A (en) | 2020-10-23 | 2020-10-23 | Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112329821A true CN112329821A (en) | 2021-02-05 |
Family
ID=74310982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011146437.8A Withdrawn CN112329821A (en) | 2020-10-23 | 2020-10-23 | Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329821A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532315A (en) * | 2021-02-07 | 2021-03-19 | 湖北鑫英泰系统技术股份有限公司 | Optical cable fault positioning method and device based on distributed temperature measurement optical fiber |
| CN113447783A (en) * | 2021-08-30 | 2021-09-28 | 武汉格蓝若智能技术有限公司 | Voltage transformer insulation fault identification model construction method and device |
-
2020
- 2020-10-23 CN CN202011146437.8A patent/CN112329821A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532315A (en) * | 2021-02-07 | 2021-03-19 | 湖北鑫英泰系统技术股份有限公司 | Optical cable fault positioning method and device based on distributed temperature measurement optical fiber |
| CN112532315B (en) * | 2021-02-07 | 2021-04-30 | 湖北鑫英泰系统技术股份有限公司 | Optical cable fault positioning method and device based on distributed temperature measurement optical fiber |
| CN113447783A (en) * | 2021-08-30 | 2021-09-28 | 武汉格蓝若智能技术有限公司 | Voltage transformer insulation fault identification model construction method and device |
| CN113447783B (en) * | 2021-08-30 | 2021-11-26 | 武汉格蓝若智能技术有限公司 | Voltage transformer insulation fault identification model construction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650451B (en) | Converter transformer fault reason identification method and system | |
| WO2014135015A1 (en) | Network for online monitoring of power transformer at intelligent substation | |
| CN112329821A (en) | Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification | |
| CN102034019A (en) | Method for comprehensively estimating insulation state of sulfur hexafluoride electrical equipment | |
| CN213986651U (en) | Multi-state online monitoring system for lightning arrester | |
| CN108663581A (en) | A kind of secondary equipment of intelligent converting station test method | |
| CN104246522A (en) | A method and an apparatus for detecting a fault in an hvdc power transmission system | |
| CN106597196A (en) | State monitoring and intelligent diagnosis and analysis system and method for power transmission and transformation equipment | |
| CN111458652A (en) | Fault determination method, device and equipment for direct current charging pile | |
| CN104569751A (en) | Device and method for detecting insulating property of high-voltage ancillary equipment of electromobile | |
| CN102393929A (en) | State overhauling control method of distribution network equipment state assessment system | |
| CN106295240A (en) | A kind of Condition Assessment for Power Transformer method based on fuzzy mathematics | |
| CN103234576A (en) | State monitoring system for power devices in intelligent substations | |
| CN108376966A (en) | Intelligent substation anti-misoperation locking logic interval association relationship analysis method and system | |
| CN112630562A (en) | Switch cabinet fault identification method and device based on deep neural network | |
| CN113205127A (en) | Transformer self-diagnosis evaluation device and method based on edge calculation | |
| CN110299758A (en) | A kind of comprehensive on-line monitoring and diagnosis system of substation | |
| CN108388236A (en) | The Performance Test System of switch controller is automated on column | |
| CN105652137B (en) | A kind of substation's on-line monitoring and diagnosis method of model identification and device | |
| CN104569601A (en) | Device and method for detecting insulating property of high-voltage control box of electromobile | |
| CN204515021U (en) | The high voltage control box of electric automobile is carried out to the device of insulating property detection | |
| CN103675606A (en) | Bridge type direct-current fault monitoring alarm | |
| CN203535128U (en) | Crosslinked polyethylene high-voltage cable on-line monitoring and early warning system | |
| CN204515070U (en) | The high pressure ancillary apparatus wire harness of electric automobile is carried out to the device of insulating property detection | |
| CN115459449A (en) | Transformer substation monitoring method and system capable of analyzing operation performance of transformer in real time |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210205 |