CN116448934A - Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network - Google Patents
Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network Download PDFInfo
- Publication number
- CN116448934A CN116448934A CN202310492358.XA CN202310492358A CN116448934A CN 116448934 A CN116448934 A CN 116448934A CN 202310492358 A CN202310492358 A CN 202310492358A CN 116448934 A CN116448934 A CN 116448934A
- Authority
- CN
- China
- Prior art keywords
- oil
- gas
- transformer
- neural network
- self
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims abstract description 4
- 238000000926 separation method Methods 0.000 claims abstract description 4
- 238000010438 heat treatment Methods 0.000 claims description 12
- 238000004587 chromatography analysis Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
- G01N2030/8804—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86 automated systems
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Control Of Temperature (AREA)
Abstract
The invention discloses a fuzzy PID transformer oil chromatographic online monitoring method and system based on a self-adaptive neural network, which comprises the following steps: step 1) oil sample collection, after the detection time set by a user is up, opening an oil inlet valve by the system, and enabling transformer oil to enter an oil-gas separator through an oil inlet valve by means of self oil pressure; step 2) oil-gas separation, in the oil-gas separator, fault characteristic gas dissolved in oil is separated, residual oil enters an oil tank through oil circulation, and the extracted gas is separated by an oil chromatographic analyzer; and 3) detecting the gas, wherein the separated gas enters a gas concentration sensor, converting gas concentration detection information into a voltage signal, converting the voltage signal into a digital sequence signal by utilizing a high-precision A/D converter, and judging whether the running state of the transformer is abnormal or not according to an analysis result.
Description
Technical Field
The invention relates to the technical field of transformer monitoring, in particular to an online transformer oil chromatographic monitoring system.
Background
In the working process of the transformer oil chromatographic online monitoring system, the temperature difference of the field operation environment is difficult to control and the condition that the temperature difference is large can occur, and parts in the system have strict requirements on the temperature, and the transformer oil chromatographic online monitoring system cannot work or measure inaccurately at the excessively low temperature or the excessively high temperature, so that the monitoring data of the dissolved gas in the transformer oil cannot be uploaded or a large amount of invalid data can be generated. The environmental temperature is too low, and the oil chromatographic permeable membrane is damaged, once the permeable membrane is damaged, the oil in the oil chamber directly enters the air chamber to pollute the whole chromatographic column, the detector, the air pump and the quantitative chamber, and the core element of the instrument is possibly damaged. For this reason, the real-time monitoring of the operating conditions of the transformer equipment by the oil chromatography on-line monitoring device faces a serious challenge of environmental temperature variation.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides the online monitoring method and the online monitoring system for the oil chromatogram of the fuzzy PID transformer based on the self-adaptive neural network, which solve the influence of the environmental temperature on the detection of the oil chromatogram and effectively improve the dynamic performance and the steady-state precision of the system.
The purpose of the invention is realized in the following way: an online monitoring method for a fuzzy PID transformer oil chromatograph based on a self-adaptive neural network comprises the following steps:
step 1) oil sample collection, after the detection time set by a user is up, opening an oil inlet valve by the system, and enabling transformer oil to enter an oil-gas separator through an oil inlet valve by means of self oil pressure;
step 2) oil-gas separation, in the oil-gas separator, fault characteristic gas dissolved in oil is separated, residual oil enters an oil tank through oil circulation, and the extracted gas is separated by utilizing a chromatographic column;
and 3) detecting the gas, wherein the separated gas enters a gas concentration sensor, converting gas concentration detection information into a voltage signal, converting the voltage signal into a digital sequence signal by using a high-precision A/D converter, reading and analyzing by a manager through the digital sequence signal, and judging whether the running state of the transformer is abnormal or not according to an analysis result.
As the preferable technical scheme of the online monitoring method for the transformer oil chromatograph based on the fuzzy PID of the adaptive neural network, the method also comprises the following step 4): the environmental temperature is controlled in the process of the step 2) and the step 3), specifically:
step 4-1), arranging an oil-gas separator, a chromatographic column and a gas concentration sensor in an incubator, wherein a heating plate and a refrigerating fan are arranged in the incubator;
step 4-2), the temperature sensor in the incubator sends the acquired temperature data to the singlechip for processing;
and 4-3) analyzing and judging the acquired temperature by the singlechip, and when the temperature exceeds a set temperature range, starting the heating plate to heat or the refrigerating fan to refrigerate by sending a level control signal by the singlechip, so that the ambient temperature in the incubator is kept within a constant range.
As the optimal technical scheme of the online monitoring method for the transformer oil chromatograph based on the fuzzy PID of the self-adaptive neural network, the step 4-3) uses the neural network to combine with the fuzzy control when the temperature analysis and judgment are carried out, describes the fuzzy control propulsion fuzzy algorithm by using the layered structure of the neural network, and carries out fuzzy quantification by the input deviation and the deviation change rate of the controller.
As the optimal technical scheme of the fuzzy PID transformer oil chromatographic online monitoring method based on the self-adaptive neural network, the neural network learning algorithm is adopted to continuously change membership functions so as to approach control rules, 3 parameters Kp, ki and Kd of the PID are subjected to online self-adaptive setting, the learning capacity and the adaptability of an incubator system are improved, and the optimal control of the temperature is realized.
The utility model provides a fuzzy PID transformer oil chromatographic on-line monitoring system based on self-adaptation neural network, includes the transformer, be equipped with the oil pipe return circuit on the transformer, be equipped with the oil separator on the oil pipe return circuit, the transformer oil flows back to the oil tank after the oil separator, and the gas vent of oil separator is connected the oil chromatographic analyzer, oil separator, oil chromatographic analyzer are all arranged in the incubator.
As the optimal technical scheme of the fuzzy PID transformer oil chromatographic online monitoring system based on the self-adaptive neural network, the bottom of the oil tank is provided with the oil outlet, the top of the oil tank is provided with the oil return port, and the oil outlet is connected with the oil return port through the oil pipe loop.
As the optimal technical scheme of the fuzzy PID transformer oil chromatographic online monitoring system based on the self-adaptive neural network, a heating plate and a refrigerating fan are arranged in the constant temperature box.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the invention, through accurately controlling the temperature, the accurate uploading of the monitoring data of the dissolved gas in the transformer oil is ensured;
(2) The BP neural network learning algorithm is introduced on the basis of the self-adaptive fuzzy PID control, the fuzzy rule control and membership function are trained and optimized, the stable control of the constant tension of the winding system can be realized, the system performance is greatly improved, and the service life of the system is prolonged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a main program of the control system of the oil chromatography incubator in the invention.
FIG. 2 shows the structure of the adaptive neural network fuzzy PID oil chromatography incubator system.
FIG. 3 is a schematic block diagram of the control system of the oil chromatography incubator of the present invention.
FIG. 4 is a block diagram of the control system of the oil chromatography incubator according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
1-2, the online monitoring method for the oil chromatograph of the fuzzy PID transformer based on the self-adaptive neural network comprises the following steps:
step 1) oil sample collection, after the detection time set by a user is up, opening an oil inlet valve by the system, and enabling transformer oil to enter an oil-gas separator through an oil inlet valve by means of self oil pressure;
step 2) oil-gas separation, in the oil-gas separator, fault characteristic gas dissolved in oil is separated, residual oil enters an oil tank through oil circulation, and the extracted gas is separated by an oil chromatographic analyzer;
step 3) gas detection, wherein the separated gas enters a gas concentration sensor, gas concentration detection information is converted into a voltage signal, the voltage signal is converted into a digital sequence signal by a high-precision A/D converter, a manager reads and analyzes the digital sequence signal, and whether the running state of the transformer is abnormal or not is judged according to an analysis result;
step 4): the environmental temperature is controlled in the process of the step 2) and the step 3), specifically:
step 4-1), arranging an oil-gas separator, a chromatographic column and a gas concentration sensor in an incubator, wherein a heating plate and a refrigerating fan are arranged in the incubator;
step 4-2), the temperature sensor in the incubator sends the acquired temperature data to the singlechip for processing;
and 4-3) the singlechip analyzes and judges the acquired temperature, when the temperature exceeds a set temperature range, the singlechip starts a heating plate to heat or a refrigerating fan to refrigerate, so that the ambient temperature in the incubator is kept in a constant range, a neural network is used for combining with fuzzy control when the temperature is analyzed and judged, a neural network layered structure is used for describing a fuzzy control propulsion fuzzy algorithm, a controller inputs deviation and deviation change rate to carry out fuzzy quantization, a membership function is continuously changed by adopting a neural network learning algorithm to approach a control rule, 3 parameters Kp, ki and Kd of PID are subjected to online self-adaptive setting, the learning capacity and adaptability of the incubator system are improved, and the optimal control on the temperature is realized.
Specifically, an initial temperature at which the oil chromatograph can normally operate is set, the temperature received by the temperature sensor is sent to the singlechip to be compared with the set initial temperature, if the temperature is higher than the set initial temperature, the singlechip starts the refrigeration fan to cool the incubator through transmitting the level control signal, otherwise, if the temperature is lower than the set initial temperature, the singlechip starts the heating plate to heat through transmitting the level control signal, so that the system can stably monitor the temperature range in which the equipment can normally operate.
In order to further improve the precision, the controller has stronger self-learning ability and adaptability by adopting the combination of a neural network and fuzzy control; and comparing the temperature obtained by the temperature sensor with the temperature obtained by the temperature sensor to obtain an error e of the temperature and the conversion rate of the error as input values of fuzzy control according to the temperature which can be normally operated by the oil chromatograph on-line monitoring system.
In order to achieve higher self-adaptability of the system, a neural network is adopted to carry out learning algorithm to carry out online self-adaptive adjustment on three parameters Kp, ki and Kd of PID so as to improve the learning ability and self-adaptive ability of the oil chromatography online monitoring system, and therefore temperature control is more accurate.
The online monitoring system based on the adaptive neural network fuzzy PID transformer oil chromatograph comprises a transformer, wherein an oil pipe loop is arranged on the transformer, an oil-gas separator is arranged on the oil pipe loop, transformer oil flows back into an oil tank after passing through the oil-gas separator, an exhaust port of the oil-gas separator is connected with an oil chromatograph, the oil-gas separator and the oil chromatograph are both arranged in an incubator, an oil outlet is arranged at the bottom of the oil tank, an oil return port is arranged at the top of the oil tank, the oil outlet is connected with the oil return port through the oil pipe loop, and a heating plate and a refrigerating fan are arranged in the incubator.
Specifically, the microprocessor selects an AT89C5 singlechip as a host of the control system of the incubator, and the singlechip has the advantages of flexible control, low voltage, low price and the like.
When the temperature sensor transmits signals, the problems of multipoint temperature measurement switching errors, amplifying circuit zero drift errors and the like exist, and electromagnetic interference exists in monitoring due to the environment of a monitoring site. The sensor used in the design of the incubator is a digital temperature sensor DS18B20, and the sensor has stronger environment-resistant electromagnetic interference, and has the advantages of smaller volume, accurate measurement and wide temperature measurement range.
The temperature control module mainly comprises a relay, a resistor, a heating plate, a triode, a fan and the like; when the change of the ambient temperature is monitored, the singlechip controls the relay to act through the on-off of the triode so as to start the heating plate to heat or control the fan to refrigerate.
The above description of the embodiments is only for aiding in the understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (7)
1. The online monitoring method for the transformer oil chromatograph based on the fuzzy PID of the self-adaptive neural network is characterized by comprising the following steps:
step 1) oil sample collection, after the detection time set by a user is up, opening an oil inlet valve by the system, and enabling transformer oil to enter an oil-gas separator through an oil inlet valve by means of self oil pressure;
step 2) oil-gas separation, in the oil-gas separator, fault characteristic gas dissolved in oil is separated, residual oil enters an oil tank through oil circulation, and the extracted gas is separated by an oil chromatographic analyzer;
and 3) detecting the gas, wherein the separated gas enters a gas concentration sensor, converting gas concentration detection information into a voltage signal, converting the voltage signal into a digital sequence signal by using a high-precision A/D converter, reading and analyzing by a manager through the digital sequence signal, and judging whether the running state of the transformer is abnormal or not according to an analysis result.
2. The online monitoring method for the oil chromatograph of the fuzzy PID transformer based on the adaptive neural network according to claim 1, further comprising the following steps: the environmental temperature is controlled in the process of the step 2) and the step 3), specifically:
step 4-1), arranging an oil-gas separator, a chromatographic column and a gas concentration sensor in an incubator, wherein a heating plate and a refrigerating fan are arranged in the incubator;
step 4-2), the temperature sensor in the incubator sends the acquired temperature data to the singlechip for processing;
and 4-3) analyzing and judging the acquired temperature by the singlechip, and when the temperature exceeds a set temperature range, starting the heating plate to heat or the refrigerating fan to refrigerate by sending a level control signal by the singlechip, so that the ambient temperature in the incubator is kept within a constant range.
3. The online monitoring method for the transformer oil chromatograph based on the fuzzy PID of the self-adaptive neural network according to claim 2, wherein the step 4-3) uses the neural network to combine with the fuzzy control when the temperature analysis and judgment are carried out, describes a fuzzy control pushing fuzzy algorithm by using a neural network layered structure, and carries out fuzzy quantification on the input deviation and the deviation change rate of the controller.
4. The online monitoring method for the fuzzy PID transformer oil chromatograph based on the self-adaptive neural network according to claim 3, wherein a neural network learning algorithm is adopted to continuously change membership functions so as to approach a control rule, 3 parameters Kp, ki and Kd of the PID are subjected to online self-adaptive setting, the learning capacity and the adaptability of an incubator system are improved, and the optimal control of the temperature is realized.
5. The utility model provides a fuzzy PID transformer oil chromatographic on-line monitoring system based on self-adaptation neural network, includes the transformer, its characterized in that is equipped with the oil pipe return circuit on the transformer, is equipped with oil separator on the oil pipe return circuit, and the transformer oil flows back to the oil tank after oil separator, and oil separator's gas vent is connected oil chromatographic analyzer, oil separator, oil chromatographic analyzer are all arranged in the thermostated container.
6. The online monitoring system for the oil chromatography of the fuzzy PID transformer oil based on the adaptive neural network according to claim 5, wherein an oil outlet is arranged at the bottom of the oil tank, an oil return port is arranged at the top of the oil tank, and the oil outlet is connected with the oil return port through an oil pipe loop.
7. The online monitoring system for transformer oil chromatography based on fuzzy PID of adaptive neural network according to claim 5, wherein a heating plate and a refrigerating fan are arranged in the incubator.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310492358.XA CN116448934A (en) | 2023-05-05 | 2023-05-05 | Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310492358.XA CN116448934A (en) | 2023-05-05 | 2023-05-05 | Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116448934A true CN116448934A (en) | 2023-07-18 |
Family
ID=87132075
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310492358.XA Pending CN116448934A (en) | 2023-05-05 | 2023-05-05 | Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116448934A (en) |
-
2023
- 2023-05-05 CN CN202310492358.XA patent/CN116448934A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN201335967Y (en) | On-line monitoring system for emission of industrial fumes and flue gases | |
US5400641A (en) | Transformer oil gas extractor | |
US9476022B1 (en) | Instrumented and controlled fermentation system and process with VOC recovery | |
CN105973954A (en) | Oxygen content calibration gas sampling device and online oxygen content calibration method | |
CN105137107A (en) | Full-automatic sampling and analyzing system and detecting method | |
CN115221809A (en) | Temperature simulation method, temperature control method and system of semiconductor waste gas treatment equipment | |
CN210776342U (en) | Transformer oil chromatogram on-line monitoring constant temperature equipment | |
CN209198394U (en) | VOCs on-line monitoring system | |
CN116448934A (en) | Fuzzy PID transformer oil chromatographic online monitoring method and system based on self-adaptive neural network | |
CN110988260A (en) | Gas concentration measuring device and method | |
CN212568647U (en) | High-temperature pretreatment device for volatile organic compounds in pollution source | |
CN206990228U (en) | A kind of quick production testing frock of air-conditioner with fixed frequency outdoor unit | |
CN109346749B (en) | Fuel cell stack tail gas detection module | |
CA3109321A1 (en) | Analysis of a gas dissolved in an insulating medium of a high-voltage device | |
CN114235380B (en) | Low-pressure high-flow overflow valve test system and test method thereof | |
CN207176085U (en) | A kind of fully automatic high temperature high pressure desorbing electrolytic control system | |
CN210051719U (en) | Automatic on-line detection device for crude oil hydrogen sulfide | |
GB2616385A (en) | Gas chromatography systems and methods with diagnostic and predictive module | |
CN112213277A (en) | Oil-immersed equipment oil way control method and device | |
CN112147079A (en) | Oil gas monitoring device with filtering capability | |
CN212410421U (en) | Fault monitoring device with anti-noise function | |
CN110333708A (en) | Based on the associated diagnosis control method of Hydraulic Power Unit technical water supply water pressure data, system, storage medium and terminal | |
CN205080146U (en) | Full -automatic sampling analysis system | |
CN217442300U (en) | Digital intelligent monitoring control device for water quality of circulating water of indirect air cooling unit | |
CN216955338U (en) | Gas dehydration sampling mechanism and dynamic detection system thereof |
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 |