An on-line monitoring system and method for dissolved gases in oil based on spectroscopic principles
By using an online monitoring system for dissolved gases in oil based on spectral principles, transformer anomalies can be identified by sound and vibration data, triggering online monitoring of transformer oil chromatography. This solves the problem of wasted carrier gas and improves the accuracy and efficiency of transformer monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING HUADIAN YUNTONG POWER TECH CO LTD
- Filing Date
- 2026-02-10
- Publication Date
- 2026-05-29
AI Technical Summary
In existing online transformer oil chromatography monitoring systems, carrier gas consumption is severely wasteful and requires a large amount of maintenance work, especially since the periodic consumption during normal transformer operation leads to unnecessary waste.
An online monitoring system for dissolved gases in oil based on the principle of spectroscopy is adopted. When the monitoring controller identifies transformer abnormalities, it triggers online monitoring of transformer oil chromatography. Data is collected using sound and vibration acquisition modules, and the data is processed and calibrated to identify abnormal points and assess the transformer status, thereby triggering the operation of the online oil chromatography monitoring module.
This reduces carrier gas consumption when the transformer malfunctions, improves the accuracy and efficiency of monitoring, and reduces maintenance workload.
Smart Images
Figure CN122108973A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of transformer online monitoring technology, specifically to an online monitoring system and method for dissolved gases in oil based on the principle of spectroscopy. Background Technology
[0002] Oil-immersed transformers are an important type of equipment widely used in power systems. They transmit and convert electrical energy by immersing the coils and iron core in transformer oil, utilizing the oil's insulation and heat dissipation properties.
[0003] Transformer oil plays two key roles here: first, as an insulating medium, it prevents discharge between coils and between coils and the iron core; second, as a cooling medium, it carries away the heat generated by the coils and maintains the normal operating temperature of the transformer.
[0004] When an oil-immersed transformer malfunctions during operation, the transformer oil decomposes and releases gases such as methane, ethane, ethylene, acetylene, and hydrogen, which dissolve in the oil. To monitor faults in oil-immersed transformers, existing technologies employ online transformer oil chromatography monitoring systems to monitor the dissolved gas composition in the transformer oil in real time, thereby enabling the monitoring of transformer faults.
[0005] However, in transformer oil chromatography online monitoring systems, carrier gas plays a crucial role. It helps deliver the separated gas to the chromatographic column for analysis. However, carrier gas is typically stored in cylinders, which need to be replaced promptly after depletion; otherwise, it will affect the normal operation of the system and the accuracy of the monitoring results. However, transformer oil chromatography online monitoring systems use a timed monitoring method. Even when the transformer is in normal operation, the carrier gas is still consumed at set intervals, resulting in waste and increasing the workload of replacement and maintenance. Summary of the Invention
[0006] This invention provides an online monitoring system and method for dissolved gases in oil based on the principle of spectroscopy. When an anomaly is detected in the transformer through pre-monitoring, the online monitoring system for transformer oil chromatography is triggered to determine the anomaly, thereby reducing the consumption of carrier gas.
[0007] An online monitoring system for dissolved gases in oil based on spectral principles, comprising:
[0008] The monitoring controller is communicatively connected to the online transformer oil chromatography monitoring module, which is suitable for identifying the transformer's status and triggering the online transformer oil chromatography monitoring module to operate when an abnormality is detected.
[0009] The transformer oil chromatography online monitoring module is connected to the transformer and is suitable for acquiring data on dissolved gases in transformer oil.
[0010] Furthermore, the monitoring controller includes at least one online sound acquisition module and at least one online vibration acquisition module, wherein;
[0011] The online sound acquisition module is suitable for acquiring sound data from transformers.
[0012] The vibration online acquisition module is suitable for collecting vibration data at transformers.
[0013] Furthermore, the online sound acquisition module includes at least one transformer sound acquisition unit and at least one ambient sound acquisition unit;
[0014] The transformer sound acquisition unit is installed on the transformer to capture the sound data generated by the transformer;
[0015] An ambient sound acquisition unit is installed around the transformer to capture ambient sound data around the transformer.
[0016] Furthermore, the vibration online acquisition module includes at least one transformer vibration acquisition unit and at least one environmental vibration acquisition unit;
[0017] The transformer vibration acquisition unit is installed on the transformer to capture the vibration data generated by the transformer.
[0018] An environmental vibration acquisition unit is installed around the transformer to capture environmental vibration data around the transformer.
[0019] Furthermore, it also includes a data processing module, which is configured to acquire sound data collected by the online sound acquisition module; and acquire vibration data collected by the online vibration acquisition module; and analyze the acquired sound data and vibration data to obtain the analysis results of the transformer.
[0020] Furthermore, the data processing module includes a sound data processing unit and a vibration data processing unit, wherein;
[0021] The sound data processing unit is configured to perform a first calibration on the sound data generated by the transformer using ambient sound data to obtain the transformer sound data.
[0022] The vibration data processing unit is configured to calibrate the environmental vibration data using the environmental vibration data to obtain transformer vibration data.
[0023] Furthermore, the data processing module also includes an evaluation unit configured to perform a second calibration on the transformer sound data using transformer vibration data; and to identify the abnormal points of the transformer by analyzing the calibrated transformer sound data.
[0024] Furthermore, it also includes a transformer condition assessment module, which is configured to assess the condition of the transformer based on the identified anomalies. When an anomaly is detected in the transformer, the online transformer oil chromatography monitoring module is triggered to analyze the data of dissolved gases in the transformer oil to determine the condition of the transformer.
[0025] Secondly, embodiments of the present invention provide an online monitoring method for dissolved gases in oil based on spectral principles, comprising the following steps:
[0026] Construct a transformer sound recognition model;
[0027] Acquire sound and vibration data from the transformer and calibrate them separately;
[0028] The vibration data was used to further calibrate the sound data;
[0029] The calibrated transformer sound data is input into the transformer sound recognition model to obtain the transformer's anomalies;
[0030] Anomalies in the transformer are assessed to determine its condition.
[0031] When an abnormality is detected in the transformer, the online transformer oil chromatography monitoring module is triggered.
[0032] The transformer status is updated using the results from the online transformer oil chromatography monitoring module.
[0033] Furthermore, further calibration of the sound data using vibration data includes:
[0034] Use vibration data to generate corresponding sound data;
[0035] The generated sound data is used to calibrate the sound data acquired at the transformer.
[0036] The beneficial effects of the above-mentioned technical solution provided by the embodiments of the present invention are as follows: The present invention utilizes the sound characteristics of transformers when they have faults to construct sound characteristics for pre-monitoring of transformers. When an abnormality is detected in the transformer, the transformer oil chromatography online monitoring system is triggered to determine the abnormality, thereby reducing the consumption of carrier gas.
[0037] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.
[0038] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0039] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:
[0040] Figure 1 This is a schematic diagram of the structure of the online dissolved gas monitoring system in oil disclosed in an embodiment of the present invention;
[0041] Figure 2 This is a schematic flowchart of the online monitoring method for dissolved gases in oil disclosed in an embodiment of the present invention.
[0042] Figure label:
[0043] 1. Transformer oil chromatography online monitoring module; 2. Monitoring controller; 21. Sound online acquisition module; 211. Transformer sound acquisition unit; 212. Ambient sound acquisition unit; 22. Vibration online acquisition module; 221. Transformer vibration acquisition unit; 222. Ambient vibration acquisition unit; 23. Data processing module; 231. Sound data processing unit; 232. Vibration data processing unit; 233. Evaluation unit; 24. Transformer condition evaluation module. Detailed Implementation
[0044] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0045] In existing technologies, transformer oil chromatography online monitoring systems include a gas acquisition section and a gas analysis section. The gas analysis section uses a chromatography module, mainly composed of a chromatographic column and gas sensors, responsible for detecting and converting the separated gas components. The chromatographic column separates gases based on their different properties, while the gas sensors convert gas concentrations into electrical signals. During operation, a carrier gas is used to input the acquired gas into the chromatography module for analysis.
[0046] During the above testing process, due to the limited capacity of the carrier gas cylinder, when the carrier gas pressure indication is lower than the set value, it is necessary to close the main valve of the carrier gas cylinder and replace it with a new carrier gas cylinder. However, testing when the transformer is not in a faulty state will continuously consume the carrier gas in the cylinder.
[0047] Based on this, such as Figure 1As shown, this invention proposes an online monitoring system for dissolved gases in oil based on the principle of spectroscopy, comprising: a monitoring controller 2 and an online oil chromatography monitoring module. The monitoring controller 2 is communicatively connected to the online transformer oil chromatography monitoring module 1, and is adapted to identify the state of the transformer. When an abnormality is detected in the transformer, the online transformer oil chromatography monitoring module 1 is triggered to run. The online transformer oil chromatography monitoring module 1 is connected to the transformer and is adapted to acquire data on dissolved gases in the transformer oil.
[0048] The online oil chromatography monitoring module uses the existing online transformer oil chromatography monitoring system.
[0049] In order to achieve the above-mentioned triggering of the transformer oil chromatography online monitoring module 1 based on transformer anomalies, the monitoring controller 2 includes at least one sound online acquisition module 21 and at least one vibration online acquisition module 22, which are used to collect data at the transformer.
[0050] Among them, the online sound acquisition module 21 is suitable for acquiring sound data at the transformer.
[0051] The online sound acquisition module 21 includes at least one transformer sound acquisition unit 211 and at least one ambient sound acquisition unit 212.
[0052] The transformer sound acquisition unit 211 is installed on the transformer and is used to capture the sound data generated by the transformer.
[0053] The ambient sound acquisition unit 212 is installed around the transformer to capture ambient sound data around the transformer.
[0054] The transformer sound acquisition unit 211 and the ambient sound acquisition unit 212 use sound sensors.
[0055] Next, the collected sound data needs to be processed and compared; a data processing module 23 is also provided.
[0056] The data processing module 23 includes a sound data processing unit 231, which is used to process the acquired sound data.
[0057] The processing includes:
[0058] 1. Import the sound data and ambient sound data generated by the transformer;
[0059] 2. Perform preprocessing on the ambient sound data to remove high-frequency noise or unwanted components;
[0060] 3. Perform spectral analysis on the sound data generated by the transformer and the ambient sound data respectively. Use Fourier transform to convert the sound signal from the time domain to the frequency domain to obtain their respective spectrum diagrams.
[0061] 4. Compare the similarity in the frequency spectrum between the sound data generated by the transformer and the ambient sound data, and identify the frequency components that they share;
[0062] 5. Using an adaptive filtering algorithm, based on the spectral characteristics of the ambient sound data, remove the corresponding ambient sound components from the sound data generated by the transformer.
[0063] The purpose of the above data processing is to separate the ambient sound from the sound data generated by the transformer, which is often mixed with ambient sound, and to perform the first calibration to obtain the sound data generated by the primary transformer.
[0064] Among them, the vibration online acquisition module 22 is suitable for acquiring vibration data at the transformer.
[0065] The vibration online acquisition module 22 includes at least one transformer vibration acquisition unit 221 and at least one environmental vibration acquisition unit 222;
[0066] The transformer vibration acquisition unit 221 is installed on the transformer and is used to capture the vibration data generated by the transformer.
[0067] The environmental vibration acquisition unit 222 is installed around the transformer to capture environmental vibration data around the transformer.
[0068] The transformer vibration acquisition unit 221 and the environmental vibration acquisition unit 222 both use vibration sensors.
[0069] Next, the collected vibration data needs to be processed and compared; a data processing module 23 is also provided.
[0070] The data processing module 23 includes a vibration data processing unit 232, which is used to process the acquired vibration data.
[0071] The processing includes:
[0072] 1. Preprocess the environmental vibration data to remove high-frequency noise or unwanted components;
[0073] 2. Analyzing the correlation between transformer-generated vibration data and environmental vibration data can be achieved by calculating the cross-correlation function or coherence function of the two signals. If the two signals are highly correlated within a certain frequency range, then this part of the signal is likely environmental vibration.
[0074] 3. Based on the results of correlation analysis, determine the components in the vibration data generated by the transformer that correspond to environmental vibrations;
[0075] 4. Using an adaptive filtering algorithm, based on the characteristics of the environmental vibration data, the corresponding environmental vibration components are removed from data a to achieve effective signal separation and obtain the vibration data generated by the transformer.
[0076] The purpose of the above data processing is to separate the environmental vibration from the vibration data generated by the transformer, thereby achieving calibration and obtaining the vibration data generated by the transformer.
[0077] The data processing module 23 also includes an evaluation unit 233, configured to perform a second calibration on the transformer sound data using transformer vibration data. After obtaining the sound data and vibration data generated by the transformer using the above steps, the second calibration is performed on the sound data generated by the transformer using the vibration data, including the following steps:
[0078] Feature identification is performed on the vibration data generated by the transformer to extract the inherent vibration data.
[0079] Spectral analysis was performed on the natural vibration data to obtain its spectral characteristics;
[0080] Extracting key features from spectral analysis;
[0081] Based on the vibration characteristics and acoustic principles of transformers, a sound synthesis model is constructed to convert the extracted vibration features into sound data, thereby obtaining verification sound data.
[0082] The sound data generated by the transformer and the verification sound data were subjected to spectral analysis. Fourier transform was used to convert the sound signals from the time domain to the frequency domain to obtain their respective spectrum diagrams.
[0083] Compare the similarity in the frequency spectrum between the sound data generated by the transformer and the verification sound data to identify the frequency components they share.
[0084] An adaptive filtering algorithm is used to remove the corresponding verification sound data components from the sound data generated by the transformer based on the spectral characteristics of the verification sound data.
[0085] The purpose of the above operation is to further calibrate the sound data generated from the transformer after the first calibration, in order to eliminate the noise generated by the normal operation vibration of the transformer itself.
[0086] The evaluation unit 233 is also used to identify the abnormal points of the transformer by analyzing the calibrated transformer sound data.
[0087] The steps for anomaly identification include:
[0088] Establish a transformer fault mode library, collect sound signals generated during various equipment faults, process and extract features from them, associate the extracted feature parameters with fault types, and establish a fault mode library.
[0089] Pattern recognition and classification involves extracting features from the secondary calibrated sound data and matching and comparing them with feature parameters in the fault mode library.
[0090] Support vector machines are used to classify and identify the sound data after secondary calibration.
[0091] Based on the classification results, the abnormal points (fault points) existing in the output transformer are identified.
[0092] It also includes a transformer condition assessment module 24, which is configured to assess the condition of the transformer based on the identified anomalies. When an anomaly is detected in the transformer, the transformer oil chromatography online monitoring module 1 is triggered to analyze the data of dissolved gases in the transformer oil to determine the condition of the transformer.
[0093] When an abnormal transformer condition is detected, the transformer oil chromatography online monitoring module 1 is triggered to run. The transformer oil chromatography online monitoring module 1 is connected to the transformer and is suitable for obtaining data on dissolved gases in the transformer oil.
[0094] A method for online monitoring of dissolved gases in oil based on spectral principles includes the following steps:
[0095] S1, Construct a transformer sound recognition model;
[0096] S2, acquire sound and vibration data from the transformer and calibrate them respectively;
[0097] S3 uses vibration data to further calibrate sound data;
[0098] S31, further calibration of sound data using vibration data includes:
[0099] S32 generates corresponding sound data using vibration data;
[0100] S33 uses the generated sound data to calibrate the sound data acquired at the transformer.
[0101] S4, input the calibrated transformer sound data into the transformer sound recognition model to obtain the transformer's abnormal points;
[0102] S5 assesses the abnormal points of the transformer to obtain the transformer's status;
[0103] S6, when there is an abnormality in the transformer's condition, the transformer oil chromatography online monitoring module 1 is triggered to run;
[0104] S7, update the transformer status using the results of the online transformer oil chromatography monitoring module 1.
[0105] This invention utilizes the acoustic characteristics of transformers when they malfunction to construct an acoustic feature for pre-monitoring of transformers. When an anomaly is detected in the transformer, it triggers the online transformer oil chromatography monitoring system to determine the anomaly, thereby reducing carrier gas consumption.
[0106] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.
[0107] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.
[0108] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.
[0109] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.
[0110] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.
[0111] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that the various embodiments can be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."
Claims
1. An online monitoring system for dissolved gases in oil based on the principle of spectroscopy, characterized in that, include: The monitoring controller is communicatively connected to the online transformer oil chromatography monitoring module, which is suitable for identifying the transformer's status and triggering the online transformer oil chromatography monitoring module to operate when an abnormality is detected. The transformer oil chromatography online monitoring module is connected to the transformer and is suitable for acquiring data on dissolved gases in transformer oil.
2. The system as described in claim 1, characterized in that, The monitoring controller includes at least one online sound acquisition module and at least one online vibration acquisition module, wherein; The online sound acquisition module is suitable for acquiring sound data from transformers. The vibration online acquisition module is suitable for collecting vibration data at transformers.
3. The system as described in claim 2, characterized in that, The online sound acquisition module includes at least one transformer sound acquisition unit and at least one ambient sound acquisition unit; The transformer sound acquisition unit is installed on the transformer to capture the sound data generated by the transformer; An ambient sound acquisition unit is installed around the transformer to capture ambient sound data around the transformer.
4. The system as described in claim 3, characterized in that, The vibration online acquisition module includes at least one transformer vibration acquisition unit and at least one environmental vibration acquisition unit; The transformer vibration acquisition unit is installed on the transformer to capture the vibration data generated by the transformer. An environmental vibration acquisition unit is installed around the transformer to capture environmental vibration data around the transformer.
5. The system as described in claim 4, characterized in that, It also includes a data processing module, which is configured to acquire sound data collected by the online sound acquisition module; and acquire vibration data collected by the online vibration acquisition module; and analyze the acquired sound data and vibration data to obtain the analysis results of the transformer.
6. The system as described in claim 5, characterized in that, The data processing module includes a sound data processing unit and a vibration data processing unit, wherein; The sound data processing unit is configured to perform a first calibration on the sound data generated by the transformer using ambient sound data to obtain the transformer sound data. The vibration data processing unit is configured to calibrate the environmental vibration data using the environmental vibration data to obtain transformer vibration data.
7. The system as described in claim 6, characterized in that, The data processing module also includes an evaluation unit configured to perform a second calibration of the transformer sound data using transformer vibration data; and to identify the abnormal points of the transformer by analyzing the calibrated transformer sound data.
8. The system as described in claim 7, characterized in that, It also includes a transformer condition assessment module, which is configured to assess the condition of the transformer based on the identified anomalies. When an anomaly is detected in the transformer, the online transformer oil chromatography monitoring module is triggered to analyze the data of dissolved gases in the transformer oil to determine the condition of the transformer.
9. A method for online monitoring of dissolved gases in oil based on the principle of spectroscopy, characterized in that, Includes the following steps: Construct a transformer sound recognition model; Acquire sound and vibration data from the transformer and calibrate them separately; The vibration data was used to further calibrate the sound data; The calibrated transformer sound data is input into the transformer sound recognition model to obtain the transformer's anomalies; Anomalies in the transformer are assessed to determine its condition. When an abnormality is detected in the transformer, the online transformer oil chromatography monitoring module is triggered. The transformer status is updated using the results from the online transformer oil chromatography monitoring module.
10. The method as described in claim 9, characterized in that, Further calibration of sound data using vibration data includes: Use vibration data to generate corresponding sound data; The generated sound data is used to calibrate the sound data acquired at the transformer.