Oil temperature early warning method and device for forced oil circulation water-cooled transformer and storage medium

Abstract

The invention discloses an oil temperature early warning method and device for a forced oil circulation water-cooled transformer and a storage medium. The method comprises the steps that the oil temperature and related data of the forced oil circulation water-cooled transformer of a hydropower station are collected in real time; the collected data is remotely transmitted to an industrial internet platform big data center; processing the received data: cleaning the data, and smoothing the data; the operation parameters, the oil temperature data, the oil flow data, the current data, the oil level data, the environment temperature data and the historical oil temperature data of the transformer are input into a Hupfield neural network model of an industrial internet platform, the monitored oil temperature data are predicted in real time, and a predicted value is obtained; setting early warning dynamic thresholds of different levels according to the predicted value; and the processed actually measured oil temperature data are compared with an early warning threshold value of predicted value deviation, and whether the current oil temperature exceeds the early warning threshold value or not is judged. And the operation safety of the forced oil circulation water-cooled transformer is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to an oil temperature early warning method, a device and a storage medium for a forced oil circulation water-cooled transformer. Background Art

[0002] During the construction period of hydropower projects, the forced oil circulation water-cooled transformer is a commonly used power equipment in the power system. Its working principle is to transfer the heat inside the transformer to the cooler through oil circulation, and then dissipate the heat to the environment through cooling water. During operation, the temperature of the transformer oil is of great significance to the safe and stable operation of the equipment. When the oil temperature is too high, it may cause problems such as aging of the insulation material inside the transformer and deterioration of the oil, thereby affecting the normal operation of the transformer and even causing accidents. Therefore, it is very necessary to monitor and warn the oil temperature of the forced oil circulation water-cooled transformer in real time. The existing oil temperature monitoring methods of forced oil circulation water-cooled transformers mainly rely on manual inspections and temperature sensors, but these methods have the following problems: manual inspections are time-consuming and labor-intensive, and it is difficult to achieve real-time monitoring; the accuracy and stability of the temperature sensor are affected by environmental factors, which may lead to false alarms or missed alarms; there is a lack of early warning mechanisms for different oil temperature levels, which cannot meet the early warning needs in different scenarios. Summary of the invention

[0003] In order to solve the problems existing in the prior art that manual inspection is time-consuming and labor-intensive, the accuracy and stability of the temperature sensor are affected by environmental factors, resulting in false alarms or missed alarms, and there is a lack of early warning mechanism for different oil temperature levels, which cannot meet the early warning needs in different scenarios, the present invention provides a method, device and storage medium for early warning of oil temperature of a water-cooled transformer with forced oil circulation.

[0004] In a first aspect, the present invention provides an oil temperature early warning method for a forced oil circulation water-cooled transformer, the method comprising: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

[0005] Furthermore, the real-time collection of oil temperature and related data of the strong oil circulation water-cooled transformer of the hydropower station is specifically as follows: The oil temperature data is collected in real time through the oil temperature sensor installed inside the transformer; The oil flow data is collected through the oil flow sensor installed on the transformer cooler; The winding current is collected through the current transformer installed on the winding; The oil level data of the oil tank is collected through the oil level gauge installed on the oil pillow; The water temperature and flow rate are collected by the cooling water temperature and flow sensors installed on the cooler; The air temperature is collected by a temperature sensor installed near the main transformer.

[0006] Furthermore, the data cleaning and data smoothing are specifically as follows: The multivariate linear regression method was used to clean the data, and the interpolation method was used to smooth the data.

[0007] Furthermore, the method further comprises: When the oil temperature exceeds the warning threshold, the industrial Internet platform sends warning information to relevant personnel, reminding them to take corresponding measures.

[0008] Furthermore, the method further comprises: Initiate the fault diagnosis process based on the early warning information, use the fault case library matching method and FMEA fault analysis method to analyze the cause of abnormal oil temperature, and after confirmation, collect relevant information to form a fault case and add it to the fault case library.

[0009] Furthermore, the processing of comparing the measured oil temperature data after processing with the warning threshold value of the predicted value deviation to determine whether the current oil temperature exceeds the warning threshold value includes: The Kendall correlation coefficient method is used to calculate the correlation of the changing oil temperature and determine the accuracy of the warning.

[0010] Furthermore, the method comprises: Take corresponding measures according to different levels of warnings, specifically: The warning levels are divided into low, medium and high levels; low-level warnings notify operation and maintenance personnel to conduct inspections and repairs and put spare coolers into use; medium-level warnings reduce the load or increase the flow of cooling water; high-level warnings require emergency shutdown after confirmation.

[0011] In a second aspect, the present invention provides an oil temperature early warning device for a forced oil circulation water-cooled transformer, the device comprising: Data acquisition module for: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Data processing module for: Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Prediction and early warning module for: Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

[0012] In a third aspect, the present invention provides an oil temperature early warning device for a forced oil circulation water-cooled transformer, the device comprising: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0013] In a fourth aspect, the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to execute the above method.

[0014] Compared with the prior art, the present invention has the following advantages: It can realize real-time monitoring and early warning of the oil temperature of the forced oil circulation water-cooled transformer, thereby improving the operating safety of the forced oil circulation water-cooled transformer; by setting different oil temperature early warning thresholds, it can meet the early warning needs in different scenarios; and reduce the risk of false alarms and missed alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of an oil temperature early warning method for a water-cooled transformer with forced oil circulation provided by an embodiment of the present invention; Figure 2 A schematic diagram of the composition of an oil temperature early warning device for a water-cooled transformer with forced oil circulation provided by an embodiment of the present invention; Figure 3 A schematic diagram of the composition of an oil temperature early warning device for a water-cooled transformer with forced oil circulation provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] Explanation of terms involved in the embodiments of the present invention: The forced oil circulation water-cooled transformer is a water-cooled transformer. There is no radiator on the oil tank, but an oil / water heat exchange system and a water / gas heat exchange system are installed outside the transformer. For water-cooled transformers, there is no radiator on the oil tank. The oil / water heat exchange system includes an oil pump, an oil filter, an oil flow meter, and a water cooler. Cooling water flows through the water cooler and the hot oil of the transformer flows outside. The cooling water takes away the heat of the oil and cools the hot oil. The upper hot oil of the transformer is pumped out by the oil pump, cooled by the water cooler, and flows back to the transformer from the bottom of the oil tank to cool the iron core and winding of the transformer. The temperature of the oil rises after being heated, and the hot oil flows to the top of the transformer again and is pumped out. The oil / water heat exchange system includes a water pump, a water flow meter, a fan, and a water replenishment device. After the cooling water absorbs the heat from the transformer hot oil, the water temperature rises, and the circulating water pump pressurizes the cooling water and sends it to the ground layer. The fan cools the cooling water loop, and after cooling, it returns to the underground layer to participate in the heat exchange with the transformer hot oil.

[0018] Hopfield neural network refers to a network designed by American biophysicist Hopfield and his colleagues based on the principles of physics, usually called the Hopfield neural network.

[0019] Kendall coefficient: n similar statistical objects are sorted by a specific attribute, and other attributes are usually out of order. Kendall correlation coefficient (R) refers to the coefficient of n statistical objects, each with two attributes. Arrange all statistical objects according to the value of attribute 1, without loss of generality, and assume that the arrangement of attribute 2 is out of order. Let P be the number of statistical objects with the same size relationship between the two attribute values, then ; FMEA (Failure Mode and Effects Analysis), failure mode and effect analysis, is also called "failure mode and effect analysis".

[0020] Hermite interpolation, Hermite interpolation, the function values ​​at the nodes are equal, and the corresponding derivative values ​​are also required to be equal, and even the higher-order derivatives are required to be equal. The interpolation polynomial that meets this requirement is the Hermite interpolation polynomial.

[0021] An oil temperature early warning method for a forced oil circulation water-cooled transformer provided in an embodiment of the present invention is a method for intelligently early warning the oil temperature of a forced oil circulation water-cooled transformer and providing corresponding treatment measures by utilizing relevant components of an industrial Internet platform.

[0022] Figure 1 A schematic diagram of an oil temperature early warning method for a water-cooled transformer with forced oil circulation is provided in an embodiment of the present invention, and the method comprises: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

[0023] In one embodiment, the real-time collection of oil temperature and related data of the forced oil circulation water-cooled transformer of the hydropower station is specifically as follows: The oil temperature data is collected in real time through the oil temperature sensor installed inside the transformer; The oil flow data is collected through the oil flow sensor installed on the transformer cooler; The winding current is collected through the current transformer installed on the winding; The oil level data of the oil tank is collected through the oil level gauge installed on the oil pillow; The water temperature and flow rate are collected by the cooling water temperature and flow sensors installed on the cooler; The air temperature is collected by a temperature sensor installed near the main transformer.

[0024] In one embodiment, the relevant data collected is transmitted remotely, and the specific process is: 1. Upload the data to the zone 2 server on the plant side through the hydropower station network; 2. Upload the data to the zone 3 data center on the plant side through the forward isolation device and the reverse isolation device; 3. Upload the data to the big data center on the company side through the forward isolation device and the reverse isolation device.

[0025] In one embodiment, the data cleaning and data smoothing are specifically as follows: The multivariate linear regression method was used to clean the data, and the interpolation method was used to smooth the data.

[0026] In one embodiment, the interpolation method adopts the Hermite interpolation method.

[0027] In one embodiment, the method further comprises: When the oil temperature exceeds the warning threshold, the industrial Internet platform sends warning information to relevant personnel, reminding them to take corresponding measures.

[0028] In one embodiment, the method further comprises: Initiate the fault diagnosis process based on the early warning information, use the fault case library matching method and FMEA fault analysis method to analyze the cause of abnormal oil temperature, and after confirmation, collect relevant information to form a fault case and add it to the fault case library.

[0029] In one embodiment, comparing the processed measured oil temperature data with the warning threshold value of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold value includes: The Kendall correlation coefficient method is used to calculate the correlation of the changing oil temperature and determine the accuracy of the warning.

[0030] In one embodiment, the method comprises: Take corresponding measures according to different levels of warnings, specifically: The warning levels are divided into low, medium and high levels; low-level warnings notify operation and maintenance personnel to conduct inspections and repairs and put spare coolers into use; medium-level warnings reduce the load or increase the flow of cooling water; high-level warnings require emergency shutdown after confirmation.

[0031] Figure 2 A schematic diagram of the composition of an oil temperature early warning device for a water-cooled transformer with forced oil circulation provided by an embodiment of the present invention, the device comprising: Data acquisition module for: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Data processing module for: Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Prediction and early warning module for: Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

[0032] Figure 3 A schematic diagram of the composition of an oil temperature early warning device for a water-cooled transformer with forced oil circulation provided by an embodiment of the present invention, the device comprising: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0033] In addition, an embodiment of the present invention provides a storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the above method.

[0034] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for early warning of oil temperature of a water-cooled transformer with a strong oil circulation, characterized in that: The method comprises: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

2. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The real-time collection of oil temperature and related data of the forced oil circulation water-cooled transformer of the hydropower station is specifically: The oil temperature data is collected in real time through the oil temperature sensor installed inside the transformer; The oil flow data is collected through the oil flow sensor installed on the transformer cooler; The winding current is collected through the current transformer installed on the winding; The oil level data of the oil tank is collected through the oil level gauge installed on the oil pillow; The water temperature and flow rate are collected by the cooling water temperature and flow sensors installed on the cooler; The air temperature is collected by a temperature sensor installed near the main transformer.

3. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The data cleaning and data smoothing are specifically as follows: The multivariate linear regression method was used to clean the data, and the interpolation method was used to smooth the data.

4. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The method further comprises: When the oil temperature exceeds the warning threshold, the industrial Internet platform sends warning information to relevant personnel, reminding them to take corresponding measures.

5. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The method further comprises: Initiate the fault diagnosis process based on the early warning information, use the fault case library matching method and FMEA fault analysis method to analyze the cause of abnormal oil temperature, and after confirmation, collect relevant information to form a fault case and add it to the fault case library.

6. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The step of comparing the processed measured oil temperature data with the warning threshold value of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold value includes: The Kendall correlation coefficient method is used to calculate the correlation of the changing oil temperature and determine the accuracy of the warning.

7. The oil temperature early warning method for a water-cooled transformer with forced oil circulation as claimed in claim 1 is characterized in that: The method comprises: Take corresponding measures according to different levels of warnings, specifically: The warning levels are divided into low, medium and high levels; low-level warning notifies the operation and maintenance personnel to conduct inspections and repairs and put into use spare coolers; medium-level warning reduces the load or increases the flow of cooling water; high-level warning causes emergency shutdown after confirmation.

8. An oil temperature early warning device for a water-cooled transformer with a strong oil circulation, characterized in that: The device comprises: Data acquisition module for: Real-time collection of oil temperature and related data of forced oil circulation water-cooled transformers in hydropower stations; Data processing module for: Remotely transmit the collected data to the big data center of the industrial Internet platform; The Industrial Internet Platform Big Data Center processes the received data, including: cleaning and smoothing the data; Prediction and early warning module for: Input the transformer's operating parameters, oil temperature data, oil flow data, current data, oil level data, ambient temperature data, and historical oil temperature data into the Hopfield neural network model of the industrial Internet platform, and make real-time predictions on the monitored oil temperature data to obtain the predicted value; Set different levels of warning dynamic thresholds based on the predicted values; The processed measured oil temperature data is compared with the warning threshold of the deviation of the predicted value to determine whether the current oil temperature exceeds the warning threshold.

9. An oil temperature early warning device for a water-cooled transformer with a strong oil circulation, characterized in that: The device comprises: Memory, used to store programs; A processor, configured to execute the program stored in the memory; when the program stored in the memory is executed, the processor is configured to execute the steps of the method as claimed in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the method according to any one of claims 1 to 7.

Images