Defect prediction method, device and equipment for transformer respirator and medium
By configuring color sensors and insulating oil parameters on transformer breathers and combining them with machine learning models, the time of defect state transition of transformer breathers can be predicted, solving the problem of untimely defect identification of transformer breathers and enabling timely early warning and optimized power outage arrangements.
Patent Information
- Application Number
- CN202411037066.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
AI Technical Summary
Existing technologies cannot effectively identify transformer breather defects and provide timely warnings, leading to untimely defect handling and affecting the normal operation of power grid equipment.
Multiple color sensors are configured on the transformer breather, and combined with the insulating oil parameters, a machine learning model is used to predict the time it takes for the breather to change from a normal state to a defective state, thus providing early warning.
It enables timely prediction and alerts for transformer breather defects, solves the problems of delayed defect reporting and untimely processing, and optimizes the power outage arrangements for power grid equipment.
Smart Images

Figure CN118969451A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power equipment maintenance, and in particular to a defect prediction method, device, equipment and medium for a transformer respirator. Background Art
[0002] The transformer's breather is a protective device that can adjust the amount of oil and pressure inside the transformer. Usually, the operating personnel conduct daily inspections to check for defects in the transformer's breather. With the advancement of intelligent operation and maintenance of substation equipment, substation equipment inspections use drone inspections, but still require manual image recognition or software recognition and manual verification, and are unable to correctly warn of equipment that is about to change from normal to abnormal, which will lead to delayed defect reporting and insufficient defect handling. In addition, as power outages for power grid equipment become more planned, power outages are shortened, and the frequency is reduced, it is even more necessary to determine the time required to handle equipment such as transformer breather defects that can be eliminated without power outages, so as to better arrange and coordinate power outage production work. Therefore, there is a need for a method that can normally identify transformer breather defects and predict the time when they change to a defective state. Summary of the invention
[0003] The present application provides a defect prediction method, device, equipment and medium for a transformer breather, which can predict in advance the time when the filler in the transformer breather becomes a defective state, and thus can promptly prompt the transformer breather defects.
[0004] In a first aspect, the present application provides a defect prediction method for a transformer respirator, wherein the transformer respirator is provided with a plurality of color sensors, and the plurality of color sensors are used to detect the colors of fillers located at different positions in the transformer respirator, and the method comprises:
[0005] In a current detection cycle, the current actual colors of the filling materials located at different positions in the transformer respirator are detected by the multiple color sensors;
[0006] Obtaining current insulating oil parameters of the transformer respirator, and obtaining historical insulating oil parameters of the transformer respirator within a historical detection period;
[0007] The color change prediction duration corresponding to the transformation of the transformer respirator into a defective state is predicted according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter.
[0008] Furthermore, predicting the predicted color change time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter includes: determining the color change speed of the filler according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter; predicting the color change predicted time corresponding to the color change portion of the filler exceeding a preset proportion according to the color change speed and the current actual color.
[0009] Furthermore, a predicted color change duration corresponding to when the color-changing portion of the filler exceeds a preset proportion is predicted based on the color-changing speed and the current actual color, including: determining the color change degree of the filler based on the current actual color; obtaining a color change prediction model of the filler based on the color change degree and the color change speed; and parsing the color change prediction model to obtain a predicted color change duration corresponding to when the color-changing portion of the filler exceeds a preset proportion.
[0010] Furthermore, determining the color change speed of the filler according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter includes: determining a calculated correction coefficient and a measured correction coefficient for correcting the color change prediction duration according to the current actual color of the filler; determining a volume correction coefficient for the insulating oil in the transformer according to the measured oil temperature in the current insulating oil parameters and the historical oil temperature in the historical insulating oil parameters; determining a humidity correction coefficient for the insulating oil in the transformer according to the measured humidity of the oil temperature drop in the current insulating oil parameters and the historical humidity of the oil temperature drop in the historical insulating oil parameters; determining the color change speed of the filler according to the calculated correction coefficient, the measured correction coefficient, the volume correction coefficient and the humidity correction coefficient.
[0011] Furthermore, before predicting the color change prediction time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters, it also includes: analyzing whether the transformer respirator is defective according to the current actual color of the filler; if so, determining the cause of the defect of the transformer respirator; if not, executing the step of predicting the color change prediction time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
[0012] Furthermore, a fixing bracket for mounting the multiple color sensors is arranged on the outside of the transformer respirator, the fixing bracket comprises a longitudinal vertical pole, a top fixing ring and a bottom fixing ring, the two ends of the longitudinal vertical pole are respectively connected to the top fixing ring and the bottom fixing ring; a plurality of magnet bases are arranged on the longitudinal vertical pole from top to bottom according to a preset distribution method, and a color sensor is placed on each magnet base; the multiple color sensors include at least a first color sensor placed on the topmost magnet base among the multiple magnet bases, a second color sensor placed on the second topmost magnet base among the multiple magnet bases, and a third color sensor placed on the bottommost magnet base among the multiple magnet bases; the preset distribution method is that the positions of different color sensors on the longitudinal vertical pole correspond one-to-one to the predicted degree of discoloration of the filler.
[0013] Furthermore, the determination of the cause of the defect of the transformer respirator includes: if it is determined according to the current actual colors corresponding to the multiple color sensors that the first color sensor first recognizes the color change of the filler, or the first actual color recognized by the first color sensor and the second color sensor within a preset time after the filler is replaced is the first preset color, then the cause of the defect is determined to be air leakage of the respirator; if the second actual color recognized by the second color sensor is the first preset color, or is not the second preset color, then the cause of the defect is determined to be that the discolored part of the filler exceeds a preset proportion; if the third actual color recognized by the third color sensor is consistent with the color of the oil in the oil sealing cup in the transformer, then the cause of the defect is determined to be oil backflow of the respirator.
[0014] In a second aspect, the present application provides a defect prediction device for a transformer respirator, wherein the transformer respirator is provided with a plurality of color sensors, and the plurality of color sensors are used to detect the colors of fillers located at different positions in the transformer respirator, and the device comprises:
[0015] A data detection module, used for detecting the current actual colors of the filling materials located at different positions in the transformer respirator through the multiple color sensors in the current detection cycle;
[0016] A parameter acquisition module, used to acquire the current insulating oil parameters of the transformer respirator, and acquire the historical insulating oil parameters of the transformer respirator within a historical detection period;
[0017] A defect prediction module is used to predict the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
[0018] In a third aspect, the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the defect prediction method for the transformer respirator described in any embodiment of the present application.
[0019] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the defect prediction method for a transformer respirator described in any embodiment of the present application when executed.
[0020] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the defect prediction method for a transformer breather as described in any embodiment of the present application.
[0021] In order to solve the defects of the prior art in the background technology, the embodiment of the present application provides a defect prediction method for a transformer respirator. The execution of this method can bring the following beneficial effects: the present application configures multiple color sensors on the transformer respirator to detect the color of the fillers located at different positions in the transformer respirator, and then combines the current insulating oil parameters measured for the transformer respirator and the historical insulating oil parameters recorded in history to predict the color change prediction time of the transformer respirator from a normal state to a defective state. The present application can predict in advance the time when the filler in the transformer respirator changes to a defective state, solve the problems of delayed defect reporting time and untimely defect handling, and then can timely prompt the transformer respirator defects, and can also better arrange and coordinate power outage production work.
[0022] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the defect prediction device of the transformer respirator, or may be packaged separately from the processor of the defect prediction device of the transformer respirator, and this application does not limit this.
[0023] The description of the second, third, ..., and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, ..., and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.
[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description.
[0025] It is understandable that before using the technical solutions disclosed in the embodiments of this application, the type, scope of use, and usage scenarios of the personal information involved in this application should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0027] Figure 1 A schematic diagram of a fixing bracket provided in an embodiment of the present application;
[0028] Figure 2 A first flow chart of a defect prediction method for a transformer respirator provided in an embodiment of the present application;
[0029] Figure 3 A second flow chart of a defect prediction method for a transformer respirator provided in an embodiment of the present application;
[0030] Figure 4 A schematic diagram of the structure of a defect prediction device for a transformer respirator provided in an embodiment of the present application;
[0031] Figure 5 The present invention is a block diagram of an electronic device used to implement a defect prediction method for a transformer respirator according to an embodiment of the present application. DETAILED DESCRIPTION
[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.
[0033] It should be noted that the terms "first", "second", "target", and "original" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including", "having", and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.
[0034] Before introducing the defect prediction method of the transformer respirator of the present embodiment, the hardware device of the present embodiment is first introduced in detail. In the present embodiment, a plurality of color sensors are arranged on the transformer respirator, and the plurality of color sensors are used to detect the color of the fillers located at different positions in the transformer respirator. A fixed bracket for mounting a plurality of color sensors is arranged on the outside of the transformer respirator, and the fixed bracket is composed of a longitudinal vertical pole, a top fixing ring and a bottom fixing ring, and the two ends of the longitudinal vertical pole are respectively connected to the top fixing ring and the bottom fixing ring; a plurality of magnet bases are arranged on the longitudinal vertical pole from top to bottom according to a preset distribution method, and a color sensor is placed on each magnet base. Among them, the preset distribution method can be that the positions of different color sensors on the longitudinal vertical poles correspond one by one to the predicted degree of discoloration of the fillers.
[0035] like Figure 1 The figure shows a schematic diagram of the fixing bracket provided in this embodiment, wherein (a) is a physical schematic diagram of a transformer respirator without a fixing bracket, (b) is a physical schematic diagram of a transformer respirator with a fixing bracket, (c) is a side view of the fixing bracket, and (d) is a top view of the top fixing ring in the fixing bracket. The figure shows that the filler of the transformer respirator is made of silicone, the top fixing ring is fixed to the transformer respirator by screws and nuts, four color sensors are arranged on the longitudinal pole, and a bottom contactor is arranged on the bottom fixing ring. When it is detected that the bottom contactor contacts an object, it can be determined that the transformer respirator has an assembly detachment failure. In addition, the number of color sensors can be increased to improve the prediction accuracy.
[0036] Optionally, an additional device can be installed in a non-disassembly manner according to the appearance of the transformer respirator, and a bolt-fixed card plate can be set. In addition, since the models and sizes of various transformer respirators are different, and some transformer respirators are equipped with metal sleeves, it is inconvenient to observe the color sensor at a fixed length position. Therefore, the position of the color sensor is set to be adjustable, and the color sensor is fixed by a magnetic base, which is convenient for adjustment according to the exposed part of the respirator to identify the color of the respirator filling. Whether the working condition of the transformer respirator is normal is judged based on the output of the color sensor installed in different positions.
[0037] Figure 2 The first flow chart of a defect prediction method for a transformer respirator provided in an embodiment of the present application is applicable to the case of predicting the duration of a transformer respirator changing from a normal state to a defective state. The defect prediction method for a transformer respirator provided in this embodiment can be executed by a defect prediction device for a transformer respirator provided in an embodiment of the present application, which can be implemented in software and / or hardware and integrated in an electronic device that executes the method. The execution subject that executes the method can be a microcontroller of the transformer respirator.
[0038] See also Figure 2 The method of this embodiment includes but is not limited to the following steps:
[0039] S110 . In the current detection cycle, the current actual colors of the fillers at different positions in the transformer respirator are detected by using a plurality of color sensors.
[0040] The interval length of each detection cycle can be set by the user according to the actual application situation. The color sensor is used to identify the color of the filler. The transformer respirator is a protective device that can adjust the oil volume and pressure inside the transformer. The filler refers to an object with color and the abnormality of the respirator can be judged by the degree of color change, such as silica gel. This embodiment detects the color of the filler at different positions in the respirator in order to determine the degree of defect of the respirator.
[0041] In the embodiment of the present application, at intervals of each detection cycle, the microcontroller detects the current actual color of the filler in real time through the color sensor to obtain the current actual color of the filler at different positions in the respirator.
[0042] Optionally, the four color sensors may be distributed evenly or unevenly on the longitudinal poles. Preferably, they may be distributed according to the color change ratio of the filler, that is, the installation position of each color sensor corresponds to a color change ratio of the filler. For example, a color sensor may be installed at a corresponding position where the color change ratio of the filler is 5%, 35%, 66% and 95%.
[0043] S120, obtaining current insulating oil parameters of the transformer respirator, and obtaining historical insulating oil parameters of the transformer respirator within a historical detection period.
[0044] Among them, the oil of the transformer respirator is also called insulating oil, which is a kind of insulating material. It is used to insulate the windings, core iron and lead wires in the transformer tank, and is used to isolate and prevent the current from leaking inside the transformer, which can ensure the normal operation of the transformer. The insulating oil parameters can include the temperature, humidity and other parameters of the insulating oil.
[0045] In the embodiment of the present application, a temperature sensor and a humidity sensor may be provided in the transformer respirator. At each detection cycle, the microcontroller detects the temperature of the insulating oil in the transformer respirator through the temperature sensor, detects the humidity of the insulating oil in the transformer respirator through the humidity sensor, and saves the temperature and humidity of the insulating oil, analyzes them, and obtains data such as the average value, peak value, and valley value in this detection cycle.
[0046] S130, predicting the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
[0047] In an optional embodiment, this step may be implemented by pre-building a defect prediction model through a machine learning model and a training data set, and then inputting the current actual color of the filler, the current insulating oil parameters, and the historical insulating oil parameters obtained in the above steps into the defect prediction model, and obtaining the color change prediction time corresponding to the transformer respirator turning into a defective state according to the output result of the defect prediction model.
[0048] In another optional embodiment, the amount of water that a certain weight of filler (such as silica gel) can absorb is fixed. In theory, as long as the amount of water in the breather can be calculated, the degree and time of silica gel discoloration can be calculated. However, due to the different amounts of oil in the transformer, the different sizes of the breathers, and the deviation of manual assembly, the amount of filler and the volume of the inhaled gas are difficult to calculate. Therefore, the volume is fuzzy processed and no specific numerical value is used for calculation. The degree of silica gel discoloration can be predicted by relying on historical insulating oil parameters (including the discoloration time, oil temperature and humidity of the filler of the transformer breather in the same period in history), predicted data (including the predicted oil temperature and humidity in a certain detection cycle in the future), and current insulating oil parameters (including the actual discoloration degree of the filler in the transformer breather, the measured oil temperature, and the measured humidity). Specifically, the implementation method of this step can also be: determine the discoloration speed of the filler according to the current actual color of the filler, the current insulating oil parameters, and the historical insulating oil parameters; predict the discoloration prediction time corresponding to the discoloration part of the filler exceeding the preset proportion according to the discoloration speed and the current actual color.
[0049] In a preferred embodiment, before executing this step S130, it also includes: analyzing whether the transformer breather has defects according to the current actual color of the filler; if so, determining the cause of the defect of the transformer breather; if not, executing this step S130.
[0050] Among them, the multiple color sensors include at least a first color sensor placed on the topmost magnet base among the multiple magnet bases, a second color sensor placed on the second topmost magnet base among the multiple magnet bases, and a third color sensor placed on the bottommost magnet base among the multiple magnet bases.
[0051] Further, determining the defect cause of the transformer respirator includes: if it is determined that the first color sensor first recognizes the color change of the filler according to the current actual colors corresponding to the multiple color sensors, or the first actual color recognized by the first color sensor and the second color sensor is the first preset color (such as pink or white) within a preset time (such as 15 days) after the filler is replaced, then the defect cause is determined to be air leakage of the respirator; if the second actual color recognized by the second color sensor is the first preset color (such as pink or white), or is not the second preset color (such as blue), then the defect cause is determined to be that the discolored part of the filler exceeds the preset proportion (such as two-thirds); if the third actual color recognized by the third color sensor is consistent with the color of the oil in the oil seal cup in the transformer (such as brown), then the defect cause is determined to be oil backflow of the respirator. The advantage of this setting is that the working condition of the transformer respirator can be judged by identifying the color of the respirator filler, and it can identify the discolored part of the filler exceeding two-thirds, abnormal air leakage during the installation of the respirator, insufficient oil inlet to the respirator and the oil seal cup, and other defects.
[0052] Optionally, the information fed back by the color sensor is used to confirm whether there is an abnormality in the transformer breather. If the status of the transformer breather is abnormal or the prediction result shows that it will turn into an abnormal state within a preset time range (such as within the next fifteen days), an alarm signal can be issued according to a preset method, for example: a preset icon is displayed on the central control display screen.
[0053] The technical solution provided by this embodiment is to detect the current actual color of the filler located at different positions in the transformer respirator through multiple color sensors in the current detection cycle; obtain the current insulating oil parameters of the transformer respirator, and obtain the historical insulating oil parameters of the transformer respirator in the historical detection cycle; predict the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters. This application configures multiple color sensors on the transformer respirator to detect the color of the filler located at different positions in the transformer respirator, and then combines the current insulating oil parameters measured for the transformer respirator and the historical insulating oil parameters recorded in history to predict the color change prediction time of the transformer respirator turning from a normal state to a defective state. This application can predict the time when the filler in the transformer respirator turns into a defective state in advance, solve the problem of delayed defect reporting time and insufficient defect processing, and then can timely prompt the transformer respirator defects, and can also better arrange and coordinate power outage production work.
[0054] The defect prediction method for a transformer respirator provided by an embodiment of the present application is further described below. Figure 3 A second flow chart of a defect prediction method for a transformer respirator provided in an embodiment of the present application. The present application embodiment is optimized on the basis of the above embodiments, and the specific optimization is as follows: This embodiment explains in detail the prediction process of the corresponding color prediction time of the transformer respirator from the normal state to the defect state.
[0055] See also Figure 3 The method of this embodiment includes but is not limited to the following steps:
[0056] S210. Determine a calculated correction coefficient and a measured correction coefficient for correcting the predicted color change duration according to the current actual color of the filling.
[0057] Specifically, the current color change degree of the filler in the transformer respirator is determined according to the current actual colors corresponding to the multiple color sensors; the target color change degree is selected from the multiple preset reference color change degrees based on the current color change degree of the filler; wherein the reference color change degree is a plurality of reference values selected by the user from the color change degree ranging from zero to one hundred percent, such as 5%, 35%, 66% and 95%; the target color change degree is a reference color change degree that the current color change degree of the filler does not exceed and is closest to, recorded as minX n .
[0058] When the current color change degree of the filler is not greater than the target color change degree, there is no need to correct the color change speed of the filler. When the current color change degree of the filler is greater than the target color change degree, the current color change speed of the filler needs to be corrected to make the predicted color change prediction duration more consistent with the actual situation. Then, it is necessary to calculate the calculation correction coefficient for correcting the color change prediction duration based on the current color change degree of the filler and the target color change degree. The calculation correction coefficient can be determined by the following formula (1):
[0059]
[0060] Among them, P s Indicates the calculation correction factor, minX n (a n ) represents the target discoloration degree, and X(a) represents the current discoloration degree of the filling in the transformer breather.
[0061] Specifically, in a future detection cycle after the current detection cycle, when the color sensor detects the actual color of the filler and obtains the corresponding actual color change degree (i.e., when the color sensor has feedback), it is necessary to correct the predicted color change degree previously predicted for the future detection cycle, i.e., the measured correction coefficient. The measured correction coefficient can be determined by the following formula (2):
[0062]
[0063] Among them, R v Indicates the measured correction factor, a n is the color change degree corresponding to the actual color detected by the color sensor in the future detection cycle, a n-1 is the degree of discoloration corresponding to the actual color detected by the color sensor in the previous detection cycle before the future detection cycle, and n is the index number of the detection cycle. X(a) represents the current degree of discoloration of the filling in the transformer respirator.
[0064] S220. Determine a volume correction coefficient for the insulating oil in the transformer according to the actual measured oil temperature in the current insulating oil parameters and the historical oil temperature in the historical insulating oil parameters.
[0065] In the embodiment of the present application, the gas inhaled by the respirator is related to the volume of the oil in the transformer. When the volume of the oil shrinks, gas will be inhaled from the outside. According to actual production, the volume of the transformer insulating oil expands by about 7 / 10000 for every increase of one degree Celsius. Ignoring other influencing factors such as gas pressure and oil leakage, the volume correction coefficient can be determined by the following formula (3):
[0066]
[0067] Among them, P v (a) represents the volume correction factor, a represents the number of days after the filler is replaced, T max (a) and T min (a) are the peak and valley values of the oil temperature in the transformer respirator during the current detection cycle, T 0 It is the average valley value of the oil temperature in the transformer breather during the historical detection period.
[0068] S230, determining a humidity correction coefficient for the insulating oil in the transformer according to the measured humidity of the oil temperature drop in the current insulating oil parameters and the historical humidity of the oil temperature drop in the historical insulating oil parameters.
[0069] In the embodiment of the present application, the volume correction coefficient can be determined by the following formula (4):
[0070]
[0071] Among them, P RH (a) represents the humidity correction factor, a represents the number of days after the filler is replaced, RH 1 (a) is the average humidity value of the oil temperature drop stage in the transformer respirator during the current detection cycle, RH 0 The average value of the oil temperature drop stage in the transformer breather during the historical detection period.
[0072] S240, determining a color change speed of the filler according to the calculated correction coefficient, the measured correction coefficient, the volume correction coefficient and the humidity correction coefficient.
[0073] In the embodiment of the present application, the color change speed of the filler is related to the volume of gas inhaled by the respirator and the gas humidity. The color change speed of the filler can be determined by the following formula (5):
[0074]
[0075] Among them, v a Indicates the color change speed of the filling, M 0 P is the theoretical average time required for the normal discoloration of the filling material in the transformer respirator to reach the defective state, v (a) represents the volume correction factor, P RH(a) represents the humidity correction factor, a represents the number of days after the filling is replaced, R v Indicates the measured correction factor, P s Indicates the calculation correction factor.
[0076] S250, determining the discoloration degree of the filling material according to the current actual color.
[0077] In an embodiment of the present application, a correlation table between actual color and discoloration degree can be pre-set. After the current actual color of the filler is detected by multiple color sensors, the corresponding discoloration degree of the current actual color filler can be obtained by searching the correlation table.
[0078] S260, determining a color change prediction model for the filler according to the color change degree and the color change speed.
[0079] In the embodiment of the present application, the standard for distinguishing normal and defective filler color change in the transformer respirator is that the filler color change portion exceeds two-thirds. When the color change degree is less than two-thirds, it indicates that the filler is currently in a normal state, and then the color change prediction time corresponding to the filler color change portion exceeding two-thirds can be predicted. The filler color change prediction model can be expressed by the following formula (6):
[0080]
[0081] Where X(a) represents the current discoloration degree of the filling material in the transformer respirator, X(a+x) represents the discoloration degree of the filling material x detection cycles after the current detection cycle, x represents the number of detection cycles, and v a It indicates the color change speed of the filler, and i indicates the index number of the detection cycle.
[0082] S270, analyzing the color change prediction model to obtain the color change prediction duration corresponding to the color change portion of the filler exceeding the preset ratio.
[0083] In the embodiment of the present application, x in formula (6) is assigned a value starting from 1 (x is a positive integer) until formula (6) satisfies the condition, and the calculated x is the predicted color change time required for the color change portion of the filler in the transformer respirator to exceed two-thirds.
[0084] The technical solution provided by the present embodiment determines the calculated correction coefficient and the measured correction coefficient for correcting the color change prediction time according to the current actual color of the filler; determines the volume correction coefficient for the insulating oil in the transformer according to the measured oil temperature in the current insulating oil parameters and the historical oil temperature in the historical insulating oil parameters; determines the humidity correction coefficient for the insulating oil in the transformer according to the measured humidity of the oil temperature drop in the current insulating oil parameters and the historical humidity of the oil temperature drop in the historical insulating oil parameters; determines the color change speed of the filler according to the calculated correction coefficient, the measured correction coefficient, the volume correction coefficient and the humidity correction coefficient; determines the color change degree of the filler according to the current actual color; determines a color change prediction model for the filler according to the color change degree and the color change speed; analyzes the color change prediction model to obtain the color change prediction time corresponding to the color change portion of the filler exceeding a preset proportion.
[0085] This application determines the calculated correction coefficient, measured correction coefficient, volume correction coefficient and humidity correction coefficient for correcting the predicted discoloration time, and then can calculate the discoloration speed of the filler. Combined with the discoloration degree of the filler, it can predict the predicted discoloration time of the transformer respirator from a normal state to a defective state. This application can predict in advance the time when the filler in the transformer respirator changes to a defective state, can promptly prompt the transformer respirator defects, solve the problems of delayed defect reporting time and untimely defect handling, and can also better arrange and coordinate power outage production work.
[0086] Figure 4 A schematic diagram of a defect prediction device for a transformer respirator provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, in the device 400, a plurality of color sensors are configured on the transformer respirator, and the plurality of color sensors are used to detect the colors of the fillers located at different positions in the transformer respirator, and may include:
[0087] The data detection module 410 is used to detect the current actual colors of the filling materials located at different positions in the transformer respirator through the multiple color sensors in the current detection cycle;
[0088] The parameter acquisition module 420 is used to acquire the current insulating oil parameters of the transformer respirator and acquire the historical insulating oil parameters of the transformer respirator within a historical detection period;
[0089] The defect prediction module 430 is used to predict the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
[0090] Furthermore, the above-mentioned defect prediction module 430 can be specifically used to: determine the color change speed of the filler based on the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters; predict the color change prediction duration corresponding to the color change portion of the filler exceeding a preset proportion based on the color change speed and the current actual color.
[0091] Furthermore, the above-mentioned defect prediction module 430 can also be specifically used to: determine the degree of discoloration of the filler according to the current actual color; determine a color change prediction model of the filler according to the degree of discoloration and the color change speed; analyze the color change prediction model to obtain the color change prediction time corresponding to the color change part of the filler exceeding a preset proportion.
[0092] Furthermore, the above-mentioned defect prediction module 430 can also be specifically used to: determine the calculated correction coefficient and the measured correction coefficient for correcting the color change prediction duration according to the current actual color of the filler; determine the volume correction coefficient of the insulating oil in the transformer according to the measured oil temperature in the current insulating oil parameters and the historical oil temperature in the historical insulating oil parameters; determine the humidity correction coefficient of the insulating oil in the transformer according to the measured humidity of the oil temperature drop in the current insulating oil parameters and the historical humidity of the oil temperature drop in the historical insulating oil parameters; determine the color change speed of the filler according to the calculated correction coefficient, the measured correction coefficient, the volume correction coefficient and the humidity correction coefficient.
[0093] Furthermore, the defect prediction device for the transformer respirator may further include: a defect detection module;
[0094] The defect detection module is used to analyze whether the transformer respirator has a defect according to the current actual color of the filler before predicting the color change prediction time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters; if so, determine the defect cause of the transformer respirator; if not, execute the step of predicting the color change prediction time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
[0095] In one embodiment, a fixing bracket for mounting the plurality of color sensors is arranged on the outside of the transformer respirator, the fixing bracket comprising a longitudinal vertical pole, a top fixing ring and a bottom fixing ring, the two ends of the longitudinal vertical pole being respectively connected to the top fixing ring and the bottom fixing ring; a plurality of magnet bases are arranged on the longitudinal vertical pole from top to bottom according to a preset distribution method, and a color sensor is placed on each magnet base; the plurality of color sensors include at least a first color sensor placed on the topmost magnet base among the plurality of magnet bases, a second color sensor placed on the second topmost magnet base among the plurality of magnet bases, and a third color sensor placed on the bottommost magnet base among the plurality of magnet bases; the preset distribution method is that the positions of different color sensors on the longitudinal vertical pole correspond one-to-one to the predicted degree of discoloration of the filler.
[0096] Furthermore, the above-mentioned defect detection module can be specifically used for: if it is determined based on the current actual colors corresponding to the multiple color sensors that the first color sensor first recognizes the color change of the filler, or the first actual color recognized by the first color sensor and the second color sensor within a preset time after the filler is replaced is the first preset color, then the cause of the defect is determined to be air leakage of the respirator; if the second actual color recognized by the second color sensor is the first preset color, or is not the second preset color, then the cause of the defect is determined to be that the discolored part of the filler exceeds a preset proportion; if the third actual color recognized by the third color sensor is consistent with the color of the oil in the oil seal cup in the transformer, then the cause of the defect is determined to be oil backflow of the respirator.
[0097] The defect prediction device for a transformer breather provided in this embodiment can be applied to the defect prediction method for a transformer breather provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0098] Figure 5 It is a block diagram of an electronic device for implementing a defect prediction method for a transformer respirator of an embodiment of the present application. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.
[0099] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0100] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0101] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a defect prediction method for a transformer respirator.
[0102] In some embodiments, the defect prediction method for a transformer respirator may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the defect prediction method for a transformer respirator described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the defect prediction method for a transformer respirator in any other appropriate manner (e.g., by means of firmware).
[0103] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0104] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0105] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0106] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0107] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server) or a computing system that includes middleware components (e.g., an application server) or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein) or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0108] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0109] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. For example, those skilled in the art can use the various forms of processes shown above to reorder, add, or delete steps; the steps recorded in the present application can be performed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present application can be achieved, and this document does not limit them here.
[0110] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.
Claims
1. A defect prediction method for a transformer respirator, characterized in that: The transformer respirator is provided with a plurality of color sensors, and the plurality of color sensors are used to detect the colors of fillers located at different positions in the transformer respirator. The method comprises: In a current detection cycle, the current actual colors of the filling materials located at different positions in the transformer respirator are detected by the multiple color sensors; Obtaining current insulating oil parameters of the transformer respirator, and obtaining historical insulating oil parameters of the transformer respirator within a historical detection period; The color change prediction duration corresponding to the transformation of the transformer respirator into a defective state is predicted according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter.
2. The defect prediction method of transformer respirator according to claim 1, characterized in that: The predicting of the color change prediction time corresponding to the transformation of the transformer respirator into a defective state according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter comprises: Determining a color change speed of the filler according to a current actual color of the filler, the current insulating oil parameter, and the historical insulating oil parameter; The color change prediction duration corresponding to the color change portion of the filler exceeding a preset proportion is predicted based on the color change speed and the current actual color prediction.
3. The defect prediction method of transformer respirator according to claim 2 is characterized in that: Predicting the color change prediction duration corresponding to the color change portion of the filler exceeding a preset ratio according to the color change speed and the current actual color includes: Determining the degree of color change of the filler according to the current actual color; Determine a color change prediction model of the filler according to the color change degree and the color change speed; The color change prediction model is analyzed to obtain the color change prediction duration corresponding to the color change portion of the filler exceeding a preset ratio.
4. The defect prediction method of transformer respirator according to claim 2 is characterized in that: The determining the color change speed of the filler according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter comprises: Determine a calculated correction coefficient and a measured correction coefficient for correcting the predicted color change duration according to the current actual color of the filler; Determine a volume correction coefficient for the insulating oil in the transformer according to the measured oil temperature in the current insulating oil parameter and the historical oil temperature in the historical insulating oil parameter; Determine a humidity correction coefficient for the insulating oil in the transformer according to the measured humidity of the oil temperature drop in the current insulating oil parameter and the historical humidity of the oil temperature drop in the historical insulating oil parameter; The color change speed of the filler is determined according to the calculated correction coefficient, the measured correction coefficient, the volume correction coefficient and the humidity correction coefficient.
5. The defect prediction method of transformer respirator according to claim 1, characterized in that: Before predicting the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter, the method further includes: Analyzing whether the transformer respirator is defective according to the current actual color of the filler; If so, determine the cause of the defect of the transformer breather; If not present, the step of predicting the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameter and the historical insulating oil parameter is performed.
6. The defect prediction method of transformer respirator according to claim 5, characterized in that: A fixing bracket for mounting the plurality of color sensors is arranged outside the transformer respirator, the fixing bracket comprising a longitudinal vertical pole, a top fixing ring and a bottom fixing ring, the two ends of the longitudinal vertical pole being respectively connected to the top fixing ring and the bottom fixing ring; a plurality of magnet bases are arranged on the longitudinal vertical pole from top to bottom in a preset distribution manner, and a color sensor is placed on each magnet base; The multiple color sensors include at least a first color sensor placed on the topmost magnet base among the multiple magnet bases, a second color sensor placed on the second topmost magnet base among the multiple magnet bases, and a third color sensor placed on the bottommost magnet base among the multiple magnet bases; the preset distribution method is that the positions of different color sensors on the longitudinal poles correspond one-to-one to the predicted degree of color change of the filler.
7. The defect prediction method of transformer respirator according to claim 6, characterized in that: Determining the defect cause of the transformer respirator includes: If it is determined that the first color sensor first recognizes that the filler changes color according to the current actual colors corresponding to the multiple color sensors, or the first actual color recognized by the first color sensor and the second color sensor is the first preset color within a preset time after the filler is replaced, it is determined that the cause of the defect is air leakage of the respirator; If the second actual color recognized by the second color sensor is the first preset color, or is not the second preset color, it is determined that the cause of the defect is that the discolored portion of the filler exceeds a preset ratio; If the third actual color recognized by the third color sensor is consistent with the color of the oil in the oil sealing cup of the transformer, it is determined that the cause of the defect is oil backflow from the breather.
8. A defect prediction device for a transformer respirator, characterized in that: The transformer respirator is provided with a plurality of color sensors, and the plurality of color sensors are used to detect the colors of fillers located at different positions in the transformer respirator. The device comprises: A data detection module, used for detecting the current actual colors of the filling materials located at different positions in the transformer respirator through the multiple color sensors in the current detection cycle; A parameter acquisition module, used to acquire the current insulating oil parameters of the transformer respirator, and acquire the historical insulating oil parameters of the transformer respirator within a historical detection period; A defect prediction module is used to predict the color change prediction time corresponding to the transformer respirator turning into a defective state according to the current actual color of the filler, the current insulating oil parameters and the historical insulating oil parameters.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the defect prediction method for the transformer breather according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the defect prediction method for a transformer breather according to any one of claims 1 to 7 when the processor executes the computer instructions.
