A transformer fault early warning method and system based on the Internet of Things

Abstract

The present invention discloses a transformer fault warning method and system based on the Internet of Things, which specifically relates to the technical field of transformers. The method and system can judge whether the fault warning system corresponding to the transformer before replacement is still applicable to the fault warning of the transformer at the replaced position according to the actual situation, thereby saving management and operation costs and more accurately identifying the potential failure risks of the transformer after replacement. In addition, for the transformer that still uses the fault warning system before replacement for failure warning, as time goes by, the fault warning system of the current transformer can be changed in time according to the actual situation, so that the potential failure risks of the transformer can be accurately identified. In addition, the method and system can periodically judge whether the fault warning system of the current transformer needs to be changed according to the current situation, thereby ensuring timely and accurate identification of the potential failure risks of the transformer.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a transformer fault early warning method and system based on the Internet of Things. Background Art

[0002] Transformer fault warning based on the Internet of Things is a system that uses the Internet of Things technology to perform real-time monitoring and fault warning of transformers. Its main purpose is to collect transformer operation data in real time through sensors, analyze data and identify potential fault risks, so as to provide early warning before the fault occurs, avoiding or reducing power outages or other losses caused by transformer failures.

[0003] For multiple transformers in a certain area, when each transformer is in use, a corresponding fault warning system is set up to identify the potential fault risks of all transformers in the area, and an alarm is issued to remind the staff which transformers may fail, and handle them in a timely manner;

[0004] However, if some accidents occur in the area and one or some transformers need to be replaced, for each newly replaced transformer, the fault warning system corresponding to the transformer at that location before the replacement may not be suitable for the fault warning of the transformer at that location after the replacement, resulting in the inability to accurately identify the potential failure risks of the transformer. If a new fault warning system is set up for each newly replaced transformer, it may increase management and operation costs; and for transformers that can use the fault warning system before replacement for fault warning, as time goes by, the fault warning system before replacement may no longer be suitable for the fault warning of the current replaced transformer, which may result in the inability to accurately identify the potential failure risks of the transformer. Summary of the invention

[0005] The purpose of the present invention is to solve the problem and propose a transformer fault early warning method and system based on the Internet of Things.

[0006] In a first aspect of the present invention, a transformer fault early warning method based on the Internet of Things is first proposed, and the method comprises:

[0007] Extracting power data, sensor data and environmental data of each transformer before replacement within a first preset time period when no failure occurs from the historical data as first state data;

[0008] Acquire power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculate a first change coefficient of the transformer according to the first state data and the second state data;

[0009] Comparing the first variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of the corresponding replaced transformer according to the comparison result;

[0010] For each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtaining aging data of the transformer after running for a second preset time period, obtaining an aging coefficient according to the aging data, and obtaining a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient, and a load variation coefficient;

[0011] comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result;

[0012] The aging coefficient of the replaced transformer corresponding to the fault warning system before replacement is obtained regularly, and the current change coefficient is calculated in combination with the first change coefficient, and the current change coefficient is compared with the preset change coefficient threshold, and it is determined whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result.

[0013] Optionally, the first variation coefficient is obtained by:

[0014] The power variation coefficient, the sensor variation coefficient and the temperature and humidity variation coefficient are obtained according to the first state data and the second state data, and the power variation coefficient, the sensor variation coefficient and the temperature and humidity variation coefficient are comprehensively analyzed to obtain the first variation coefficient.

[0015] Optionally, the method for obtaining the power variation coefficient is:

[0016] Obtain the actual current and voltage of each transformer before replacement at different times in the last first preset time period when no accidents have occurred, and mark them as V 前 f and I 前 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer;

[0017] Obtain the actual current and voltage of the corresponding replaced transformer at different times within the first preset time period just after replacement, and mark them as V 后 f and I 后 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer;

[0018] Calculate the power of the transformer at different times before and after replacement. The calculation formula is: P 前 f =I前 f ×V 前 f , P 后 f =I 后 f ×V 后 f Where, P 前 f is the power of the transformer at different times before replacement, P 后 f The power of the transformer at different times after replacement

[0019] Calculate the power variation coefficient using the following formula: Where Bax represents the power variation coefficient.

[0020] Optionally, the method for obtaining the sensor variation coefficient is:

[0021] Obtain the number and type of sensors of each transformer before replacement in the last first preset time period when no accidents have occurred, and obtain the number and type of sensors of the corresponding transformer after replacement in the first preset time period just after replacement;

[0022] Compare the types of sensors before and after the transformer is replaced, mark the sensors with inconsistent types as 1, mark the sensors with consistent types as 0, and obtain the number of 1s, which is recorded as the number of inconsistencies;

[0023] The difference in the number of sensors before and after the transformer is replaced is calculated, and the difference in the number and the number of inconsistencies are weighted summed to obtain the sensor variation coefficient.

[0024] Optionally, the method for obtaining the temperature and humidity variation coefficient is:

[0025] Obtain the average temperature and average humidity of each transformer before replacement in the last first preset time period when no accidents have occurred, and record them as the pre-replacement temperature and pre-replacement humidity;

[0026] Obtaining the average temperature and average humidity of the corresponding replaced transformer within a first preset time period just after replacement, and recording them as the post-replacement temperature and the post-replacement humidity;

[0027] According to the temperature and humidity before and after the replacement, the absolute temperature difference and the absolute humidity difference are calculated respectively, and the absolute temperature difference and the absolute humidity difference are weightedly summed to obtain the temperature and humidity change coefficient;

[0028] The method for obtaining the first coefficient of variation is:

[0029] The power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient are normalized to construct the first variation coefficient model and generate the first variation coefficient Dgf. The specific formula is as follows:

[0030]

[0031] In the formula, Dgf is the first variation coefficient, Bax, Dsx and Hlm are the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, a1, a2 and a3 are the preset proportional coefficients of the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, and a1, a2 and a3 are all greater than 0.

[0032] Optionally, comparing the first variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of the corresponding replaced transformer according to the comparison result includes:

[0033] The first variation coefficient is compared with a preset variation coefficient threshold value, and if the first variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer;

[0034] If the first variation coefficient is not less than a preset variation coefficient threshold, an alarm is immediately issued and the fault warning system is reset for the replaced transformer.

[0035] Optionally, aging data of each replaced transformer after running for a second preset time period is obtained, an aging coefficient is obtained according to the aging data, and a second variation coefficient is obtained according to the aging coefficient and the first variation coefficient;

[0036] Obtaining the initial insulation resistance of each replaced transformer after running for a first preset period of time, and recording it as the initial resistance, and obtaining the current insulation resistance after running for a second preset period of time, and calculating the absolute difference between the initial insulation resistance and the current insulation resistance, and dividing the absolute difference by the initial insulation resistance to obtain the insulation aging coefficient;

[0037] Obtain the time from the first maintenance to the last maintenance of each replaced transformer between the first preset time period and the second preset time period, obtain the total maintenance time, obtain the corresponding number of maintenance times, calculate the ratio of the total maintenance time to the number of maintenance times, and obtain the average maintenance interval time; obtain the time interval from the last maintenance time to the current time, obtain the current maintenance time interval, and divide the current maintenance time interval by the average maintenance interval time to obtain the maintenance interval coefficient;

[0038] Obtain the load of each replaced transformer after running for a first preset time period and the load at the current moment, calculate the difference between the load after the first preset time period and the load at the current moment, obtain the load change difference, calculate the ratio of the load change difference and the load after the first preset time period, and obtain the load change coefficient;

[0039] The insulation aging coefficient, the maintenance interval coefficient and the load variation coefficient are weightedly summed to obtain the aging coefficient, and the second variation coefficient is obtained according to the aging coefficient and the first variation coefficient.

[0040] Optionally, obtaining the second variation coefficient according to the aging coefficient and the first variation coefficient includes:

[0041] The second variation coefficient can be obtained according to the aging coefficient and the first variation coefficient through the following formula: Dps=Dgf×(1+Lky), where Dps is the second variation coefficient, Lky is the aging coefficient, and Dgf is the first variation coefficient.

[0042] Optionally, comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result includes:

[0043] The second variation coefficient is compared with a preset variation coefficient threshold value, and if the second variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer;

[0044] If the second variation coefficient is not less than the preset variation coefficient threshold, an alarm is immediately issued and the fault warning system is reset for the replaced transformer.

[0045] In a second aspect of the present invention, a transformer fault early warning system based on the Internet of Things is proposed, comprising:

[0046] The first state data module: extracts the power data, sensor data and environmental data of each transformer before replacement within the last first preset time period when no failure occurs from the historical data as the first state data;

[0047] A first variation coefficient module: obtaining power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculating a first variation coefficient of the transformer according to the first state data and the second state data;

[0048] A first comparison module: compares the first variation coefficient with a preset variation coefficient threshold, and adjusts the fault warning system of the corresponding replaced transformer according to the comparison result;

[0049] Second variation coefficient module: for each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtain its aging data after running for a second preset time period, obtain an aging coefficient according to the aging data, and obtain a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient and a load variation coefficient;

[0050] A second comparison module: comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result;

[0051] Timing adjustment module: regularly obtain the aging coefficient of the replaced transformer corresponding to the fault warning system before replacement, calculate the current change coefficient in combination with the first change coefficient, and compare the current change coefficient with the preset change coefficient threshold, and determine whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result.

[0052] Beneficial effects of the present invention:

[0053] The present invention proposes a transformer fault warning method and system based on the Internet of Things, which can judge whether the fault warning system corresponding to the transformer before replacement is still applicable to the fault warning of the transformer at the replaced position according to the actual situation, while saving management and operation costs, it can also more accurately identify the potential failure risks of the transformer after replacement; in addition, for the transformer that still uses the fault warning system before replacement for fault warning, as time goes by, the fault warning system of the current transformer can be changed in time according to the actual situation, so that the potential failure risks of the transformer can be accurately identified. In addition, it can periodically judge whether the fault warning system of the current transformer needs to be changed according to the current situation, ensuring timely and accurate identification of the potential failure risks of the transformer. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] Figure 1 A flowchart of a transformer fault early warning method based on the Internet of Things is provided for an embodiment of the present invention;

[0056] Figure 2 Another framework diagram of a transformer fault early warning system based on the Internet of Things is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0059] The embodiment of the present invention provides a transformer fault early warning method based on the Internet of Things. Figure 1 , Figure 1 A flowchart of a transformer fault early warning method based on the Internet of Things provided by an embodiment of the present invention. The method comprises the following steps:

[0060] Extracting power data, sensor data and environmental data of each transformer before replacement within a first preset time period when no failure occurs from the historical data as first state data;

[0061] Acquire power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculate a first change coefficient of the transformer according to the first state data and the second state data;

[0062] Comparing the first variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of the corresponding replaced transformer according to the comparison result;

[0063] For each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtaining aging data of the transformer after running for a second preset time period, obtaining an aging coefficient according to the aging data, and obtaining a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient, and a load variation coefficient;

[0064] The second variation coefficient is compared with a preset variation coefficient threshold, and the fault warning system of each replaced transformer is adjusted according to the comparison result.

[0065] The aging coefficient of the replaced transformer corresponding to the fault warning system before replacement is obtained regularly, and the current change coefficient is calculated in combination with the first change coefficient, and the current change coefficient is compared with the preset change coefficient threshold, and it is determined whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result.

[0066] Based on a transformer fault warning method based on the Internet of Things provided by an embodiment of the present invention, through the above-mentioned method, it is possible to judge whether the fault warning system corresponding to the transformer before replacement is still applicable to the fault warning of the transformer at the position after replacement according to the actual situation, while saving management and operation costs, it is also possible to more accurately identify the potential failure risks of the transformer after replacement; in addition, for the transformer that still uses the fault warning system before replacement for fault warning, as time goes by, the fault warning system of the current transformer can be changed in time according to the actual situation, so that the potential failure risks of the transformer can be accurately identified. In addition, it is possible to periodically judge whether the fault warning system of the current transformer needs to be changed according to the current situation, so as to ensure timely and accurate identification of the potential failure risks of the transformer.

[0067] It should be noted that for the newly replaced transformer, in the initial operation period, that is, in the first preset time period of operation, the fault warning system of the transformer before replacement corresponding to the location is still used for warning. The advantage is that switching to a new fault warning system requires time and resources, while the old system may have been running well at the location, which can ensure that the transformer continues to be monitored and warned during the transition period after the replacement, maintaining the continuity and stability of the system; secondly, continuing to use the old system can provide the operation and maintenance team with additional time to evaluate the operation and characteristics of the new transformer. During this period, more data and experience can be collected to help determine and adjust the configuration and parameters of the new fault warning system. In addition, by using the old system first, a gradual transition to the new system can be made, allowing the settings of the new system to be adjusted according to the actual operation conditions to maximize the optimization of the transformer's fault warning effect. This can reduce false alarms or missed alarms caused by improper settings or incomplete understanding of the transformer's operating characteristics.

[0068] It should be noted that the first preset time period and the second preset time period are time periods set by professionals according to actual conditions, and the specific time period values ​​are not limited.

[0069] In one embodiment, the method for obtaining the first variation coefficient is:

[0070] The power variation coefficient, the sensor variation coefficient and the temperature and humidity variation coefficient are obtained according to the first state data and the second state data, and the power variation coefficient, the sensor variation coefficient and the temperature and humidity variation coefficient are comprehensively analyzed to obtain the first variation coefficient.

[0071] In one embodiment, the method for obtaining the power variation coefficient is:

[0072] Obtain the actual current and voltage of each transformer before replacement at different times in the last first preset time period when no accidents have occurred, and mark them as V 前 fand I 前 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer;

[0073] Obtain the actual current and voltage of the corresponding replaced transformer at different times within the first preset time period just after replacement, and mark them as V 后 f and I 后 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer;

[0074] Calculate the power of the transformer at different times before and after replacement. The calculation formula is: P 前 f =i 前 f ×V 前 f , P 后 f =I 后 f ×V 后 f Where, P 前 f is the power of the transformer at different times before replacement, P 后 f The power of the transformer at different times after replacement

[0075] Calculate the power variation coefficient using the following formula: Where, Bax represents the power variation coefficient;

[0076] It should be noted that the actual current and voltage of each replaced transformer at different times within the first preset time period after replacement can be obtained based on the real-time monitoring system of the transformer itself, or in other ways, which are not limited or elaborated in detail.

[0077] In one implementation, the power variation coefficient of the transformer calculated by the above method is more accurate and can represent the actual power of the transformer before and after replacement.

[0078] In one embodiment, the method for obtaining the sensor variation coefficient is:

[0079] Obtain the number and type of sensors of each transformer before replacement in the last first preset time period when no accidents have occurred, and obtain the number and type of sensors of the corresponding transformer after replacement in the first preset time period just after replacement;

[0080] Compare the types of sensors before and after the transformer is replaced, mark the sensors with inconsistent types as 1, mark the sensors with consistent types as 0, and obtain the number of 1s, which is recorded as the number of inconsistencies;

[0081] The difference in the number of sensors before and after the transformer is replaced is calculated, and the difference in the number and the number of inconsistencies are weighted summed to obtain the sensor variation coefficient.

[0082] It should be noted that the number and type of sensors of the replaced transformer within the first preset time period after the replacement can be obtained according to the installation log of the transformer, or in other ways, which are not limited or elaborated in detail.

[0083] In one implementation, this method can be used to quantify the changes in the types and quantities of sensors used in the transformer after replacement, obtain a more accurate sensor variation coefficient, and more accurately evaluate whether changes in the sensor configuration of the transformer system may affect the accuracy and effectiveness of the current fault warning system.

[0084] In one embodiment, the method for obtaining the temperature and humidity variation coefficient is:

[0085] Obtain the average temperature and average humidity of each transformer before replacement in the last first preset time period when no accidents have occurred, and record them as the pre-replacement temperature and pre-replacement humidity;

[0086] Obtaining the average temperature and average humidity of the corresponding replaced transformer within a first preset time period just after replacement, and recording them as the post-replacement temperature and the post-replacement humidity;

[0087] The absolute temperature difference and the absolute humidity difference are calculated according to the temperature and humidity before and after the replacement, and the absolute temperature difference and the absolute humidity difference are weightedly summed to obtain the temperature and humidity change coefficient.

[0088] It should be noted that the average temperature and average humidity of the replaced transformer within the first preset time period after replacement can be obtained in real time based on temperature and humidity sensors installed around or inside the transformer, or in other ways, which are not limited or elaborated in detail.

[0089] In one implementation, this method can be used to quantify changes in temperature and humidity of the transformer after replacement, obtain a more accurate temperature and humidity variation coefficient, and use the temperature and humidity variation coefficient to evaluate the potential impact of changes in environmental conditions on transformer operation.

[0090] In one embodiment, the method for obtaining the first variation coefficient is:

[0091] The power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient are normalized to construct the first variation coefficient model and generate the first variation coefficient Dgf. The specific formula is as follows:

[0092]

[0093] In the formula, Dgf is the first variation coefficient, Bax, Dsx and Hlm are the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, a1, a2 and a3 are the preset proportional coefficients of the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, and a1, a2 and a3 are all greater than 0.

[0094] In one implementation, the first variation coefficient obtained by the above method is more accurate and more consistent with the actual situation of the transformer before and after replacement.

[0095] It should be noted that the reason why the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient are selected to calculate the first variation coefficient instead of other parameters is that power, sensor and temperature and humidity are key factors affecting the operation of the transformer. The power variation coefficient reflects the changes in power transmission and transformer load, the sensor variation coefficient reflects the changes in the monitoring system and data acquisition, and the temperature and humidity variation coefficient reflects the impact of environmental conditions on transformer performance, which is directly related to the changes before and after the transformer is replaced, and can thus more accurately determine whether the transformer fault warning system before replacement is still in use.

[0096] In one embodiment, comparing the first variation coefficient with a preset variation coefficient threshold, and changing the fault warning system corresponding to the replaced transformer according to the comparison result includes:

[0097] The first variation coefficient is compared with a preset variation coefficient threshold value, and if the first variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer;

[0098] If the first variation coefficient is not less than the preset variation coefficient threshold, an alarm is immediately issued to remind the staff to reset the fault warning system for the replaced transformer.

[0099] In one implementation, the preset variation coefficient threshold is set by professionals according to actual conditions and is not specifically limited.

[0100] In one embodiment, aging data of each replaced transformer after running for a second preset time period is obtained, an aging coefficient is obtained according to the aging data, and a second variation coefficient is obtained according to the aging coefficient and the first variation coefficient;

[0101] Obtaining the initial insulation resistance of each replaced transformer after running for a first preset period of time, and recording it as the initial resistance, and obtaining the current insulation resistance after running for a second preset period of time, and calculating the absolute difference between the initial insulation resistance and the current insulation resistance, and dividing the absolute difference by the initial insulation resistance to obtain the insulation aging coefficient;

[0102] Obtain the time from the first maintenance to the last maintenance of each replaced transformer between the first preset time period and the second preset time period, obtain the total maintenance time, obtain the corresponding number of maintenance times, calculate the ratio of the total maintenance time to the number of maintenance times, and obtain the average maintenance interval time; obtain the time interval from the last maintenance time to the current time, obtain the current maintenance time interval, and divide the current maintenance time interval by the average maintenance interval time to obtain the maintenance interval coefficient;

[0103] Obtain the load of each replaced transformer after running for a first preset time period and the load at the current moment, calculate the difference between the load after the first preset time period and the load at the current moment, obtain the load change difference, calculate the ratio of the load change difference and the load after the first preset time period, and obtain the load change coefficient;

[0104] The insulation aging coefficient, the maintenance interval coefficient and the load variation coefficient are weightedly summed to obtain the aging coefficient, and the second variation coefficient is obtained according to the aging coefficient and the first variation coefficient.

[0105] It should be noted that the initial insulation resistance and current insulation resistance of the replaced transformer can be obtained through the transformer maintenance and inspection records. During each maintenance or inspection process, the insulation resistance of the transformer is usually measured. These records should be recorded by the maintenance team or operation and maintenance personnel in the maintenance report or maintenance management system, or in other ways, which are not limited or elaborated. The time interval from the time of the first maintenance of the transformer to the time of the last maintenance, the time of the last maintenance to the current time, and the number of maintenance of the transformer can be obtained from the maintenance record or maintenance management system. The record usually includes the start and end date and time of each maintenance, as well as the specific content and number of maintenance. These data are recorded and maintained by the maintenance team or maintenance recorder, or in other ways, which are not limited or elaborated. The load of each replaced transformer after the first preset time period and the load at the current moment can be obtained through a real-time monitoring system or a regular load measurement device. Usually, a load monitoring device is installed at the transformer installation location or the main control room. These devices will record and transmit load data. In addition, the load data of the transformer can also be obtained in regular load tests or regular inspections, or in other ways, which are not limited or elaborated.

[0106] It should be noted that the effects of the insulation aging coefficient, maintenance interval coefficient and load variation coefficient on the aging of the transformer are different, reflecting the changes and degradation of key parameters of the transformer during use. The insulation aging coefficient directly affects the electrical performance and insulation strength of the transformer. As the degree of aging increases, the dielectric properties of the insulation material may decrease, increasing the risk of insulation breakdown and failure. The maintenance interval coefficient reflects the frequency and timeliness of maintenance and repair of the transformer during use. A high coefficient may mean less maintenance needs, but attention should be paid to the timeliness of maintenance. The load variation coefficient affects the thermal stress and electrical stability of the transformer. Frequent load changes may accelerate the aging and damage of the equipment.

[0107] It should be noted that the insulation aging coefficient, maintenance interval coefficient and load change coefficient are normalized to construct an aging coefficient model and generate the aging coefficient Lky. The specific formula is as follows: Lky=b1×Ash+b2×Gnv+b3×Cbn, where Lky is the aging coefficient, Ash, Gnv and Cbn are the insulation aging coefficient, maintenance interval coefficient and load change coefficient, respectively, b1, b2 and b3 are the preset proportional coefficients of the insulation aging coefficient, maintenance interval coefficient and load change coefficient, respectively, and b1, b2 and b3 are all greater than 0.

[0108] It should be noted that the reason why the insulation aging coefficient, maintenance interval coefficient and load change coefficient are used to calculate the aging coefficient instead of other parameters is:

[0109] Selection of insulation aging coefficient: The insulation system of the transformer is a key component, which directly affects electrical safety and operational stability. Over time, the insulation material will gradually fail due to factors such as electrothermal aging and hygrothermal aging, resulting in reduced insulation strength and increased risk of insulation breakdown. Therefore, the addition of the insulation aging coefficient can effectively evaluate the health of the transformer insulation system and help predict the possibility of insulation failure.

[0110] Selection of maintenance interval coefficient: The maintenance and repair of transformers are crucial to their long-term operation. The maintenance interval coefficient reflects the frequency and timeliness of maintenance and overhaul of transformers during use. Shorter maintenance intervals may imply frequent maintenance and potential problems, while longer maintenance intervals may mean lower maintenance requirements, but the timeliness and adequacy of maintenance need to be ensured. Therefore, the introduction of maintenance interval coefficients helps to evaluate the maintenance management efficiency of transformers and the rationality of maintenance strategies.

[0111] Selection of load variation coefficient: The load variation experienced by the transformer during operation directly affects the thermal stress and stability of its electrical components. Frequent load variations may accelerate the aging and damage of the internal components of the transformer, posing a potential threat to the stability of the power system. Therefore, the consideration of the load variation coefficient can help evaluate the performance changes of the transformer under different load conditions.

[0112] In summary, the reason for selecting the insulation aging factor, maintenance interval factor and load variation factor to construct the aging factor model is that they can comprehensively evaluate the key aspects of the long-term operation of the transformer and help predict and manage the aging process and possible failure risks of the transformer.

[0113] In one implementation, the aging coefficient obtained by the above method is more accurate and more consistent with the actual aging condition of the replaced transformer.

[0114] In one embodiment, obtaining the second variation coefficient according to the aging coefficient and the first variation coefficient includes:

[0115] The second variation coefficient can be obtained according to the aging coefficient and the first variation coefficient through the following formula: Dps=Dgf×(1+Lky), where Dps is the second variation coefficient, Lky is the aging coefficient, and Dgf is the first variation coefficient.

[0116] It should be noted that the impact of transformer aging on the transformer's coefficient of variation is that transformer aging will cause changes in its physical, electrical, thermal, mechanical and other characteristics. These changes will directly affect the accuracy and reliability of the fault warning system currently used by the transformer before replacement. In order to ensure the effectiveness of the warning system, it is necessary to adjust and optimize it according to the actual state of the transformer after aging.

[0117] In one implementation, through the above method, the calculated second variation coefficient is more accurate and more consistent with the current situation of the replaced transformer.

[0118] In one embodiment, the second variation coefficient is compared with a preset variation coefficient threshold, and the fault warning system of each replaced transformer is adjusted according to the comparison result.

[0119] The second variation coefficient is compared with a preset variation coefficient threshold value, and if the second variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer;

[0120] If the second variation coefficient is not less than the preset variation coefficient threshold, an alarm is immediately issued to remind the staff to reset the fault warning system for the corresponding replaced transformer.

[0121] In one embodiment, the aging coefficient of the replaced transformer corresponding to the pre-replacement fault warning system is obtained at regular intervals, and the current change coefficient is calculated in combination with the first change coefficient, and the current change coefficient is compared with a preset change coefficient threshold, and it is determined whether to adjust the corresponding fault warning system of the replaced transformer based on the comparison result.

[0122] In one implementation method, by acquiring and evaluating the aging data of the transformer in real time, combining it with the initial variation coefficient, calculating the current variation coefficient and comparing it with the preset threshold, the fault warning system can be dynamically adjusted. This ensures that the fault warning system can accurately reflect the actual operating status and health status of the transformer, avoid false alarms or missed alarms caused by aging, improve the accuracy and reliability of transformer monitoring, and reduce management and operating costs.

[0123] Based on the same inventive concept, the embodiment of the present invention also provides a transformer fault early warning system based on the Internet of Things. Figure 2 , Figure 2 A schematic diagram of a transformer fault early warning framework based on the Internet of Things provided by an embodiment of the present invention includes:

[0124] The first state data module: extracts the power data, sensor data and environmental data of each transformer before replacement within the last first preset time period when no failure occurs from the historical data as the first state data;

[0125] A first variation coefficient module: obtaining power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculating a first variation coefficient of the transformer according to the first state data and the second state data;

[0126] A first comparison module: compares the first variation coefficient with a preset variation coefficient threshold, and adjusts the fault warning system of the corresponding replaced transformer according to the comparison result;

[0127] Second variation coefficient module: for each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtain its aging data after running for a second preset time period, obtain an aging coefficient according to the aging data, and obtain a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient and a load variation coefficient;

[0128] A second comparison module: comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result;

[0129] Timing adjustment module: regularly obtain the aging coefficient of the replaced transformer corresponding to the fault warning system before replacement, calculate the current change coefficient in combination with the first change coefficient, and compare the current change coefficient with the preset change coefficient threshold, and determine whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result.

[0130] Based on a transformer fault warning system based on the Internet of Things provided by an embodiment of the present invention, through the above-mentioned method, it is possible to judge whether the fault warning system corresponding to the transformer before replacement is still applicable to the fault warning of the transformer at the replaced position according to the actual situation, while saving management and operation costs, it is also possible to more accurately identify the potential failure risks of the transformer after replacement; in addition, for the transformer that still uses the fault warning system before replacement for fault warning, as time goes by, the fault warning system of the current transformer can be changed in time according to the actual situation, so that the potential failure risks of the transformer can be accurately identified. In addition, it is possible to periodically judge whether the fault warning system of the current transformer needs to be changed according to the current situation, so as to ensure timely and accurate identification of the potential failure risks of the transformer.

[0131] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A transformer fault early warning method based on the Internet of Things, characterized in that: The following steps are involved: Extracting power data, sensor data and environmental data of each transformer before replacement within a first preset time period when no failure occurs from the historical data as first state data; Acquire power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculate a first change coefficient of the transformer according to the first state data and the second state data; Comparing the first variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of the corresponding replaced transformer according to the comparison result; For each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtaining aging data of the transformer after running for a second preset time period, obtaining an aging coefficient according to the aging data, and obtaining a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient, and a load variation coefficient; comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result; Regularly obtain the aging coefficient of the replaced transformer corresponding to the pre-replacement fault warning system, calculate the current change coefficient in combination with the first change coefficient, compare the current change coefficient with the preset change coefficient threshold, and determine whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result; The method for obtaining the first coefficient of variation is: According to the first state data and the second state data, a power variation coefficient, a sensor variation coefficient and a temperature and humidity variation coefficient are obtained, and a first variation coefficient is obtained by comprehensively analyzing the power variation coefficient, the sensor variation coefficient and the temperature and humidity variation coefficient; The method for obtaining the power variation coefficient is: Obtain the actual current and voltage of each transformer before replacement at different times in the last first preset time period when no accidents have occurred, and mark them as V 前 f and I 前 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer; Obtain the actual current and voltage of the corresponding replaced transformer at different times within the first preset time period just after replacement, and mark them as V 后 f and I 后 f , f represents the sequence number of the actual current and voltage at different times, f = 1, 2, 3, 4, ..., n, n is a positive integer; Calculate the power of the transformer at different times before and after replacement. The calculation formula is: P 前 f =I 前 f ×V 前 f , P 后 f =I 后 f ×V 后 f Where, P 前 f is the power of the transformer at different times before replacement, P 后 f is the power of the transformer at different times after replacement; Calculate the power variation coefficient using the following formula: Where, Bax represents the power variation coefficient; The method for obtaining the sensor variation coefficient is: Obtain the number and type of sensors of each transformer before replacement in the last first preset time period when no accidents have occurred, and obtain the number and type of sensors of the corresponding transformer after replacement in the first preset time period just after replacement; Compare the types of sensors before and after the transformer is replaced, mark the sensors with inconsistent types as 1, mark the sensors with consistent types as 0, and obtain the number of 1s, which is recorded as the number of inconsistencies; Calculate the difference in the number of sensors before and after the transformer is replaced, and perform weighted summation of the difference in number and the number of inconsistencies to obtain the sensor variation coefficient; The method for obtaining the temperature and humidity variation coefficient is: Obtain the average temperature and average humidity of each transformer before replacement in the last first preset time period when no accidents have occurred, and record them as the pre-replacement temperature and pre-replacement humidity; Obtaining the average temperature and average humidity of the corresponding replaced transformer within a first preset time period just after replacement, and recording them as the post-replacement temperature and the post-replacement humidity; According to the temperature and humidity before and after the replacement, the absolute temperature difference and the absolute humidity difference are calculated respectively, and the absolute temperature difference and the absolute humidity difference are weightedly summed to obtain the temperature and humidity change coefficient; The method for obtaining the first coefficient of variation is: The power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient are normalized to construct the first variation coefficient model and generate the first variation coefficient Dgf. The specific formula is as follows: In the formula, Dgf is the first variation coefficient, Bax, Dsx and Hlm are the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, a1, a2 and a3 are the preset proportional coefficients of the power variation coefficient, sensor variation coefficient and temperature and humidity variation coefficient respectively, and a1, a2 and a3 are all greater than 0.

2. A transformer fault early warning method based on the Internet of Things according to claim 1, characterized in that: The first variation coefficient is compared with a preset variation coefficient threshold, and the fault warning system of the corresponding replaced transformer is adjusted according to the comparison result, including: The first variation coefficient is compared with a preset variation coefficient threshold value, and if the first variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer; If the first variation coefficient is not less than a preset variation coefficient threshold, an alarm is immediately issued and the fault warning system is reset for the replaced transformer.

3. The transformer fault early warning method based on the Internet of Things according to claim 1 is characterized in that: Acquire aging data of each replaced transformer after running for a second preset time period, obtain an aging coefficient according to the aging data, and obtain a second variation coefficient according to the aging coefficient and the first variation coefficient; Obtaining the initial insulation resistance of each replaced transformer after running for a first preset period of time, and recording it as the initial resistance, and obtaining the current insulation resistance after running for a second preset period of time, and calculating the absolute difference between the initial insulation resistance and the current insulation resistance, and dividing the absolute difference by the initial insulation resistance to obtain the insulation aging coefficient; Obtain the time from the first maintenance to the last maintenance of each replaced transformer between the first preset time period and the second preset time period, obtain the total maintenance time, obtain the corresponding number of maintenance times, calculate the ratio of the total maintenance time to the number of maintenance times, and obtain the average maintenance interval time; Obtain the time interval from the last maintenance time to the current time to obtain the current maintenance time interval, and divide the current maintenance time interval by the average maintenance time interval to obtain the maintenance interval coefficient; Obtain the load of each replaced transformer after running for a first preset time period and the load at the current moment, calculate the difference between the load after the first preset time period and the load at the current moment, obtain the load change difference, calculate the ratio of the load change difference and the load after the first preset time period, and obtain the load change coefficient; The insulation aging coefficient, the maintenance interval coefficient and the load variation coefficient are weightedly summed to obtain the aging coefficient, and the second variation coefficient is obtained according to the aging coefficient and the first variation coefficient.

4. The transformer fault early warning method based on the Internet of Things according to claim 3 is characterized in that: Obtaining the second variation coefficient according to the aging coefficient and the first variation coefficient includes: The second variation coefficient can be obtained according to the aging coefficient and the first variation coefficient through the following formula: Dps=Dgf×(1+Lky), where Dps is the second variation coefficient, Lky is the aging coefficient, and Dgf is the first variation coefficient.

5. The transformer fault early warning method based on the Internet of Things according to claim 1 is characterized in that: The second variation coefficient is compared with a preset variation coefficient threshold, and the fault warning system of each replaced transformer is adjusted according to the comparison result, including: The second variation coefficient is compared with a preset variation coefficient threshold value, and if the second variation coefficient is less than the preset variation coefficient threshold value, the transformer fault warning system before replacement is still used to provide a fault warning for the replaced transformer; If the second variation coefficient is not less than the preset variation coefficient threshold, an alarm is immediately issued and the fault warning system is reset for the replaced transformer.

6. A transformer fault early warning system based on the Internet of Things, used to implement a transformer fault early warning method based on the Internet of Things as described in any one of claims 1 to 5, characterized in that: The system comprises: The first state data module: extracts the power data, sensor data and environmental data of each transformer before replacement within the last first preset time period when no failure occurs from the historical data as the first state data; A first variation coefficient module: obtaining power data, sensor data and environmental data within a first preset time period after each transformer is replaced as second state data, and calculating a first variation coefficient of the transformer according to the first state data and the second state data; A first comparison module: compares the first variation coefficient with a preset variation coefficient threshold, and adjusts the fault warning system of the corresponding replaced transformer according to the comparison result; Second variation coefficient module: for each replaced transformer whose first variation coefficient is less than a preset variation coefficient threshold, obtain its aging data after running for a second preset time period, obtain an aging coefficient according to the aging data, and obtain a second variation coefficient according to the aging coefficient and the first variation coefficient; the aging data includes an insulation aging coefficient, a maintenance interval coefficient and a load variation coefficient; A second comparison module: comparing the second variation coefficient with a preset variation coefficient threshold, and adjusting the fault warning system of each replaced transformer according to the comparison result; Timing adjustment module: regularly obtain the aging coefficient of the replaced transformer corresponding to the fault warning system before replacement, calculate the current change coefficient in combination with the first change coefficient, and compare the current change coefficient with the preset change coefficient threshold, and determine whether to adjust the corresponding fault warning system of the replaced transformer according to the comparison result.

Images