Power transformer fault detection system and method based on Internet of Things

Abstract

The invention discloses a power transformer fault detection system and method based on the Internet of Things, and relates to the technical field of fault detection.The power transformer fault detection system comprises a data acquisition module, a data analysis module, a winding analysis module, a scheme making module, an early warning terminal and a database; if a fault occurs, analyzing the fault type of the winding, analyzing each potential fault type and simultaneously analyzing the fault degree of the winding, if the fault degree is high, analyzing the matching degree of each standby winding, randomly selecting a standby winding with the high matching degree for replacement, and if the fault degree is low, selecting the standby winding with the high matching degree for replacement. If yes, the fault type, each potential fault type and the operation environment of the winding are obtained, a maintenance scheme is formulated, whether the winding breaks down or not can be accurately judged, and the operation effect of the power transformer after winding replacement and the effectiveness of the maintenance scheme are guaranteed.

Description

Technical Field

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

[0002] Power transformers are vital equipment in power systems. Winding failure is one of the main causes of transformer failure and power system shutdown. The reliability of the winding's operating status directly affects the stability of power supply. Through the Internet of Things technology, real-time monitoring and data collection of the power transformer winding's operating status can be achieved, and data analysis algorithms can be used to timely and accurately determine whether the transformer's winding has a fault and the type of fault.

[0003] The traditional power transformer fault detection system and method determine whether the winding of the power transformer is faulty through certain data. If the winding is faulty, the cause and type of the winding fault are determined, and the degree of the winding fault is analyzed. If the degree of the winding fault is high, the winding is replaced. If the degree of the winding fault is low, a maintenance plan is formulated. Obviously, this power transformer fault detection system and method have at least the following shortcomings: 1. The traditional power transformer fault detection system and method determine whether the winding of the power transformer is faulty through a single data, and the winding fault does not necessarily cause the change of the data, and it is impossible to accurately determine whether the winding is faulty.

[0004] 2. When replacing the winding, the traditional power transformer fault detection system and method lack the analysis of the winding matching degree, and cannot determine whether the selected spare winding is suitable for the operation of the power transformer at this time, and then cannot guarantee the operation effect of the power transformer after replacing the winding.

[0005] 3. When a winding fails, it may cause other potential faults. However, the traditional power transformer fault detection system and method lack analysis in this regard and do not consider the impact of the operating environment on maintenance, and cannot guarantee the effectiveness of the maintenance plan. Summary of the invention

[0006] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a power transformer fault detection system and method based on the Internet of Things.

[0007] To solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect, the present invention provides an Internet of Things-based power transformer fault detection system, comprising the following modules: a data acquisition module, a data analysis module, a winding analysis module, a plan formulation module, an early warning terminal and a database.

[0008] The data acquisition module is used to set each acquisition point according to a preset distance interval, and to collect the temperature, amplitude and sound pressure level of each acquisition point in real time.

[0009] The data analysis module is used to obtain the temperature, amplitude and sound pressure level of each collection point at each operating moment, and analyze whether the winding of the power transformer is faulty. If a fault occurs, the winding analysis module is executed and an early warning is issued.

[0010] The winding analysis module includes a correlation analysis unit and a fault analysis unit.

[0011] The correlation analysis unit is used to obtain various fault types that occurred during various historical winding faults from a database, and analyze the correlation values ​​between various fault types.

[0012] The fault analysis unit is used to collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding.

[0013] The program formulation module is used to obtain various operating parameters of the winding, analyze the fault degree of the winding, and formulate a maintenance plan according to the fault degree.

[0014] The early warning terminal is used to issue an early warning when a winding failure occurs.

[0015] The database is used to store various fault types that occurred during various historical faults of the winding, various data of the winding when no fault occurred, and various maintenance plans.

[0016] In a second aspect, the present invention provides a method for detecting power transformer faults based on the Internet of Things, comprising the following steps: Step 1, data collection: setting each collection point at a preset distance interval, and collecting the temperature, amplitude and sound pressure level of each collection point in real time.

[0017] Step 2: Data analysis: Obtain the temperature, amplitude and sound pressure level of each collection point at each operating time, and analyze whether the winding of the power transformer is faulty. If a fault occurs, execute the winding analysis module and issue an early warning.

[0018] Step 3: Correlation analysis: Obtain the various fault types that occurred during each historical winding fault from the database, and analyze the correlation values ​​between the various fault types.

[0019] Step 4: Fault analysis: Collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding.

[0020] Step 5. Develop a maintenance plan: Obtain the operating parameters of the winding, analyze the fault level of the winding, and develop a maintenance plan based on the fault level.

[0021] The beneficial effects of the present invention are: 1. A power transformer fault detection system and method based on the Internet of Things, which determines whether a winding fault occurs by temperature, amplitude and sound pressure level. If a fault occurs, the fault type of the winding is analyzed, and each potential fault type is analyzed, and the fault degree of the winding is analyzed at the same time. If the fault degree is high, the matching degree of each spare winding is analyzed, and a spare winding with a high matching degree is randomly selected for replacement. If the fault degree is low, the fault type of the winding, each potential fault type and the operating environment are obtained, and a maintenance plan is formulated. It can accurately determine whether the winding has a fault, thereby ensuring the operating effect of the power transformer after replacing the winding and the effectiveness of the maintenance plan.

[0022] 2. The present invention analyzes the fault index of the winding through the temperature, vibration signal and sound signal of each collection point of the winding. If the fault index of the winding is 1, it means that the winding is faulty. If the fault index of the winding is 0, it means that the winding is not faulty. It can accurately determine whether the winding is faulty.

[0023] 3. When a winding fault occurs, the present invention first analyzes the correlation values ​​between the various fault types of the winding through the various fault types that occurred during each historical fault of the winding, and then analyzes the fault type of the winding, and obtains the various potential fault types of the winding according to the fault type of the winding. At the same time, a maintenance plan is formulated according to the fault type of the winding, various potential fault types and the operating environment, thereby ensuring the effectiveness of the maintenance plan.

[0024] 4. When replacing the windings, the present invention obtains the performance parameters and dimensions of each spare winding, and analyzes the matching degree of each spare winding according to the performance parameters and dimensions of each spare winding, and simultaneously obtains the spare windings with high matching degree, and randomly selects a spare winding from them for replacement, thereby ensuring the operating effect of the power transformer after replacing the windings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a schematic diagram of the system structure connection of the present invention.

[0027] Figure 2 The present invention is a schematic flow chart of the steps for implementing the method. DETAILED DESCRIPTION

[0028] 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.

[0029] See also Figure 1 As shown, the present invention provides a power transformer fault detection system based on the Internet of Things, including the following modules: a data acquisition module, a data analysis module, a winding analysis module, a solution formulation module, an early warning terminal and a database.

[0030] The data acquisition module is connected to the data analysis module, the data analysis module is connected to the winding analysis module and the early warning terminal, the winding analysis module is connected to the program formulation module, and the database is connected to the data analysis module, the winding analysis module and the program formulation module.

[0031] The data acquisition module is used to set each acquisition point according to a preset distance interval, and to collect the temperature, amplitude and sound pressure level of each acquisition point in real time.

[0032] It should be noted that the fiber grating sensor, vibration sensor and sound level meter are used to collect the temperature, amplitude and sound pressure level of each collection point in real time.

[0033] The data analysis module is used to obtain the temperature, amplitude and sound pressure level of each collection point at each operating moment, and analyze whether the winding of the power transformer is faulty. If a fault occurs, the winding analysis module is executed and an early warning is issued.

[0034] In a specific embodiment, the analysis of whether the winding of the power transformer is faulty is as follows: the temperature, amplitude and sound pressure level of each collection point at each operating time are obtained, and input into the sound abnormality model and the vibration abnormality model, and the sound abnormality value of each collection point is output. and the vibration abnormal values ​​of each collection point ,when or When, representing The sound of the first collection point is abnormal or The vibration of the collection point is abnormal. or When, representing The sound of the first collection point is normal or The vibration of the collection points is normal. Represents the number of each collection point, =1,2,3,..., , Represents the total number of collection points, and All are positive integers.

[0035] Among them, the sound abnormality model: , where Representative The sound pressure level at each operating moment, Representative The sound pressure level at each operating moment, Represents the preset sound pressure level difference threshold, Represents the preset sound pressure level difference threshold between adjacent operating moments, Represents the number of each running time, =1,2,3,..., , Represents the total number of running times, and are all positive integers, Represents the standard sound pressure level, wherein the preset sound pressure level difference threshold is determined by the staff according to the difference between the sound pressure level of the winding when the power transformer has not failed in the past and the standard sound pressure level, and the preset adjacent operating moment sound pressure level difference threshold is set by the staff according to the change of the sound pressure level of the winding at each operating moment when the power transformer has not failed in the past. The preset sound pressure level difference threshold and the preset adjacent operating moment sound pressure level difference threshold are both used to judge whether the sound of the winding is normal, wherein the standard sound pressure level is set by the staff.

[0036] In the above, the vibration abnormality model: , where Representative The amplitude of the running time, Representative The amplitude of the running time, Represents the preset amplitude difference threshold, Represents the preset amplitude difference threshold between adjacent running moments. Represents the standard amplitude, wherein the preset amplitude difference threshold is determined by the staff based on the difference between the amplitude of the winding and the standard amplitude when the power transformer has not failed in the past, and the preset adjacent operating moment amplitude difference threshold is set by the staff based on the change in amplitude at each operating moment when the power transformer has not failed in the past. Both the preset amplitude difference threshold and the preset adjacent operating moment amplitude difference threshold are used to determine whether the vibration of the winding is normal, wherein the standard amplitude is set by the staff.

[0037] It should be explained that when the power transformer has no faults, the amplitude and sound pressure level of each collection point at each operating moment are obtained from the database, and the average value is calculated and used as the standard amplitude and standard sound pressure level.

[0038] The temperature, sound abnormality value and vibration abnormality value of each collection point at each operating time are obtained and input into the winding abnormality model, and the winding abnormality value is output. If the winding abnormality value is 1, it means that the winding has a fault. If the winding abnormality value is 0, it means that the winding has not a fault.

[0039] It should be noted that the expression of the winding abnormality model is as follows: , where Representative Running time The temperature of the collection point, Representative Running time The temperature of the collection point, Representative The average temperature of the sampling points, Represents the preset temperature difference threshold, Represents the abnormal value of the winding, where the preset temperature difference threshold is set by the staff to determine whether the temperature change of each collection point is normal.

[0040] The winding analysis module includes a correlation analysis unit and a fault analysis unit.

[0041] The correlation analysis unit is used to obtain various fault types that occurred during various historical winding faults from a database, and analyze the correlation values ​​between various fault types.

[0042] In a specific embodiment, the analysis of the correlation value between each fault type is as follows: the fault types of each historical fault of the winding are obtained from the database, and are divided into a main fault type and each secondary fault type, and the main fault type and each secondary fault type of each historical fault of the winding are combined in pairs to obtain each fault combination.

[0043] It should be noted that various fault types include short circuit fault, open circuit fault and insulation fault.

[0044] It should also be noted that the data values ​​in each fault type are obtained, and the difference between the data values ​​in each fault type and the data values ​​during normal operation is calculated. At the same time, the sum of the data differences in each fault type is calculated and compared. The fault type with the largest sum of the data differences is taken as the main fault type, and the other fault types are taken as secondary fault types.

[0045] Compare each fault combination, divide each fault combination with the same main fault type into one category, and obtain each type of fault combination in this way; compare each fault combination in each type of fault combination, call each fault combination with the same type of combination the same fault combination, and obtain each same type of fault combination in each type of fault combination in this way, and count the number of fault combinations in each same type of fault combination and the number of fault combinations in each type of fault combination; in each type of fault combination, calculate the ratio of the number of fault combinations in each same type of fault combination to the number of fault combinations in the fault combination class to which each same type of fault combination belongs, and call it the proportion of each same type of fault combination, and obtain the proportion of each same type of fault combination in this way.

[0046] A certain same kind of fault combination is compared with other same kind of fault combinations, and the other same kind of fault combinations are called each compared same kind of fault combinations. If the main fault type in the same kind of fault combination is the same as the secondary fault type in a certain compared same kind of fault combination, and the secondary fault type in the same kind of fault combination is the same as the main fault type in the compared same kind of fault combination, then the same kind of fault combination and the compared same kind of fault combination are called associated combinations, and the same kind of fault combination is called the first fault combination, and the compared same kind of fault combination is called the second fault combination, and each associated combination is obtained in this way.

[0047] Obtain the proportion of the first fault combination and the proportion of the second fault combination in each associated combination according to the analysis formula: Get the first The associated value of the associated combination , where represents the proportion of the first fault combination, represents the proportion of the second fault combination, Represents the number of each associated combination, =1,2,3,..., , Represents the total number of associated combinations, and If they are all positive integers, the association value of each association combination represents the association value of each fault type in each association combination. This method is used to analyze the association value between each fault type.

[0048] The fault analysis unit is used to collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding.

[0049] In a specific embodiment, the fault analysis unit has the following specific process: obtaining the DC resistance, dielectric loss factor, no-load current and no-load loss of the winding, and analyzing the fault type of the winding based on the acquired data; at the same time, based on the fault type of the winding, obtaining various fault types that may occur in the winding, and calling them various potential fault types.

[0050] It should be noted that a DC resistance tester is used to measure the DC resistance of the winding, and a dielectric loss factor of the winding is measured using a dielectric loss tester.

[0051] It should also be noted that the power transformer is put into no-load operation state, and an ammeter and a power meter are used to measure the no-load current and no-load loss of the acquisition winding.

[0052] Among them, the process of obtaining the possible fault type of the winding is: obtaining the correlation value between the fault type of the winding and other fault types. If the correlation value between the fault type and one of the other fault types is greater than 0.6, it means that the fault type among the other fault types is the possible fault type of the winding. In this way, various possible fault types of the winding are obtained.

[0053] In the above, the specific process of analyzing the fault type of the winding is as follows: when the winding of the power transformer has no fault, the DC resistance, real-time dielectric loss factor, real-time no-load current and real-time no-load loss of the winding at each operating time are obtained from the database, and the average values ​​of the real-time DC resistance, real-time no-load current and real-time no-load loss are calculated, and the average values ​​are used as the standard value of the DC resistance, the standard value of the no-load current and the standard value of the no-load loss, and the dielectric loss factors at each operating time are compared to obtain the standard range of the dielectric loss factor.

[0054] Obtain the DC resistance of the winding, the dielectric loss factor of the winding, the no-load current and no-load loss of each phase winding, then: , where represents the DC resistance of the winding, Represents the dielectric loss factor of the winding, represents the no-load current of the winding, represents the no-load loss of the winding, Represents the standard value of DC resistance, Represents the standard range of dielectric loss factor, Represents the standard value of no-load current, Represents the standard value of no-load loss, Represents the return value of the winding fault type, Represents the preset DC resistance difference threshold, Represents the preset no-load current difference threshold, Represents the preset no-load loss difference threshold.

[0055] It should be noted that the preset DC resistance difference threshold is set by the staff and is used to determine whether the DC resistance of the winding is normal.

[0056] It should also be noted that the preset no-load current difference threshold and the preset no-load loss difference threshold are set by the staff to determine whether the no-load current and no-load loss of the winding are normal.

[0057] When the winding fault type return value is 1, it means that the winding fault type is an open circuit fault. When the winding fault type return value is 0, it means that the winding fault type is an insulation fault. When the winding fault type return value is -1, it means that the winding fault type is a short circuit fault.

[0058] The program formulation module is used to obtain various operating parameters of the winding, analyze the fault degree of the winding, and formulate a maintenance plan according to the fault degree.

[0059] In a specific embodiment, the maintenance plan is formulated, and the specific process is as follows: the values ​​of various operating parameters of the winding at various operating times when the power transformer is not faulty are obtained from the database, and the standard value range of each operating parameter is obtained by comparison. At the same time, various sensors are used to collect the various operating parameters of the winding at this time, and the fault degree return value of the winding is calculated. When the fault degree return value of the winding is 1, it means that the fault degree of the winding is high. When the fault degree return value of the winding is 0, it means that the fault degree of the winding is low.

[0060] It should be noted that the operating parameters include inductance, phase, voltage and resistance, etc.

[0061] It should also be noted that a mutual inductance sensor is used to collect inductance, a Hall effect sensor is used to collect phase, a voltage transformer is used to collect voltage, and a digital multimeter is used to collect resistance.

[0062] When the fault degree of the winding is high, the performance parameter values ​​and dimensions of each spare winding are obtained from the database, and the matching degree of each spare winding is analyzed, and a spare winding is randomly selected from each used winding with a high matching degree for replacement.

[0063] It should be noted that the performance parameters of the winding include withstand voltage, magnetic permeability, loss tangent and thermal conductivity.

[0064] When the fault degree of the winding is low, each maintenance plan in the database is obtained, and each operating parameter of the winding after maintenance in each maintenance plan is obtained, the maintenance effect score of each maintenance plan is calculated, and each fault type repaired in each maintenance plan is obtained, and compared with the fault type of the winding and each potential fault type. If the fault types repaired in a maintenance plan include the fault type of the winding and each potential fault type, then the maintenance plan is used as a backup maintenance plan. In this way, each backup maintenance plan is obtained, and the maintenance effect, maintenance time, maintenance cost and each operating environment parameter of each backup maintenance plan, as well as each operating environment parameter of the winding, are obtained, and normalized, then: , where Representative The first of the backup maintenance plans The operating environment parameter value, Represents the winding The operating environment parameter value, Representative The maintenance cost of the alternative maintenance plan, Representative The maintenance time of the backup maintenance plan, Representative The practicality coefficient of the backup maintenance plan, Representative The repair effect score of the backup repair plan, Represents the number of each alternative maintenance plan, =1,2,3,..., , represents the total number of alternative maintenance options, Represents the number of each operating environment parameter, =1,2,3,..., , Represents the total number of operating environment parameters. , , and All are positive integers.

[0065] It should be noted that the operating environment parameters include temperature, humidity, and air pressure.

[0066] The practicality coefficients of the main and backup maintenance plans are compared, and the backup maintenance plan with the largest practicality coefficient is selected and used as the final maintenance plan.

[0067] In the above, the calculation of the return value of the fault degree of the winding is specifically performed as follows: the values ​​of the various operating parameters of the winding and the standard value range of each operating parameter are obtained, and normalized, then: , where Representative The operating parameter values, Representative The minimum value of the standard numerical range of the operating parameters, Representative The maximum value of the standard value range of the operating parameter, Represents the preset fault level indicator threshold, Represents the number of each operating parameter, =1,2,3,..., , Represents the total number of operating parameters, and are both positive integers, represents a natural constant, Return value representing the fault degree of the winding.

[0068] It should be noted that the preset fault degree index threshold is set by the staff and is used to judge the fault degree of the winding.

[0069] In the above, the matching degree of each spare winding is analyzed, and the specific process is as follows: the performance parameter values ​​and sizes of each spare winding are obtained from the database, and the standard value range of each performance parameter of the winding and the required size of the winding are obtained, and normalized, then: , where Representative The size of the spare winding, Representative The first spare winding Performance parameter values, Represents winding No. The minimum value of the standard numerical range of each performance parameter, Represents winding No. The maximum value of the standard value range of each performance parameter, represents the required size of the winding, represents the preset performance coefficient threshold, Representative The matching coefficient of the spare winding, Represents the number of the spare winding, =1,2,3,..., , represents the total number of spare windings, Represents the performance parameter number of the winding, =1,2,3,..., , Represents the total number of performance parameters of the winding, , , and All are positive integers.

[0070] It should be noted that the standard numerical range of each performance parameter of the winding is set by the staff to ensure that the winding can operate normally, and the required size of the winding is also set by the staff.

[0071] It should also be noted that .

[0072] When the matching coefficient of a spare winding is 1, it means that the matching degree of the spare winding is high. When the matching coefficient of a spare winding is 0, it means that the matching degree of the spare winding is low. This method is used to analyze the matching degree of each spare winding.

[0073] In the above, the specific process of calculating the maintenance effect score of each maintenance plan is as follows: Obtain the operating parameters of the winding after maintenance, then: , where Representative In the alternative maintenance plan, the first winding after maintenance The operating parameter values, Representative The optimal values ​​of the operating parameters, Representative The maintenance effect score of the backup maintenance plan.

[0074] It should be noted that the operating efficiency at each operating time when the power transformer is not faulty is obtained from the database, and compared, the operating time with the highest operating efficiency is selected, and the operating parameter values ​​at this operating time are used as the optimal values ​​of each operating parameter.

[0075] The early warning terminal is used to issue an early warning when a winding failure occurs.

[0076] The database is used to store various fault types that occurred during various historical faults of the winding, various data of the winding when no fault occurred, and various maintenance plans.

[0077] It should be noted that the data of the winding when no fault occurs include various operating parameters, DC resistance, dielectric loss factor, no-load current and no-load loss.

[0078] See also Figure 2 As shown, the present invention provides a power transformer fault detection method based on the Internet of Things, comprising the following steps: Step 1, data collection: setting each collection point according to a preset distance interval, and collecting the temperature, amplitude and sound pressure level of each collection point in real time.

[0079] Step 2: Data analysis: Obtain the temperature, amplitude and sound pressure level of each collection point at each operating time, and analyze whether the winding of the power transformer is faulty. If a fault occurs, execute the winding analysis module and issue an early warning.

[0080] Step 3: Correlation analysis: Obtain the various fault types that occurred during each historical winding fault from the database, and analyze the correlation values ​​between the various fault types.

[0081] Step 4: Fault analysis: Collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding.

[0082] Step 5. Develop a maintenance plan: Obtain the operating parameters of the winding, analyze the fault level of the winding, and develop a maintenance plan based on the fault level.

[0083] The embodiment of the present invention determines whether a winding fault occurs through temperature, amplitude and sound pressure level. If a fault occurs, the fault type of the winding is analyzed, and each potential fault type is analyzed, and the fault degree of the winding is analyzed at the same time. If the fault degree is high, the matching degree of each spare winding is analyzed, and a spare winding with a high matching degree is randomly selected for replacement. If the fault degree is low, the fault type of the winding, each potential fault type and the operating environment are obtained, and a maintenance plan is formulated. It can accurately determine whether the winding has a fault, and ensure the operating effect of the power transformer after replacing the winding and the effectiveness of the maintenance plan.

[0084] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they shall all fall within the protection scope of the present invention.

Claims

1. A power transformer fault detection system based on the Internet of Things, characterized in that: Includes the following modules: The data acquisition module is used to set each acquisition point according to a preset distance interval, and to collect the temperature, amplitude and sound pressure level of each acquisition point in real time; The data analysis module is used to obtain the temperature, amplitude and sound pressure level of each collection point at each operating time, and analyze whether the winding of the power transformer is faulty. If a fault occurs, the winding analysis module is executed and an early warning is issued; The winding analysis module includes a correlation analysis unit and a fault analysis unit: The correlation analysis unit is used to obtain various fault types that occurred during various historical faults of the winding from the database, and analyze the correlation values ​​between the various fault types; The fault analysis unit is used to collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding; The plan formulation module is used to obtain various operating parameters of the winding, analyze the fault degree of the winding, and formulate a maintenance plan based on the fault degree; The early warning terminal is used to give an early warning when a winding fault occurs; The database is used to store various fault types that occurred during each historical fault of the winding, various data of the winding when no fault occurred, and various maintenance plans.

2. The power transformer fault detection system based on the Internet of Things according to claim 1 is characterized in that: The specific process of analyzing whether the winding of the power transformer is faulty is as follows: Obtain the temperature, amplitude and sound pressure level of each collection point at each operating time, and input them into the sound anomaly model and vibration anomaly model, and output the sound anomaly value of each collection point and the vibration abnormal values ​​of each collection point ,when or When, representing The sound of the first collection point is abnormal or The vibration of the collection point is abnormal. or When, representing The sound of the first collection point is normal or The vibration of the collection points is normal. Represents the number of each collection point, =1,2,3,..., , Represents the total number of collection points, and All are positive integers; The temperature, sound abnormality value and vibration abnormality value of each collection point at each operating time are obtained and input into the winding abnormality model, and the winding abnormality value is output. If the winding abnormality value is 1, it means that the winding has a fault. If the winding abnormality value is 0, it means that the winding has not a fault.

3. The power transformer fault detection system based on the Internet of Things according to claim 1 is characterized in that: The specific process of analyzing the correlation values ​​between various fault types is as follows: Obtain each fault type at each historical fault of the winding from the database, and divide it into a main fault type and each secondary fault type, and combine the main fault type and each secondary fault type at each historical fault of the winding in pairs to obtain each fault combination; Compare each fault combination, classify each fault combination with the same main fault type into one category, and obtain each type of fault combination in this way; compare each fault combination in each type of fault combination, and refer to each fault combination with the same combination as the same type of fault combination; obtain each same type of fault combination in each type of fault combination in this way, and count the number of fault combinations in each same type of fault combination and the number of fault combinations in each type of fault combination; in each type of fault combination, calculate the ratio of the number of fault combinations in each same type of fault combination to the number of fault combinations in the fault combination class to which each same type of fault combination belongs, and refer to it as the proportion of each same type of fault combination; and obtain the proportion of each same type of fault combination in this way; A certain same type of fault combination is compared with other same type of fault combinations, and the other same type of fault combinations are referred to as each compared same type of fault combination. If the main fault type in the same type of fault combination is the same as the secondary fault type in a certain compared same type of fault combination, and the secondary fault type in the same type of fault combination is the same as the main fault type in the compared same type of fault combination, then the same type of fault combination and the compared same type of fault combination are referred to as associated combinations, and the same type of fault combination is referred to as a first fault combination, and the compared same type of fault combination is referred to as a second fault combination, and each associated combination is obtained in this way; Obtain the proportion of the first fault combination and the proportion of the second fault combination in each associated combination according to the analysis formula: Get the first The associated value of the associated combination , where represents the proportion of the first fault combination, represents the proportion of the second fault combination, Represents the number of each associated combination, =1,2,3,..., , Represents the total number of associated combinations, and If they are all positive integers, the association value of each association combination represents the association value of each fault type in each association combination. This method is used to analyze the association value between each fault type.

4. The power transformer fault detection system based on the Internet of Things according to claim 1 is characterized in that: The specific process of the fault analysis unit is as follows: The DC resistance, dielectric loss factor, no-load current and no-load loss of the winding are obtained, and the fault type of the winding is analyzed based on the obtained data. At the same time, based on the fault type of the winding, various fault types that may occur in the winding are obtained and are called various potential fault types.

5. The power transformer fault detection system based on the Internet of Things according to claim 4 is characterized in that: The specific process of analyzing the fault type of the winding is as follows: Obtaining from the database the DC resistance, real-time dielectric loss factor, real-time no-load current and real-time no-load loss of the winding at each operating moment when the winding of the power transformer is not faulty, and calculating the average values ​​of the real-time DC resistance, real-time no-load current and real-time no-load loss, using the average values ​​as the standard value of the DC resistance, the standard value of the no-load current and the standard value of the no-load loss, comparing the dielectric loss factors at each operating moment, and obtaining the standard range of the dielectric loss factor; Obtain the DC resistance of the winding, the dielectric loss factor of the winding, the no-load current and no-load loss of each phase winding, then: ， In the formula represents the DC resistance of the winding, Represents the dielectric loss factor of the winding, represents the no-load current of the winding, represents the no-load loss of the winding, Represents the standard value of DC resistance, Represents the standard range of dielectric loss factor, Represents the standard value of no-load current, Represents the standard value of no-load loss, Represents the return value of the winding fault type, Represents the preset DC resistance difference threshold, Represents the preset no-load current difference threshold, Represents the preset no-load loss difference threshold; When the winding fault type return value is 1, it means that the winding fault type is an open circuit fault. When the winding fault type return value is 0, it means that the winding fault type is an insulation fault. When the winding fault type return value is -1, it means that the winding fault type is a short circuit fault.

6. The power transformer fault detection system based on the Internet of Things according to claim 1 is characterized in that: The specific process of formulating a maintenance plan is as follows: The values ​​of the operating parameters of the winding at each operating time when the power transformer has no fault are obtained from the database, and the standard value range of each operating parameter is obtained by comparison. At the same time, each sensor is used to collect the operating parameters of the winding at this time, and the return value of the fault degree of the winding is calculated. When the return value of the fault degree of the winding is 1, it means that the fault degree of the winding is high, and when the return value of the fault degree of the winding is 0, it means that the fault degree of the winding is low; When the fault degree of the winding is high, the performance values ​​and dimensions of each spare winding are obtained from the database, and the matching degree of each spare winding is analyzed, and a spare winding is randomly selected from each used winding with a high matching degree for replacement; When the fault degree of the winding is low, each maintenance plan in the database is obtained, and each operating parameter of the winding after maintenance in each maintenance plan is obtained, the maintenance effect score of each maintenance plan is calculated, and each fault type repaired in each maintenance plan is obtained, and compared with the fault type of the winding and each potential fault type. If the fault types repaired in a maintenance plan include the fault type of the winding and each potential fault type, then the maintenance plan is used as a backup maintenance plan. In this way, each backup maintenance plan is obtained, and the maintenance effect, maintenance time, maintenance cost and each operating environment parameter of each backup maintenance plan, as well as each operating environment parameter of the winding, are obtained, and normalized, then: ， In the formula Representative The first of the backup maintenance plans The operating environment parameter value, Represents the winding The operating environment parameter value, Representative The maintenance cost of the alternative maintenance plan, Representative The maintenance time of the backup maintenance plan, Representative The practicality coefficient of the backup maintenance plan, Representative The repair effect score of the backup repair plan, Represents the number of each alternative maintenance plan, =1,2,3,..., , represents the total number of alternative maintenance options, Represents the number of each operating environment parameter, =1,2,3,..., , Represents the total number of operating environment parameters. , , and All are positive integers; Compare the practicality coefficients of the main and backup maintenance plans, select the backup maintenance plan with the largest practicality coefficient, and use the backup maintenance plan as the final maintenance plan; A maintenance plan is formulated according to steps S71 to S73.

7. The power transformer fault detection system based on the Internet of Things according to claim 6 is characterized in that: The specific process of calculating the return value of the fault degree of the winding is as follows: Obtain the values ​​of each operating parameter of the winding and the standard value range of each operating parameter, and perform normalization processing, then: ， In the formula Representative The operating parameter values, Representative The minimum value of the standard numerical range of the operating parameters, Representative The maximum value of the standard value range of the operating parameter, Represents the preset fault level indicator threshold, Represents the number of each operating parameter, =1,2,3,..., , Represents the total number of operating parameters, and are both positive integers, represents a natural constant, Return value representing the fault degree of the winding.

8. The power transformer fault detection system based on the Internet of Things according to claim 6 is characterized in that: The specific process of analyzing the matching degree of each spare winding is as follows: The performance parameter values ​​and sizes of each spare winding are obtained from the database, and the standard value range of each performance parameter of the winding and the required size of the winding are obtained, and normalized. Then: ， In the formula Representative The size of the spare winding, Representative The first spare winding Performance parameter values, Represents winding No. The minimum value of the standard numerical range of each performance parameter, Represents winding No. The maximum value of the standard value range of each performance parameter, represents the required size of the winding, represents the preset performance coefficient threshold, Representative The matching coefficient of the spare winding, Represents the number of the spare winding, =1,2,3,..., , represents the total number of spare windings, Represents the performance parameter number of the winding, =1,2,3,..., , Represents the total number of performance parameters of the winding, , , and All are positive integers; When the matching coefficient of a spare winding is 1, it means that the matching degree of the spare winding is high. When the matching coefficient of a spare winding is 0, it means that the matching degree of the spare winding is low. This method is used to analyze the matching degree of each spare winding.

9. The power transformer fault detection system based on the Internet of Things according to claim 7 is characterized in that: The specific process of calculating the maintenance effect score of each maintenance plan is as follows: Get the operating parameters of the winding after maintenance: ， In the formula Representative In the alternative maintenance plan, the first winding after maintenance The operating parameter values, Representative The optimal values ​​of the operating parameters, Representative The maintenance effect score of the backup maintenance plan.

10. A fault detection method for a power transformer fault detection system based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include: Step 1: Data collection: Set each collection point at a preset distance interval, and collect the temperature, amplitude and sound pressure level of each collection point in real time; Step 2: Data analysis: Obtain the temperature, amplitude and sound pressure level of each collection point at each operating time, analyze whether the winding of the power transformer is faulty, and if a fault occurs, execute the winding analysis module and issue an early warning; Step 3: Correlation analysis: Obtain the various fault types that occurred during each historical fault of the winding from the database, and analyze the correlation values ​​between the various fault types; Step 4: Fault analysis: Collect various parameters of the winding, analyze the fault type of the winding, and analyze other fault types that may be caused by the fault type of the winding; Step 5. Develop a maintenance plan: Obtain the operating parameters of the winding, analyze the fault level of the winding, and develop a maintenance plan based on the fault level.

Images