Transformer mechanical state diagnosis method and system

Abstract

The invention relates to the technical field of transformers, and discloses a transformer mechanical state diagnosis method and system, and the method comprises the steps: obtaining a first variable quantity vector, a second variable quantity vector, a third variable quantity vector and a fourth variable quantity vector through comprehensive analysis of frequency domain amplitude vectors of a vibration signal, a current signal and a voltage signal, the method can accurately reflect the key feature information of the mechanical state change of the transformer, effectively overcomes the problem that the existing vibration-based diagnosis method is not high in accuracy, can quickly and accurately diagnose the mechanical state of the transformer, is suitable for quick and accurate on-site research and judgment, greatly improves the efficiency and accuracy of the mechanical state diagnosis of the transformer, and reduces the cost. And powerful technical support is provided for ensuring safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and particularly to a method and system for diagnosing the mechanical state of a transformer. Background Art

[0002] In the power system, as a core device, the stability of the mechanical state of a transformer plays a decisive role in the safe and reliable operation of the power grid. Accurately and timely diagnosing the mechanical state of a transformer can detect potential faults in advance, avoid equipment damage and power outage accidents, and is of great significance for ensuring the stable operation of the power system.

[0003] Traditional methods for diagnosing the mechanical state of transformers, such as oil chromatography analysis and partial discharge detection, have a certain degree of accuracy in transformer state assessment. However, these methods have obvious limitations. Oil chromatography analysis requires regular sampling and testing of transformer oil, with a long detection cycle and unable to reflect the operating state of the transformer in real time; partial discharge detection usually requires professional equipment and complex operations, with a high detection cost, and some detection methods require the transformer to be powered off, which not only affects the normal power supply of the power grid but also increases the difficulty and cost of detection. Therefore, traditional methods are difficult to meet the requirements of on-site rapid diagnosis and are restricted in practical applications.

[0004] In recent years, the technology for diagnosing the mechanical state of transformers based on vibration has gradually emerged. By collecting and analyzing the vibration signals generated during the operation of the transformer, this technology can effectively reflect the changes in its internal mechanical state and electrical state. Compared with traditional diagnostic methods, the vibration-based diagnostic technology has significant advantages such as non-invasive, real-time online, and low cost. It does not require the transformer to be powered off and does not interfere with the normal operation of the transformer, and can obtain the operating state information of the transformer in real time, providing a new way for the state monitoring and fault diagnosis of the transformer.

[0005] Although the vibration-based technology for diagnosing the mechanical state of transformers has many advantages, there are still some problems in its actual application. Existing vibration-based diagnostic methods lack effective comprehensive analysis means when processing vibration signals, current signals, and voltage signals, and it is difficult to accurately extract the key feature information reflecting the changes in the mechanical state of the transformer, resulting in low accuracy and reliability of the diagnostic results and unable to meet the requirements of on-site rapid and accurate diagnosis of the mechanical state of the transformer. Summary of the Invention

[0006] Based on this, it is necessary to propose a transformer mechanical state diagnosis method and system for the above problems, which can accurately reflect the key characteristic information of the change of the transformer mechanical state, effectively overcome the problem of low accuracy of the existing vibration-based diagnosis method, and can quickly and accurately diagnose the mechanical state of the transformer, which is applicable to rapid and accurate judgment on site, greatly improving the efficiency and accuracy of the transformer mechanical state diagnosis, and providing strong technical support for ensuring the safe and stable operation of the power system.

[0007] To achieve the above object, in the first aspect of the present invention, a transformer mechanical state diagnosis method is provided, and the method includes: Determine the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be measured in each time period; Judge whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period to obtain a first judgment result, and judge whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period to obtain a second judgment result; If the first judgment result is the same, determine a first change vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a second change vector according to the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period. If the second judgment result is the same, determine a third change vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a fourth change vector according to the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1; If j is less than the total number of time periods, let j = j + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; If j is equal to the total number of time periods and i is less than the total number of time periods, let i = i + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; If i is equal to the total number of time periods, diagnose whether the mechanical state of the transformer to be measured has changed according to all the first change vectors, all the second change vectors, all the third change vectors, and all the fourth change vectors.

[0008] Optionally, the diagnosing whether the mechanical state of the transformer to be measured has changed according to all the first change vectors, all the second change vectors, all the third change vectors, and all the fourth change vectors includes: Input all the second change amount vectors and all the fourth change amount vectors into a preset transfer parameter model to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors; Diagnose whether the mechanical state of the transformer under test has changed according to all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors.

[0009] Optionally, the preset transfer parameter model includes a first transfer parameter model between the vibration change amount and the voltage change amount and a second transfer parameter model between the vibration change amount and the current change amount. The step of inputting all the second change amount vectors and all the fourth change amount vectors into the preset transfer parameter model to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors includes: Input all the second change amount vectors into the first transfer parameter model in sequence to obtain a plurality of first predicted change amount vectors; Input all the fourth change amount vectors into the second transfer parameter model in sequence to obtain a plurality of second predicted change amount vectors.

[0010] Optionally, the step of diagnosing whether the mechanical state of the transformer under test has changed according to all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors includes: Diagnose whether the mechanical state of the iron core of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector; Diagnose whether the mechanical state of the winding of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector.

[0011] Optionally, the step of diagnosing whether the mechanical state of the iron core of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector includes: Determine the total first difference rate between each element in each first change amount vector and each element in the corresponding first predicted change amount vector, and the first difference rate between each element in each first change amount vector and the corresponding element in the corresponding first predicted change amount vector; Among all the total first difference rates and all the first difference rates, if there is a total first difference rate with a difference rate sum greater than the first preset percentage, or there is a first difference rate with a difference rate greater than the second preset percentage, diagnose that the mechanical state of the iron core of the transformer under test has changed; otherwise, diagnose that the mechanical state of the iron core of the transformer under test has not changed.

[0012] Optionally, diagnosing whether the winding mechanical state of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector includes: Determining the total second difference rate between each element in each third change amount vector and each element in the corresponding second predicted change amount vector, and the second difference rate between each element in each third change amount vector and the corresponding element in the corresponding second predicted change amount vector; Among all the total second difference rates and all the second difference rates, if there is a first total difference rate whose total difference rate is greater than the third preset percentage, or a first difference rate whose difference rate is greater than the first preset percentage, it is diagnosed that the winding mechanical state of the transformer under test has changed; otherwise, it is diagnosed that the winding mechanical state of the transformer under test has not changed.

[0013] Optionally, determining the frequency-domain vibration amplitude vectors of the vibration signals of the transformer under test in each time period includes: Obtaining the sensing signals of all vibration sensors, where all vibration sensors are uniformly installed on the fuel tank of the transformer under test; Dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals of each time period, where the initial value of n is 1; Performing time-frequency domain conversion on the vibration signal of each time period to obtain the frequency-domain vibration amplitude vectors of each time period; Diagnosing whether the mechanical state of the transformer under test has changed according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, and all the third change amount vectors and the corresponding multiple second predicted change amount vectors includes: Diagnosing whether the mechanical state of the transformer under test has changed at the nth vibration sensor according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, and all the third change amount vectors and the corresponding multiple second predicted change amount vectors; Let n = n + 1, and return to execute the step of dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals of each time period until n is equal to the total number of vibration sensors.

[0014] Optionally, determining the frequency-domain current amplitude vectors of the current signals and the frequency-domain voltage amplitude vectors of the voltage signals of the transformer under test in each time period includes: Obtaining the mutual inductance current signal of the current transformer and the mutual inductance voltage signal of the voltage transformer, where the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer under test; Divide the mutual inductance current signal into time periods to obtain the current signals for each time period, and divide the mutual inductance voltage signal into time periods to obtain the voltage signals for each time period; Perform time-frequency domain conversion on the current signal for each time period to obtain the frequency-domain current amplitude vectors for each time period, and perform time-frequency domain conversion on the time-domain voltage signal for each time period to obtain the frequency-domain voltage amplitude vectors for each time period.

[0015] Optionally, the method further includes: When the transformer under test is first put into operation or operates normally, determine the normal frequency-domain vibration amplitude vectors of the normal vibration signals, the normal frequency-domain current amplitude vectors of the normal current signals, and the normal frequency-domain voltage amplitude vectors of the normal voltage signals for each time period of the transformer under test; Judge whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period to obtain the first normal judgment result, and judge whether the normal frequency-domain voltage amplitude vector in the x-th time period is the same as the normal frequency-domain voltage amplitude vector in the y-th time period to obtain the second normal judgment result; If the first normal judgment results are the same, determine the first normal change amount vector according to the normal frequency-domain vibration amplitude vector in the x-th time period and the normal frequency-domain vibration amplitude vector in the y-th time period, and determine the second normal change amount vector according to the normal frequency-domain voltage amplitude vector in the x-th time period and the normal frequency-domain voltage amplitude vector in the y-th time period. If the second normal judgment results are the same, determine the third normal change amount vector according to the normal frequency-domain vibration amplitude vector in the x-th time period and the normal frequency-domain vibration amplitude vector in the y-th time period, and determine the fourth normal change amount vector according to the normal frequency-domain current amplitude vector in the x-th time period and the normal frequency-domain current amplitude vector in the y-th time period. The initial value of x is 1, and the initial value of y is 1; If y is less than the total number of time periods, let y = y + 1, and return to execute the step of judging whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period; If y is equal to the total number of time periods and x is less than the total number of time periods, let x = x + 1, and return to execute the step of judging whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period; If x is equal to the total number of time periods, input all the first normal change amount vectors and all the second normal change amount vectors into the first initial machine learning model for training to obtain the first transfer parameter model, and input all the third normal change amount vectors and all the fourth change amount vectors into the second initial machine learning model for training to obtain the second transfer parameter model.

[0016] To achieve the above object, in a second aspect, the present invention provides a transformer mechanical state diagnosis system, which includes a plurality of vibration sensors, a current transformer, a voltage transformer, and a processor; The plurality of vibration sensors are evenly installed on the oil tank wall of the transformer to be measured, and the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer to be measured; The processor is used to execute the method described in any one of the first aspect.

[0017] To achieve the above object, in a third aspect, the present invention provides a transformer mechanical state diagnosis device, which includes: A determination module, configured to determine the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be measured in each time period; A judgment module, configured to judge whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period to obtain a first judgment result, and judge whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period to obtain a second judgment result; A same execution module, configured to, if the first judgment result is the same, determine a first change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a second change amount vector according to the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period. If the second judgment result is the same, determine a third change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a fourth change amount vector according to the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1; A first return execution module, configured to, if j is less than the total number of time periods, set j = j + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; A second return execution module, configured to, if j is equal to the total number of time periods and i is less than the total number of time periods, set i = i + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; A diagnosis module, configured to, if i is equal to the total number of time periods, diagnose whether the mechanical state of the transformer to be measured has changed according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors.

[0018] To achieve the above object, in a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to execute the method according to any one of the first aspect.

[0019] To achieve the above object, in a fifth aspect, the present invention provides a computer device including a memory and a processor, where the memory stores a computer program, which, when executed by the processor, causes the processor to execute the method according to any one of the first aspect.

[0020] Adopting the embodiment of the present invention has the following beneficial effects: The above method determines the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be measured in each time period, and determines whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period to obtain a first judgment result, and determines whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period to obtain a second judgment result. If the first judgment result is the same, a first change amount vector is determined according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and a second change amount vector is determined according to the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period. If the second judgment result is the same, a third change amount vector is determined according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and a fourth change amount vector is determined according to the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1. If j is less than the total number of time periods, then let j = j + 1, and return to execute the step of determining whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period. If j is equal to the total number of time periods and i is less than the total number of time periods, then let i = i + 1, and return to execute the step of determining whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period. If i is equal to the total number of time periods, then according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors, it is diagnosed whether the mechanical state of the transformer to be measured has changed; that is, by comprehensively analyzing the frequency-domain amplitude vectors of the vibration signal, the current signal, and the voltage signal to obtain the first change amount vector, the second change amount vector, the third change amount vector, and the fourth change amount vector, the key characteristic information reflecting the change of the mechanical state of the transformer can be accurately obtained, effectively overcoming the problem of low accuracy of the existing vibration-based diagnosis method. This method can quickly and accurately diagnose the mechanical state of the transformer, is suitable for rapid and accurate judgment on-site, greatly improves the efficiency and accuracy of the mechanical state diagnosis of the transformer, and provides strong technical support for ensuring the safe and stable operation of the power system. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0022] Wherein: Figure 1 It is a schematic diagram of a method for diagnosing the mechanical state of a transformer in an embodiment of the present application; Figure 2 It is a schematic diagram of a device for diagnosing the mechanical state of a transformer in an embodiment of the present application; Figure 3 It is an internal structure diagram of a computer device in some embodiments. Detailed implementation manners

[0023] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts fall within the protection scope of the present invention.

[0024] In the power system, as a core device, the stability of the mechanical state of the transformer plays a decisive role in the safe and reliable operation of the power grid. Accurately and timely diagnosing the mechanical state of the transformer can detect potential faults in advance, avoid equipment damage and power outage accidents, and is of great significance for ensuring the stable operation of the power system.

[0025] Traditional methods for diagnosing the mechanical state of transformers, such as oil chromatography analysis and partial discharge detection, etc., have a certain degree of accuracy in transformer state assessment. However, these methods have obvious limitations. Oil chromatography analysis requires regular sampling and testing of transformer oil, with a long detection cycle and cannot reflect the operating state of the transformer in real time; partial discharge detection usually requires professional equipment and complex operations, with a high detection cost, and some detection methods require the transformer to be powered off, which not only affects the normal power supply of the power grid but also increases the difficulty and cost of detection. Therefore, traditional methods are difficult to meet the requirements of on-site rapid diagnosis and are restricted in practical applications.

[0026] In recent years, the technology for diagnosing the mechanical state of transformers based on vibration has gradually emerged. By collecting and analyzing the vibration signals generated during the operation of the transformer, this technology can effectively reflect the changes in its internal mechanical state and electrical state. Compared with traditional diagnostic methods, the vibration-based diagnostic technology has significant advantages such as non-invasive, real-time online, and low cost. It does not require the transformer to be powered off and does not interfere with the normal operation of the transformer, and can obtain the operating state information of the transformer in real time, providing a new way for the state monitoring and fault diagnosis of the transformer.

[0027] Although the vibration-based mechanical condition diagnosis technology for transformers has many advantages, there are still some problems in its practical application at present. When dealing with vibration signals, current signals, and voltage signals, the existing vibration-based diagnosis methods lack effective comprehensive analysis means, making it difficult to accurately extract the key feature information reflecting the mechanical condition changes of transformers. As a result, the accuracy and reliability of the diagnosis results are not high, and it cannot meet the requirements of quickly and accurately diagnosing the mechanical condition of transformers on-site.

[0028] To address the above problems, this application proposes a transformer mechanical condition diagnosis method and system, which can accurately reflect the key feature information of the mechanical condition changes of transformers, effectively overcoming the problem of low accuracy of the existing vibration-based diagnosis methods. This method can quickly and accurately diagnose the mechanical condition of transformers, is applicable to on-site rapid and accurate judgment, greatly improves the efficiency and accuracy of transformer mechanical condition diagnosis, and provides strong technical support for ensuring the safe and stable operation of the power system. The specific implementation principle will be described in detail in the following embodiments.

[0029] This application provides a transformer mechanical condition diagnosis method in the first aspect.

[0030] Please refer to Figure 1 , which is a schematic diagram of a transformer mechanical condition diagnosis method in an embodiment of this application. The method includes: Step 110: Determine the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be measured in each time period.

[0031] Among them, the transformer to be measured refers to the transformer that needs to perform on-line mechanical condition diagnosis.

[0032] It should be noted that since there is a correlation between the mechanical condition changes (such as winding deformation, core loosening, etc.) of the transformer to be measured and the vibration signal, current signal, and voltage signal, therefore, this application uses the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal to diagnose the mechanical condition.

[0033] It can be understood that for the mechanical condition of the core of the transformer to be measured, its vibration signal is proportional to the square of the voltage signal, and for the mechanical condition of the winding of the transformer to be measured, its vibration signal is proportional to the square of the current signal.

[0034] In some embodiments, a sensor can be mounted on the tank wall of the transformer under test, and then the vibration sensor is used to collect the vibration signal of the transformer under test. Finally, the vibration signal is converted into a frequency-domain vibration amplitude vector. Similarly, the current signal and voltage signal of the transformer under test can be collected by a current transformer and a voltage transformer respectively, and are respectively converted to obtain a frequency-domain current amplitude vector and a frequency-domain voltage amplitude vector.

[0035] Step 120: Determine whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period to obtain a first judgment result, and determine whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period to obtain a second judgment result.

[0036] Step 130: If the first judgment result is the same, determine a first change vector based on the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a second change vector based on the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period. If the second judgment result is the same, determine a third change vector based on the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a fourth change vector based on the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1.

[0037] Regarding the determination method of the change vector, in some embodiments, the difference between the corresponding elements of the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period can be used as the first change vector, and the difference between the corresponding elements of the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period can be used as the second change vector. Similarly, the difference between the corresponding elements of the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period can be used as the third change vector, and the difference between the corresponding elements of the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period can be used as the fourth change vector.

[0038] Step 140: If j is less than the total number of time periods, let j = j + 1, and return to execute the step of determining whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period.

[0039] It should be noted that for the first judgment result and the second judgment result, if there are different situations, the same situations in step 130 do not need to be executed, and step 140 can be directly executed; for example, if the first judgment result is different, the situations where the first judgment result is the same do not need to be executed, and if the second judgment result is different, the situations where the second judgment result is the same do not need to be executed, and step 140 can be directly executed.

[0040] Step 150: If j is equal to the total number of time periods and i is less than the total number of time periods, then let i = i + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector of the i-th time period is the same as the frequency-domain current amplitude vector of the j-th time period.

[0041] Wherein, the total number of time periods is the total number of time periods in each time period in step 110.

[0042] Step 160: If i is equal to the total number of time periods, then diagnose whether the mechanical state of the transformer under test has changed according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors and all the fourth change amount vectors.

[0043] In some embodiments, it is possible to diagnose whether the mechanical state of the transformer under test has changed according to the comparison results of all the first change amount vectors, all the second change amount vectors, all the third change amount vectors and all the fourth change amount vectors with the corresponding preset change amount vectors; in other embodiments, it is also possible to obtain the corresponding preset change amount vectors according to all the second change amount vectors and all the fourth change amount vectors, and then diagnose whether the mechanical state of the transformer under test has changed according to the comparison results between all the first change amount vectors and all the third change amount vectors and the corresponding preset change amount vectors; wherein, the corresponding preset change amount vectors can be the change amount vectors obtained before the mechanical state of the transformer has not changed.

[0044] It should be particularly noted that in addition to being able to evaluate whether the mechanical state of the winding and the mechanical state or position of the iron core have changed, this method of the present application can also evaluate whether the mechanical state or position of other mechanical components in the transformer under test has changed; for example, the pads, clamping parts, fasteners, etc. of the transformer under test.

[0045] In the embodiment of the present application, by comprehensively analyzing the frequency-domain amplitude vectors of vibration signals, current signals, and voltage signals to obtain the first change quantity vector, the second change quantity vector, the third change quantity vector, and the fourth change quantity vector, the key characteristic information reflecting the change of the mechanical state of the transformer can be accurately obtained, effectively overcoming the problem of low accuracy of the existing vibration-based diagnosis method. This method can quickly and accurately diagnose the mechanical state of the transformer, is suitable for rapid and accurate judgment on-site, greatly improves the efficiency and accuracy of the mechanical state diagnosis of the transformer, and provides strong technical support for ensuring the safe and stable operation of the power system.

[0046] In addition, the transformer mechanical state diagnosis method proposed in this application, in addition to being able to accurately reflect the key feature information of the transformer mechanical state change, effectively overcome the problem of low accuracy of the existing vibration-based diagnosis method, quickly and accurately diagnose the transformer mechanical state, be applicable to on-site rapid and accurate judgment, improve the efficiency and accuracy of the transformer mechanical state diagnosis, and provide strong technical support for ensuring the safe and stable operation of the power system, etc., also has the following advantages: Precise maintenance plan formulation: Since this method can quickly and accurately diagnose the transformer mechanical state, power operation and maintenance personnel can formulate a more precise maintenance plan according to the diagnosis results. For example, if it is diagnosed that there are early wear signs in some mechanical components of the transformer (such as pads, clamping parts), but it has not reached the serious fault level, targeted maintenance can be arranged in advance, such as replacing the worn pads, tightening the clamping parts, etc., to avoid the further deterioration of the fault, reduce the unplanned power outage time, and improve the reliability of the power grid operation; Rational allocation of maintenance resources: By accurately evaluating the transformer mechanical state, it can be clear which transformers need to be maintained first and which can appropriately extend the maintenance cycle. This helps to rationally allocate maintenance resources, avoid unnecessary maintenance of transformers in good condition, reduce the maintenance cost, and at the same time ensure that transformers with potential problems are handled in a timely manner; Reducing the degree of equipment damage: Discovering the change of the transformer mechanical state in advance can take measures in the early stage of the fault to avoid the further development of the fault resulting in serious damage to the equipment. For example, when the mechanical state of the winding is detected to be abnormal, taking timely measures can prevent the further deformation of the winding, reduce the maintenance difficulty and cost, and extend the service life of the transformer; Reducing power outage losses: Quick and accurate diagnosis helps to arrange transformer maintenance or replacement in a timely manner, reducing the power outage time and scope caused by transformer faults, which is crucial for industrial production, commercial activities and residents' lives, and can avoid economic losses and social impacts caused by power outages; Data accumulation and analysis: A large amount of transformer mechanical state data will be accumulated during the implementation of this method. These data can provide a basis for the intelligent analysis of the power grid. By deeply mining these data, the change rules and influencing factors of the transformer mechanical state can be understood, providing a more scientific basis for the design, manufacture and operation of the transformer; Integration with other systems: This diagnosis method can be integrated with other monitoring and control systems of the power grid (such as SCADA system, on-line monitoring system, etc.) to realize data sharing and interaction, which helps to build a more intelligent power grid operation management system and improve the overall operation efficiency and reliability of the power grid; Promoting technological innovation: This method comprehensively analyzes vibration signals, current signals and voltage signals, providing new ideas and methods for transformer mechanical state diagnosis, which will prompt more researchers and enterprises to invest in the research in this field and promote the continuous innovation and development of transformer diagnosis technology;Improve the diagnostic criteria: With the wide application and practical verification of this method, a large number of diagnostic cases and data can be accumulated, providing a basis for formulating more scientific and perfect diagnostic criteria for the mechanical state of transformers, which helps to improve the accuracy and consistency of the mechanical state diagnosis of transformers in the whole industry.

[0047] In a feasible implementation manner, in step 160 of the above embodiment, according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors, diagnose whether the mechanical state of the transformer under test has changed, including: input all the second change amount vectors and all the fourth change amount vectors into a preset transfer parameter model to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors; according to all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors, diagnose whether the mechanical state of the transformer under test has changed.

[0048] Herein, the preset transfer parameter model refers to a machine learning model that has been trained and can be directly used to predict and output the first predicted change amount vector and the second predicted change amount vector according to the input second change amount vector and fourth change amount vector.

[0049] It should be noted that the preset transfer parameter model of the present application can be used to reflect the transfer parameter relationship between the vibration change amount and the current change amount and the voltage change amount.

[0050] Furthermore, it should be noted that the number of the second change amount vectors, the first predicted change amount vectors, and the first change amount vectors is equal, and the number of the fourth change amount vectors, the second predicted change amount vectors, and the third change amount vectors is also equal.

[0051] For the training method of the preset transfer parameter model, in some embodiments, a large number of first change amount vectors, second change amount vectors, third change amount vectors, and fourth change amount vectors can be obtained, and then all the first change amount vectors, second change amount vectors, third change amount vectors, and fourth change amount vectors are input into an initial machine learning model for training. After training to a certain extent, the trained preset transfer parameter model can be obtained; among them, the first change amount vector and the third change amount vector can be used as the true values of the initial machine learning model, that is, by comparing the true values with the first predicted change amount vector and the second predicted change amount vector output during the training process one by one, it can be determined whether the initial machine learning model has been trained well and meets the expected requirements.

[0052] In the embodiments of the present application, by introducing a preset transfer parameter model, the first and second predicted change amount vectors are predicted using the second and fourth change amount vectors, thereby diagnosing the mechanical state of the transformer and improving the intelligence and accuracy of the diagnosis.

[0053] It can be understood that the improvement in intelligent diagnosis is as follows: Through the preset transfer parameter model, the second change amount vector and the fourth change amount vector are used as inputs, and the first predicted change amount vector and the second predicted change amount vector are automatically output. This method avoids the complex manual analysis and judgment in traditional methods, realizes the intelligence of the diagnosis process, and greatly improves the diagnosis efficiency. The improvement in accuracy is as follows: This model can reflect the transfer parameter relationship between the vibration change amount and the current change amount and the voltage change amount. Using this relationship for prediction makes the predicted change amount vector closer to the actual situation. During the diagnosis process, by comparing the first change amount vector with the first predicted change amount vector and the third change amount vector with the second predicted change amount vector, the change in the mechanical state of the transformer can be more accurately detected, effectively improving the accuracy of the diagnosis. The in-depth mining of data relationships is as follows: The training process of the preset transfer parameter model is actually an in-depth mining of the relationships among a large number of first change amount vectors, second change amount vectors, third change amount vectors, and fourth change amount vectors. Through this mining, the model can learn the potential laws behind the data, so that in actual diagnosis, the corresponding predicted change amount vectors can be more accurately predicted based on the input change amount vectors, providing strong support for accurately diagnosing the mechanical state of the transformer. The enhancement of adaptability and flexibility is as follows: Once the preset transfer parameter model is trained, it can be directly applied to the mechanical state diagnosis of different transformers. Regardless of the model and specifications of the transformer, as long as the corresponding second change amount vector and fourth change amount vector can be obtained, prediction and diagnosis can be performed through this model. This enhances the adaptability and flexibility of the diagnosis method, enabling it to be widely applied to the mechanical state diagnosis of various transformers.

[0054] In a feasible implementation manner, the preset transfer parameter model in the above embodiments includes a first transfer parameter model between the vibration change amount and the voltage change amount and a second transfer parameter model between the vibration change amount and the current change amount.

[0055] Inputting all the second change amount vectors and all the fourth change amount vectors into the preset transfer parameter model in the above embodiments to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors includes: sequentially inputting all the second change amount vectors into the first transfer parameter model to obtain a plurality of first predicted change amount vectors; sequentially inputting all the fourth change amount vectors into the second transfer parameter model to obtain a plurality of second predicted change amount vectors.

[0056] Among them, the first transfer parameter model here refers to a machine learning model that has been trained and can be directly used to predict and output the first predicted change vector based on the input second change vector; the second transfer parameter model here refers to a machine learning model that has been trained and can be directly used to predict and output the second predicted change vector based on the input fourth change vector.

[0057] It should be noted that the first transfer parameter model of the present application can be used to reflect the transfer parameter relationship between the vibration change and the voltage change; the second transfer parameter model of the present application can be used to reflect the transfer parameter relationship between the vibration change and the current change.

[0058] For the training methods of the first transfer parameter model and the second transfer parameter model, they are similar to the training method of the preset transfer parameter model. The relevant content of the above-mentioned preset transfer parameter model training method can be referred to, and will not be elaborated here.

[0059] In the embodiments of the present application, by adopting a dual-model architecture that respectively reflects the transfer parameter relationships between vibration and voltage, and vibration and current, the accuracy and intelligent level of transformer mechanical state diagnosis are further improved.

[0060] It can be understood that the precise diagnosis is refined: the first transfer parameter model focuses on the relationship between the vibration change amount and the voltage change amount, and the second transfer parameter model focuses on the relationship between the vibration change amount and the current change amount. This subdivision enables the model to capture the internal connections between different physical quantities more precisely. During diagnosis, by comparing the predicted change amount vector output by each model with the actual change amount vector respectively, the subtle changes in the mechanical state of the transformer can be detected more sensitively, greatly improving the accuracy of diagnosis; the degree of intelligence is deepened: under the dual-model architecture, the second change amount vector is input into the first transfer parameter model to obtain the first predicted change amount vector, and the fourth change amount vector is input into the second transfer parameter model to obtain the second predicted change amount vector. The whole process is automatically completed without complex manual analysis and judgment. This intelligent processing method not only improves the diagnosis efficiency but also reduces the errors caused by human factors, making the diagnosis process more scientific and reliable; the data relationship mining is more precise: the two models are trained separately, and in-depth mining is carried out for the respective corresponding data relationships. The first transfer parameter model mines the potential laws behind the vibration and voltage data, and the second transfer parameter model mines the potential laws behind the vibration and current data. This enables the model to more accurately predict the corresponding predicted change amount vector according to the input change amount vector during actual diagnosis, providing more powerful support for accurately diagnosing the mechanical state of the transformer; the adaptability and flexibility are expanded: the dual-model architecture enhances the adaptability and flexibility of the diagnosis method. For transformers of different models and specifications, as long as the corresponding second change amount vector and fourth change amount vector can be obtained, they can be respectively input into the corresponding models for prediction and diagnosis. This flexibility enables this method to be widely applied to the mechanical state diagnosis of various transformers without being restricted by the individual differences of transformers.

[0061] In a feasible implementation manner, diagnosing whether the mechanical state of the transformer under test has changed according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, and all the third change amount vectors and the corresponding multiple second predicted change amount vectors in the above embodiments includes: diagnosing whether the iron core mechanical state of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector; diagnosing whether the winding mechanical state of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector.

[0062] It should be noted that since the vibration signal of the iron core mechanical state of the transformer under test is proportional to the square of the voltage signal, the transfer parameter relationship between the vibration change amount and the voltage change amount can be used to diagnose the iron core mechanical state of the transformer under test; since the vibration signal of the winding mechanical state of the transformer under test is proportional to the square of the current signal, the transfer parameter relationship between the vibration change amount and the current change amount can be used to diagnose the winding mechanical state of the transformer under test.

[0063] In the embodiments of the present application, by calculating the difference rates respectively, it is possible to accurately and separately diagnose whether the mechanical states of the iron core and the winding of the transformer under test have changed, providing a strong basis for the targeted maintenance of the transformer.

[0064] It can be understood that for accurately diagnosing the mechanical state of the iron core: Since there is a specific relationship between the mechanical state of the iron core of the transformer under test and the vibration signal and the voltage signal, that is, the vibration signal is proportional to the square of the voltage signal, so by using the transfer parameter relationship between the vibration change amount and the voltage change amount, by calculating the difference rate between each first change amount vector and the corresponding first predicted change amount vector, it is possible to accurately diagnose whether the mechanical state of the iron core of the transformer under test has changed. This diagnostic method based on a specific physical relationship makes the judgment of the mechanical state of the iron core more accurate and reliable, helping to detect potential problems of the iron core in a timely manner; for accurately diagnosing the mechanical state of the winding: For the mechanical state of the winding of the transformer under test, there is a similar relationship between it and the vibration signal and the current signal, and the vibration signal is proportional to the square of the current signal. Therefore, by means of the transfer parameter relationship between the vibration change amount and the current change amount, by calculating the difference rate between each third change amount vector and the corresponding second predicted change amount vector, it is possible to accurately diagnose whether the mechanical state of the winding of the transformer under test has changed. This targeted diagnostic method can accurately capture the subtle changes in the mechanical state of the winding, providing timely and effective information for the maintenance and repair of the winding; support for targeted maintenance: By accurately diagnosing the mechanical states of the iron core and the winding respectively, power operation and maintenance personnel can formulate a more targeted maintenance plan according to the diagnostic results. For example, if it is diagnosed that the mechanical state of the iron core is abnormal, further inspections and maintenance can be carried out on the iron core. If there are problems with the mechanical state of the winding, corresponding measures can be taken for the winding in a timely manner. This targeted maintenance method avoids blind maintenance, improves the maintenance efficiency, reduces the maintenance cost, and at the same time helps to extend the service life of the transformer and ensure the safe and stable operation of the power system.

[0065] In a feasible implementation manner, diagnosing whether the mechanical state of the iron core of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector in the above embodiment includes: determining the total sum of the first difference rates between each element in each first change amount vector and each element in the corresponding first predicted change amount vector, and the first difference rate between each element in each first change amount vector and the corresponding element in the corresponding first predicted change amount vector; among all the total sums of the first difference rates and all the first difference rates, if there is a total sum of the first difference rates greater than the first preset percentage, or there is a first difference rate greater than the second preset percentage, it is diagnosed that the mechanical state of the iron core of the transformer under test has changed, otherwise, it is diagnosed that the mechanical state of the iron core of the transformer under test has not changed.

[0066] Among them, both the first preset percentage and the second preset percentage can be obtained and preset in advance by the operator based on a large amount of experience, experiments or statistics. Of course, they can also be set by the operator according to actual needs.

[0067] In some embodiments, the present application may set the first preset percentage to 10% and the second preset percentage to 5%.

[0068] For the total sum of the first difference rates, in some embodiments, in the manner of determining the first difference rate, the formula can be used to determine the total sum of the first difference rates and the first difference rate; where is the total sum of the first difference rates between each element in the d-th first change amount vector and each element in the d-th first predicted change amount vector, is the total number of elements in the change amount vector, is the first difference rate between the m-th element in the d-th first change amount vector and the m-th element in the d-th first predicted change amount vector, is the m-th element in the d-th first change amount vector, is the m-th element in the d-th first predicted change amount vector, is the reference value, and the reference value can be or .

[0069] In the embodiments of the present application, by setting the difference rate threshold, the mechanical state of the iron core is accurately diagnosed, providing a reliable basis for targeted maintenance and ensuring the stable operation of the transformer.

[0070] It can be understood that accurately judging the core state: By determining the total first difference rate between each first change amount vector and the corresponding first predicted change amount vector, as well as the first difference rate of each element, and setting the first preset percentage and the second preset percentage as judgment thresholds, it is possible to accurately judge whether the mechanical state of the transformer under test has changed. This judgment method based on the specific numerical difference rate avoids fuzzy judgment and makes the diagnostic result more accurate and reliable; Targeted maintenance support: Once it is diagnosed that the mechanical state of the core has changed, the power operation and maintenance personnel can quickly conduct further inspections and maintenance on the core. This targeted maintenance method avoids blindly maintaining the entire transformer, improves the maintenance efficiency, reduces the maintenance cost, and also helps to timely discover potential problems of the core, prevent the problems from deteriorating further, and extend the service life of the transformer; Adapt to different situations: By setting different preset percentage thresholds, it is possible to adapt to the diagnostic requirements of the mechanical state of the core under different transformers and different operating environments. Whether it is a slight state change or a more serious fault indication, it can be accurately judged by this method, providing a strong guarantee for the stable operation of the transformer.

[0071] In a feasible implementation manner, diagnosing whether the winding mechanical state of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector in the above embodiment includes: determining the total second difference rate between each element in each third change amount vector and each element in the corresponding second predicted change amount vector, and the second difference rate between each element in each third change amount vector and the corresponding element in the corresponding second predicted change amount vector; among all the total second difference rates and all the second difference rates, if there is a total first difference rate with a difference rate greater than the third preset percentage, or a first difference rate with a difference rate greater than the first preset percentage, it is diagnosed that the winding mechanical state of the transformer under test has changed, otherwise, it is diagnosed that the winding mechanical state of the transformer under test has not changed.

[0072] Among them, the third preset percentage can be set in advance by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set by the operator according to actual needs.

[0073] In some embodiments, the present application can set the third preset percentage to 20%.

[0074] For the total second difference rate, the determination method of the second difference rate is similar to the determination method of the total first difference rate. For the relevant content of the determination method of the total second difference rate with the second difference rate, reference can be made to the above, and it will not be elaborated here.

[0075] In the embodiments of the present application, by setting a difference rate threshold, the mechanical state of the winding is accurately diagnosed, providing a reliable basis for targeted maintenance and ensuring the stable operation of the transformer.

[0076] It can be understood that accurately judging the winding state: by determining the total second difference rate between each third change amount vector and the corresponding second predicted change amount vector, as well as the second difference rate of each element, and setting the third preset percentage and the first preset percentage as judgment thresholds, it is possible to accurately judge whether the mechanical state of the winding of the transformer to be tested has changed. This judgment method based on the specific numerical difference rate avoids fuzzy judgment and makes the diagnostic result more accurate and reliable; Targeted maintenance support: Once it is diagnosed that the mechanical state of the winding has changed, the power operation and maintenance personnel can quickly conduct further inspections and maintenance on the winding. This targeted maintenance method avoids blindly maintaining the entire transformer, improves the maintenance efficiency, reduces the maintenance cost, and also helps to timely discover potential problems of the winding, prevent the problems from deteriorating further, and extend the service life of the transformer; Adapt to different situations: By setting different preset percentage thresholds, it is possible to adapt to the diagnostic requirements of the mechanical state of the winding under different transformers and different operating environments. Whether it is a slight state change or a more serious fault indication, it can be accurately judged by this method, providing a strong guarantee for the stable operation of the transformer.

[0077] In a feasible implementation manner, step 110 in the above embodiment, determining the frequency-domain vibration amplitude vector of the vibration signal of the transformer to be tested in each time period, includes: obtaining the sensing signals of all vibration sensors, where all vibration sensors are uniformly installed on the oil tank of the transformer to be tested; dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals of each time period, where the initial value of n is 1; performing time-frequency domain conversion on the vibration signal of each time period to obtain the frequency-domain vibration amplitude vector of each time period.

[0078] Diagnosing whether the mechanical state of the transformer to be tested has changed according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, as well as all the third change amount vectors and the corresponding multiple second predicted change amount vectors in the above embodiment, includes: diagnosing whether the mechanical state of the transformer to be tested at the nth vibration sensor has changed according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, as well as all the third change amount vectors and the corresponding multiple second predicted change amount vectors; let n = n + 1, and return to execute the step of dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals of each time period until n is equal to the total number of vibration sensors.

[0079] In some embodiments, the present application generally sets the number of vibration sensors to 6 - 9, that is, the total number of vibration sensors is 6 - 9.

[0080] In the embodiments of the present application, through the layout of multiple vibration sensors and cyclic iterative diagnosis, comprehensive and accurate condition monitoring of the transformer is achieved, providing all-round guarantee for the stable operation of the transformer.

[0081] It can be understood that for comprehensive monitoring of the transformer status: by evenly installing multiple vibration sensors on the oil tank of the transformer to be measured, all key parts of the transformer can be comprehensively covered. This layout method can ensure that vibration signals of the transformer are collected from multiple angles and positions, thus more comprehensively reflecting the mechanical state of the transformer. The cyclic iterative diagnosis method divides the sensing signals of each vibration sensor by time period and performs time-frequency domain conversion to obtain the frequency-domain vibration amplitude vector, and further diagnoses the mechanical state of the transformer at different positions through differential rate analysis, achieving comprehensive monitoring of the transformer status; for accurate diagnosis of the status at different positions: the vibration signals collected by each vibration sensor represent the mechanical state of a specific position of the transformer. By analyzing and diagnosing the signals collected by each vibration sensor respectively, it can be accurately judged whether the mechanical state of the transformer at different positions has changed. This ability to accurately diagnose the status at different positions helps to timely discover potential problems in each part of the transformer, providing a strong basis for targeted maintenance; for improving the reliability of diagnosis: due to the adoption of the layout of multiple vibration sensors and the cyclic iterative diagnosis method, the transformer status can be monitored and diagnosed from multiple angles and positions. This method can mutually verify the diagnosis results at different positions, improving the reliability of diagnosis. Even if the signal of a certain vibration sensor is interfered or abnormal, it can be compensated and verified by the signals of other sensors to ensure the accuracy of the diagnosis results; for meeting the requirements of large transformers: for relatively large transformers with complex structures, the changes in mechanical states may involve multiple parts. Through the layout of multiple vibration sensors and the cyclic iterative diagnosis method, the requirements of such complex structures can be met, and comprehensive and accurate monitoring and diagnosis of the transformer can be carried out. This method helps to timely discover potential problems in each part of the large transformer, preventing damage or power outage accidents of the entire transformer caused by local failures; for optimizing the maintenance strategy: based on the comprehensive and accurate diagnosis results, power operation and maintenance personnel can formulate more optimized maintenance strategies. For example, for the parts diagnosed with potential problems, maintenance and inspection can be prioritized, while for the parts in good condition, the maintenance cycle can be appropriately extended. This optimized maintenance strategy helps to reasonably allocate maintenance resources, improve maintenance efficiency, reduce maintenance costs, and ensure the stable operation of the transformer at the same time.

[0082] In a feasible implementation manner, step 110 in the above embodiment, which determines the frequency-domain current amplitude vectors of the current signals and the frequency-domain voltage amplitude vectors of the voltage signals of the transformer under test in each time period, includes: obtaining the mutual inductance current signal of the current transformer and the mutual inductance voltage signal of the voltage transformer, where the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer under test; dividing the mutual inductance current signal into time periods to obtain the current signals in each time period, and dividing the mutual inductance voltage signal into time periods to obtain the voltage signals in each time period; performing time-frequency domain conversion on the current signal in each time period to obtain the frequency-domain current amplitude vectors in each time period, and performing time-frequency domain conversion on the time-domain voltage signal in each time period to obtain the frequency-domain voltage amplitude vectors in each time period.

[0083] In the embodiments of the present application, current and voltage transformers are installed on the high-voltage side busbar to obtain signals, realizing comprehensive and accurate current and voltage monitoring, and further improving the accuracy and reliability of transformer mechanical state diagnosis.

[0084] It can be understood that comprehensive current and voltage monitoring: Installing current transformers and voltage transformers on the high-voltage side busbar of the transformer under test can accurately obtain the current and voltage signals of the transformer. This layout ensures the comprehensiveness and accuracy of the current and voltage signals, providing a solid foundation for subsequent signal analysis and state diagnosis. By dividing the mutual inductance current signal and the mutual inductance voltage signal into time periods and performing time-frequency domain conversion, the frequency-domain current amplitude vectors and frequency-domain voltage amplitude vectors in each time period can be obtained, providing comprehensive current and voltage data support for the mechanical state diagnosis of the transformer; improving diagnosis accuracy: Since the current and voltage signals are closely related to the mechanical state changes of the transformer, by accurately obtaining these signals and conducting in-depth analysis, the mechanical state changes of the transformer can be more accurately reflected. In the diagnosis process, using the correlation between these signals and vibration signals, it is possible to more precisely determine whether there are mechanical state abnormalities in the transformer, thereby improving the accuracy of the diagnosis; adapting to complex environments: Installing current transformers and voltage transformers on the high-voltage side busbar can adapt to complex and changing power grid environments. Regardless of how the power grid load changes, the current and voltage signals of the transformer can be accurately obtained, providing stable and reliable data support for the mechanical state diagnosis of the transformer; optimizing the system architecture: Installing current transformers and voltage transformers on the high-voltage side busbar can optimize the architecture of the entire diagnosis system. This layout not only facilitates the installation and maintenance of sensors but also reduces interference and losses during signal transmission, improving the quality and stability of the signals. At the same time, it is also conducive to integration with other monitoring and control systems (such as SCADA systems, online monitoring systems, etc.) to achieve data sharing and interaction and build a more intelligent power grid operation management system.

[0085] In a feasible implementation manner, the method in the above embodiment further includes: when the transformer under test is first put into operation or operates normally, determining the normal frequency-domain vibration amplitude vector of the normal vibration signal, the normal frequency-domain current amplitude vector of the normal current signal, and the normal frequency-domain voltage amplitude vector of the normal voltage signal of the transformer under test in each time period; judging whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period to obtain a first normal judgment result, and judging whether the normal frequency-domain voltage amplitude vector in the x-th time period is the same as the normal frequency-domain voltage amplitude vector in the y-th time period to obtain a second normal judgment result; if the first normal judgment results are the same, determining a first normal change amount vector according to the normal frequency-domain vibration amplitude vector in the x-th time period and the normal frequency-domain vibration amplitude vector in the y-th time period, and determining a second normal change amount vector according to the normal frequency-domain voltage amplitude vector in the x-th time period and the normal frequency-domain voltage amplitude vector in the y-th time period, if the second normal judgment results are the same, determining a third normal change amount vector according to the normal frequency-domain vibration amplitude vector in the x-th time period and the normal frequency-domain vibration amplitude vector in the y-th time period, and determining a fourth normal change amount vector according to the normal frequency-domain current amplitude vector in the x-th time period and the normal frequency-domain current amplitude vector in the y-th time period, the initial value of x is 1, and the initial value of y is 1; if y is less than the total number of time periods, then let y = y + 1, and return to execute the step of judging whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period; if y is equal to the total number of time periods and x is less than the total number of time periods, then let x = x + 1, and return to execute the step of judging whether the normal frequency-domain current amplitude vector in the x-th time period is the same as the normal frequency-domain current amplitude vector in the y-th time period; if x is equal to the total number of time periods, then input all the first normal change amount vectors and all the second normal change amount vectors into the first initial machine learning model for training to obtain a first transfer parameter model, and input all the third normal change amount vectors and all the fourth change amount vectors into the second initial machine learning model for training to obtain a second transfer parameter model.

[0086] In the embodiments of the present application, through model training based on normal data, the accuracy and adaptability of the diagnostic model are improved, providing a more accurate and reliable basis for the mechanical state diagnosis of transformers.

[0087] It is understandable that improving the accuracy of the diagnostic model: when the transformer to be tested is first put into operation or is operating normally, normal vibration signals, current signals, and voltage signals in each time period are collected and converted into corresponding frequency-domain vectors. By comparing whether the frequency-domain vectors in different time periods are the same, the normal change vector is determined. Subsequently, these normal change vectors are input into the initial machine learning model for training to obtain the first transfer parameter model and the second transfer parameter model. This model training method based on normal data can ensure that the model learns the data characteristics under the normal operating state of the transformer, so that in subsequent diagnostic processes, abnormal states can be more accurately identified, improving the accuracy of diagnosis; enhancing model adaptability: since the normal states of different transformers or the same transformer in different operating environments may vary, through model training based on actual operating data, the model can better adapt to these differences. This adaptability not only improves the application effect of the model on different transformers but also enables the model to more accurately reflect the mechanical state changes of the transformer in a specific operating environment; reducing human intervention: Traditional model training methods may require a large amount of expert experience and manual adjustment, while the automatic training method based on normal data greatly reduces human intervention. By automatically collecting and analyzing normal data, the model can automatically learn the laws behind the data, thereby improving the training efficiency and accuracy; optimizing the diagnostic process: Integrating the model training steps into the diagnostic process makes the entire diagnostic process more systematic and automated. Data is collected and the model is trained when the transformer is first put into operation or is operating normally, and then the trained model is directly used for judgment in subsequent diagnostic processes, simplifying the diagnostic process and improving the diagnostic efficiency; enhancing system reliability: Through model training based on normal data, the obtained transfer parameter model can more accurately reflect the change law of the mechanical state of the transformer. In practical applications, these models can more reliably identify potential faults of the transformer, providing strong guarantee for the stable operation of the power system. At the same time, since the model is trained based on actual data, its prediction results are more credible and practical.

[0088] In a second aspect of the present application, a transformer mechanical state diagnostic system is provided. The system includes a plurality of vibration sensors, current transformers, voltage transformers, and a processor (not shown).

[0089] In a feasible implementation manner, the plurality of vibration sensors are evenly installed on the oil tank wall of the transformer to be tested, and the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer to be tested; the processor is configured to execute the method according to any one of the first aspect.

[0090] In the embodiments of the present application, through the integrated diagnostic system architecture, efficient and accurate diagnosis of the transformer mechanical state is achieved, providing strong support for the stable operation of the power system.

[0091] It can be understood that for the integrated system architecture: The transformer mechanical state diagnosis system proposed in this application integrates multiple vibration sensors, current transformers, voltage transformers and processors to form a complete diagnosis system. This integrated system architecture enables the signal acquisition, processing and diagnosis processes to be completed on a unified platform, improving the efficiency and accuracy of diagnosis; Comprehensive signal acquisition: Multiple vibration sensors are evenly installed on the oil tank wall of the transformer to be measured, which can comprehensively cover all key parts of the transformer to ensure that vibration signals of the transformer are collected from multiple angles and positions. At the same time, current transformers and voltage transformers are installed on the busbar on the high-voltage side to accurately obtain the current and voltage signals of the transformer. This comprehensive signal acquisition method provides a rich data basis for subsequent diagnosis; Efficient signal processing: The processor, as the core component of the system, is responsible for executing the diagnosis method in any one of the first aspects. It can quickly and accurately process vibration signals, current signals and voltage signals, extract key feature information reflecting changes in the mechanical state of the transformer. By introducing a preset transfer parameter model, the processor can use the second and fourth change amount vectors to predict the first and second predicted change amount vectors, and then realize the intelligent diagnosis of the mechanical state of the transformer; Accurate diagnosis result: Since the system integrates comprehensive signal acquisition and efficient signal processing functions, it can obtain more accurate diagnosis results. By comparing the difference rate between the actual change amount vector and the predicted change amount vector, it can accurately judge whether the iron core mechanical state and winding mechanical state of the transformer to be measured have changed. This accurate diagnosis result provides a reliable decision-making basis for power operation and maintenance personnel, helping to take targeted maintenance measures in a timely manner to ensure the stable operation of the power system; Strong adaptability: The diagnostic system has good adaptability and can be applied to transformers of different models and specifications. As long as the corresponding vibration signals, current signals and voltage signals can be obtained, diagnosis can be performed through this system. This flexibility enables this method to be widely applied to the mechanical state diagnosis of various transformers without being restricted by the individual differences of transformers; Easy to integrate and expand: The diagnostic system is easy to integrate with other monitoring and control systems (such as SCADA systems, on-line monitoring systems, etc.) to achieve data sharing and interaction. At the same time, the system architecture is also convenient for subsequent expansion and upgrade to adapt to changing diagnostic requirements and technological developments.

[0092] This application provides a transformer mechanical state diagnosis device in the third aspect.

[0093] Please refer to Figure 2 , which is a schematic diagram of a transformer mechanical state diagnosis device in an embodiment of this application. The device 210 includes: A determination module 211, configured to determine the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be measured in each time period; A judgment module 212, configured to judge whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period, to obtain a first judgment result, and to judge whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period, to obtain a second judgment result; A same execution module 213, configured to, if the first judgment result is the same, determine a first change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a second change amount vector according to the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period; if the second judgment result is the same, determine a third change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determine a fourth change amount vector according to the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1; A first return execution module 214, configured to, if j is less than the total number of time periods, set j = j + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; A second return execution module 215, configured to, if j is equal to the total number of time periods and i is less than the total number of time periods, set i = i + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; A diagnosis module 216, configured to, if i is equal to the total number of time periods, diagnose whether the mechanical state of the transformer to be measured has changed according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors.

[0094] In the embodiments of the present application, the relevant content of the above determination module 211, judgment module 212, same execution module 213, first return execution module 214, second return execution module 215, and diagnosis module 216 can be referred to Figure 1 the content in the shown embodiments, and details are not described herein.

[0095] It should be noted that the device 210 of the present application further includes some other modules. It can be understood that there is a one-to-one correspondence between the method of the present application and the device 210. Therefore, some other modules of the device 210 of the present application are the corresponding content of the method of the present application in the above embodiments.

[0096] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to execute a transformer mechanical state diagnosis method in the above method embodiments.

[0097] In a fifth aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to execute a transformer mechanical state diagnosis method in the above method embodiments.

[0098] Figure 3 The internal structure diagram of the computer device in some embodiments is shown. The computer device may specifically be a terminal, a server, or a gateway. As Figure 3 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus.

[0099] Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, which, when executed by the processor, enables the processor to implement each step in the above method embodiments. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute each step in the above method embodiments. Those skilled in the art can understand that Figure 3 the structure shown in

[0100] is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0101] Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0102] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0103] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for diagnosing the mechanical state of a transformer, characterized in that, The method includes: Determining the frequency-domain vibration amplitude vector of the vibration signal, the frequency-domain current amplitude vector of the current signal, and the frequency-domain voltage amplitude vector of the voltage signal of the transformer to be tested in each time period; Judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period to obtain a first judgment result, and judging whether the frequency-domain voltage amplitude vector in the i-th time period is the same as the frequency-domain voltage amplitude vector in the j-th time period to obtain a second judgment result; If the first judgment result is the same, determining a first change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determining a second change amount vector according to the frequency-domain voltage amplitude vector in the i-th time period and the frequency-domain voltage amplitude vector in the j-th time period. If the second judgment result is the same, determining a third change amount vector according to the frequency-domain vibration amplitude vector in the i-th time period and the frequency-domain vibration amplitude vector in the j-th time period, and determining a fourth change amount vector according to the frequency-domain current amplitude vector in the i-th time period and the frequency-domain current amplitude vector in the j-th time period. The initial value of i is 1, and the initial value of j is 1; If j is less than the total number of time periods, let j = j + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; If j is equal to the total number of time periods and i is less than the total number of time periods, let i = i + 1, and return to execute the step of judging whether the frequency-domain current amplitude vector in the i-th time period is the same as the frequency-domain current amplitude vector in the j-th time period; If i is equal to the total number of time periods, diagnosing whether the mechanical state of the transformer to be tested has changed according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors.

2. The transformer mechanical state diagnosis method according to claim 1, wherein The diagnosing whether the mechanical state of the transformer to be tested has changed according to all the first change amount vectors, all the second change amount vectors, all the third change amount vectors, and all the fourth change amount vectors includes: Inputting all the second change amount vectors and all the fourth change amount vectors into a preset transfer parameter model to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors; Diagnosing whether the mechanical state of the transformer to be tested has changed according to all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors.

3. The transformer mechanical state diagnosis method according to claim 2, characterized in that, The preset transfer parameter model includes a first transfer parameter model between the vibration change amount and the voltage change amount and a second transfer parameter model between the vibration change amount and the current change amount. The inputting all the second change amount vectors and all the fourth change amount vectors into a preset transfer parameter model to obtain a plurality of first predicted change amount vectors and a plurality of second predicted change amount vectors includes: Sequentially inputting all the second change amount vectors into the first transfer parameter model to obtain a plurality of first predicted change amount vectors; Input all the fourth change amount vectors into the second transfer parameter model in sequence to obtain a plurality of second predicted change amount vectors.

4. The transformer mechanical state diagnosis method according to claim 2, characterized in that Diagnosing whether the mechanical state of the transformer under test has changed based on all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors, includes: Diagnosing whether the mechanical state of the iron core of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector; Diagnosing whether the mechanical state of the winding of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector.

5. The transformer mechanical state diagnosis method according to claim 4, wherein, The diagnosing whether the mechanical state of the iron core of the transformer under test has changed according to the difference rate between each first change amount vector and the corresponding first predicted change amount vector includes: Determining the total sum of the first difference rates between each element in each first change amount vector and the corresponding element in the corresponding first predicted change amount vector, and the first difference rate between each element in each first change amount vector and the corresponding element in the corresponding first predicted change amount vector; Among all the total sums of the first difference rates and all the first difference rates, if there is a total sum of the first difference rates greater than the first preset percentage, or there is a first difference rate greater than the second preset percentage, then diagnose that the mechanical state of the iron core of the transformer under test has changed; otherwise, diagnose that the mechanical state of the iron core of the transformer under test has not changed.

6. The transformer mechanical state diagnosis method according to claim 4, characterized in that The diagnosing whether the mechanical state of the winding of the transformer under test has changed according to the difference rate between each third change amount vector and the corresponding second predicted change amount vector includes: Determining the total sum of the second difference rates between each element in each third change amount vector and the corresponding element in the corresponding second predicted change amount vector, and the second difference rate between each element in each third change amount vector and the corresponding element in the corresponding second predicted change amount vector; Among all the total sums of the second difference rates and all the second difference rates, if there is a total sum of the first difference rates greater than the third preset percentage, or a first difference rate greater than the first preset percentage, then diagnose that the mechanical state of the winding of the transformer under test has changed; otherwise, diagnose that the mechanical state of the winding of the transformer under test has not changed.

7. The transformer mechanical state diagnosis method according to claim 2, characterized in that, The determining the frequency domain vibration amplitude vector of the vibration signal of the transformer under test in each time period includes: Obtaining the sensing signals of all vibration sensors, where all vibration sensors are uniformly installed on the oil tank of the transformer under test; Dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals in each time period, where the initial value of n is 1; Performing time-frequency domain conversion on the vibration signal in each time period to obtain the frequency domain vibration amplitude vector in each time period; Diagnosing whether the mechanical state of the transformer under test has changed based on all the first change amount vectors and the corresponding plurality of first predicted change amount vectors, and all the third change amount vectors and the corresponding plurality of second predicted change amount vectors, includes: Diagnose whether the mechanical state of the transformer under test has changed at the nth vibration sensor according to all the first change amount vectors and the corresponding multiple first predicted change amount vectors, and all the third change amount vectors and the corresponding multiple second predicted change amount vectors; Let n = n + 1, and return to execute the step of dividing the sensing signal of the nth vibration sensor into time periods to obtain the vibration signals of each time period until n is equal to the total number of vibration sensors.

8. The transformer mechanical state diagnosis method according to claim 1, wherein Determine the frequency-domain current amplitude vector of the current signal and the frequency-domain voltage amplitude vector of the voltage signal of the transformer under test in each time period, including: Obtain the mutual inductance current signal of the current transformer and the mutual inductance voltage signal of the voltage transformer, where the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer under test; Divide the mutual inductance current signal into time periods to obtain the current signals of each time period, and divide the mutual inductance voltage signal into time periods to obtain the voltage signals of each time period; Perform time-frequency domain conversion on the current signal of each time period to obtain the frequency-domain current amplitude vectors of each time period, and perform time-frequency domain conversion on the time-domain voltage signal of each time period to obtain the frequency-domain voltage amplitude vectors of each time period.

9. The transformer mechanical state diagnosis method according to claim 3, characterized in that, The method further includes: Under the condition that the transformer under test is first put into operation or operates normally, determine the normal frequency-domain vibration amplitude vector of the normal vibration signal, the normal frequency-domain current amplitude vector of the normal current signal, and the normal frequency-domain voltage amplitude vector of the normal voltage signal of the transformer under test in each time period; Judge whether the normal frequency-domain current amplitude vector in the xth time period is the same as the normal frequency-domain current amplitude vector in the yth time period to obtain a first normal judgment result, and judge whether the normal frequency-domain voltage amplitude vector in the xth time period is the same as the normal frequency-domain voltage amplitude vector in the yth time period to obtain a second normal judgment result; If the first normal judgment results are the same, determine a first normal change amount vector according to the normal frequency-domain vibration amplitude vector in the xth time period and the normal frequency-domain vibration amplitude vector in the yth time period, and determine a second normal change amount vector according to the normal frequency-domain voltage amplitude vector in the xth time period and the normal frequency-domain voltage amplitude vector in the yth time period. If the second normal judgment results are the same, determine a third normal change amount vector according to the normal frequency-domain vibration amplitude vector in the xth time period and the normal frequency-domain vibration amplitude vector in the yth time period, and determine a fourth normal change amount vector according to the normal frequency-domain current amplitude vector in the xth time period and the normal frequency-domain current amplitude vector in the yth time period. The initial value of x is 1, and the initial value of y is 1; If y is less than the total number of time periods, let y = y + 1, and return to execute the step of judging whether the normal frequency-domain current amplitude vector in the xth time period is the same as the normal frequency-domain current amplitude vector in the yth time period; If y is equal to the total number of the time periods, and x is less than the total number of the time periods, then let x = x + 1, and return to execute the step of determining whether the normal frequency-domain current amplitude vector of the x-th time period is the same as the normal frequency-domain current amplitude vector of the y-th time period; If x is equal to the total number of the time periods, then input all the first normal change amount vectors and all the second normal change amount vectors into the first initial machine learning model for training to obtain the first transfer parameter model, and input all the third normal change amount vectors and all the fourth change amount vectors into the second initial machine learning model for training to obtain the second transfer parameter model.

10. A transformer mechanical state diagnosis system, characterized in that, The system includes a plurality of vibration sensors, a current transformer, a voltage transformer and a processor; The plurality of vibration sensors are uniformly installed on the oil tank wall of the transformer to be measured, and the current transformer and the voltage transformer are installed on the busbar on the high-voltage side of the transformer to be measured; The processor is configured to execute the transformer mechanical state diagnosis method according to any one of claims 1 to 9.

Images