Stability evaluation method and system of on-load tap-changer for extra-high voltage converter transformer

Abstract

The invention provides a stability evaluation method and system of an on-load tap-changer for an extra-high voltage converter transformer, and relates to the technical field of electric power maintenance. Multi-dimensional state parameters, including vibration acceleration, current, voltage, temperature and spring stress, of the on-load tap-changer of the extra-high voltage converter transformer are collected; electrical, thermal and mechanical related state characteristic parameters are extracted, and corresponding electrical stability scores, thermal stability scores and mechanical stability scores are generated. Then, the states are divided into normal, critical and abnormal states by using a deep learning model, and a stability evaluation model is constructed by using a historical stability score and state training model; and the operation state of the on-load tap-changer is evaluated in real time by inputting the current comprehensive stability score.

Description

Technical Field

[0001] The present invention relates to the technical field of power maintenance, and in particular to a stability assessment method and system for an on-load tap changer for an ultra-high voltage converter transformer. Background Art

[0002] UHV converter transformers are core equipment in the power transmission system, and the stability of their operation is directly related to the safety and reliability of the entire power system. As an important part of UHV converter transformers, on-load tap changers undertake the key task of voltage regulation. However, during long-term operation, due to frequent switching operations, on-load tap changers are often subject to the coupling of multiple physical fields such as electrical, thermal and mechanical, resulting in increased contact resistance and fatigue of mechanical components. These problems can cause performance degradation of the equipment, and may even cause fault interruptions, seriously affecting the safe and stable operation of the power grid. At present, the evaluation of the operating status of on-load tap changers mainly relies on the monitoring of a single physical field, such as the measurement of contact resistance or the collection of temperature. There is a lack of comprehensive analysis of the coupling of multiple physical fields, making it difficult to achieve an accurate evaluation of their operating stability. Therefore, there is an urgent need for a stability evaluation method based on multi-physical field coupling analysis, which can monitor and analyze the electrical, thermal and mechanical characteristics of on-load tap changers in real time, thereby providing an accurate evaluation of the operating status.

[0003] In the prior art, publication number CN118710041A discloses a converter transformer risk assessment method and system based on rough quantitative analysis, which qualitatively scores the risk value of the health of the converter transformer to obtain a qualitative assessment score of the converter transformer; then quantitatively evaluates multiple indicators of the converter transformer to obtain a comprehensive health score of the converter transformer; quantitatively quantifies multiple operating risks of the converter transformer, and combines the comprehensive health score to obtain a quantitative assessment score of the converter transformer; finally, the qualitative assessment score and the quantitative assessment score are weighted and summed to evaluate the converter transformer risk.

[0004] The main problems with the above scheme are: it uses qualitative scoring and quantitative analysis of a single indicator to evaluate the health status and operating risks of the converter transformer, without considering the complex coupling effects and dynamic change characteristics of various physical fields during the operation of the converter transformer, and there are certain deficiencies in the accuracy and scientificity of the assessment; it mainly relies on historical data or single monitoring results to quantify and evaluate risks, fails to update data in a timely manner, and the real-time nature of risk assessment is insufficient.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a stability evaluation method and system for an on-load tap changer for an ultra-high voltage converter transformer, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A stability evaluation method for an on-load tap changer for a UHV converter transformer, comprising the following specific steps:

[0009] Step 1: Collect the state parameters of the on-load tap changer in the monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress;

[0010] Step 2: Extract the characteristics of the state parameters within the monitoring period to obtain the state characteristic parameters, which include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring period, the vibration acceleration mean of the on-load tap changer within the monitoring period, and the spring stress change of the spring within the monitoring period;

[0011] Step 3: Based on the state characteristic parameters, an electrical stability score, a thermal stability score, and a mechanical stability score are generated to evaluate the electrical state, the heating state, and the mechanical state of the on-load tap changer respectively, and a comprehensive stability score for comprehensive evaluation of the on-load tap changer is generated by combining the above three scores;

[0012] Step 4: Construct an on-load tap changer stability assessment model based on the deep learning network. Obtain the comprehensive stability score of the on-load tap changer in the monitoring period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment. The state includes normal state, critical state and abnormal state. The comprehensive stability score of the on-load tap changer at the historical moment is used as input, and the state is used as a label to train the on-load tap changer stability assessment model.

[0013] Step 5: Input the comprehensive stability score of the on-load tap changer in the monitoring period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

[0014] Furthermore, data is collected at equal time intervals during the monitoring period, and an acceleration sensor is installed at the contact position of the on-load tap changer for real-time monitoring. The measured acceleration is the overall vibration acceleration of the on-load tap changer; a current sensor is installed at the contact position to collect the contact current; a voltage sensor is used to monitor the voltage at both ends of the contact to generate the contact voltage; an infrared temperature sensor is installed at the contact position to monitor the contact temperature change in real time; and a strain gauge is used to directly measure the spring stress.

[0015] Furthermore, the principle for generating the state characteristic parameters is:

[0016] The formula used to generate the contact resistance change rate is:

[0017]

[0018] Among them, R c (t) represents the contact resistance at time t, V z (t) represents the contact voltage at time t, I z (t) represents the contact current at time t, t represents the index of the acquisition time in the monitoring period, and t∈[1,S], S represents the total number of acquisition times, ΔR c Represents the contact resistance change rate, R c (t-1) represents the contact resistance at time t-1;

[0019] The formula for generating the current fluctuation is:

[0020] ΔI z =max I z (t)-minI z (t)

[0021] Among them, ΔI z Indicates current fluctuation, max I z (t) represents the maximum contact current collected during the monitoring period, minI z (t) represents the minimum contact current collected during the monitoring period;

[0022] The heat source power is generated according to the formula:

[0023]

[0024] Where Q represents the heat source power;

[0025] The formula used to generate the rate of temperature rise is:

[0026]

[0027] Where W represents the temperature rise rate, T(t) represents the contact temperature at time t, T(t-1) represents the contact temperature at time t-1, and ΔT(t) represents the time difference between collecting T(t) and T(t-1);

[0028] The formula for generating the mean value of the vibration acceleration of the on-load tap-changer is:

[0029]

[0030] Where A represents the average value of the vibration acceleration of the on-load tap changer, a t represents the vibration acceleration of the on-load tapchanger collected at time t;

[0031] The formula for generating the spring stress variation is:

[0032]

[0033] Among them, Δσ 弹簧 represents the change in spring stress, σ 弹簧 (t) represents the spring stress collected at time t, σ 弹簧 (t-1) represents the spring stress collected at time t-1.

[0034] Further, the formula used to generate the electrical stability score is:

[0035] S1=max(0,100-k1·ΔR c -k2·ΔI z )

[0036] Wherein, S1 represents the electrical stability score, k1 and k2 represent the weight coefficients of the contact resistance change rate and the current fluctuation, respectively, and k1+k2=1, k1=k2;

[0037] The formula used to generate the thermal stability score is:

[0038] S2=max(0,100-k3·W-k4·Q)

[0039] Among them, S2 represents the thermal stability score, k3 and k4 represent the weight coefficients of the temperature rise rate and the heat source power respectively, k3+k3=1, and k3<k4;

[0040] The formula used to generate the Mechanical Stability Score is:

[0041] S3=max(0,100-k5·A-k6·Δσ 弹簧 )

[0042] Among them, S3 represents the mechanical stability score, k5 and k6 represent the weight coefficients of the vibration acceleration mean and the spring stress change respectively, k5+k6=1, and k5<k6.

[0043] Furthermore, the formula for generating the comprehensive stability score is:

[0044] X=w1·S1+w2·S2+w3·S3

[0045] Wherein, X represents the comprehensive stability score, w1, w2, and w3 represent the weight coefficients of the electrical stability score, the thermal stability score, and the mechanical stability score, respectively, and w1+w2+w3=1.

[0046] The present invention also provides a stability evaluation system for an on-load tap changer for an ultra-high voltage converter transformer, the system being used to implement the stability evaluation method for an on-load tap changer for an ultra-high voltage converter transformer, specifically comprising:

[0047] A data acquisition module is used to collect state parameters of the on-load tap changer in a monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress;

[0048] A feature extraction module is used to extract features of state parameters within the monitoring time period to obtain state feature parameters, wherein the state feature parameters include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring time period, the vibration acceleration mean value of the on-load tap changer within the monitoring time period, and the spring stress change amount of the spring within the monitoring time period;

[0049] A characteristic scoring module is used to generate an electrical stability score, a thermal stability score, and a mechanical stability score for respectively evaluating the electrical state, the heating state, and the mechanical state of the on-load tap changer based on the state characteristic parameters, and to generate a comprehensive stability score for comprehensively evaluating the on-load tap changer by combining the above three scores;

[0050] A model training module is used to build an on-load tap changer stability assessment model based on a deep learning network, obtain the comprehensive stability score of the on-load tap changer in the monitoring time period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment, the state includes a normal state, a critical state and an abnormal state, and use the comprehensive stability score of the on-load tap changer at the historical moment as input and the state as a label to train the on-load tap changer stability assessment model;

[0051] The evaluation and judgment module is used to input the comprehensive stability score of the on-load tap changer in the monitoring time period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention collects dynamic data in the monitoring time period before the current moment, including multi-dimensional state parameters such as vibration acceleration, contact current, contact voltage, contact temperature and spring stress, comprehensively covering the three major influencing factors of electricity, heat and mechanics, and can more accurately reflect the operating status of the on-load tap changer, and avoid the one-sidedness and lag that may be caused by relying solely on data at a single time point; features covering the three dimensions of electricity, heat and mechanics are extracted from the monitoring data. Through the diversity of characteristic parameters, multi-angle analysis of the cause of the fault can be achieved, thereby improving the accuracy of the evaluation.

[0054] The present invention also generates electrical stability scores, thermal stability scores and mechanical stability scores respectively, making each score more targeted and facilitating the identification of potential faults or weak links in specific areas. This field-based scoring mechanism can help operation and maintenance personnel quickly locate the source of the problem, improve operation and maintenance efficiency, and generate a more comprehensive comprehensive stability score by integrating electrical, thermal and mechanical stability scores, which can effectively avoid a single score from having too much impact on the overall evaluation results; by collecting on-load tap changer data with known stability states and comparing and analyzing them with the comprehensive scoring results, the scoring system and grading standards can be continuously optimized to make the evaluation model more intelligent and accurate; finally, based on the deep learning network training on-load tap changer stability evaluation model, the stability rating results can be quickly output according to the comprehensive score, providing data support for real-time early warning of equipment operation and future trend prediction, significantly improving the initiative of fault prevention, and continuously optimizing the model according to the training data to ensure timely and accurate data updates. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a schematic diagram of a method flow of an embodiment of the present invention;

[0056] Figure 2 Schematic diagram of system modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0058] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0059] Example:

[0060] See also Figure 1 , the present invention provides a technical solution:

[0061] Step 1: Collect the state parameters of the on-load tap changer in the monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress;

[0062] In this embodiment, data is collected once at the same time interval during the monitoring period, and an acceleration sensor is installed at the contact position of the on-load tap changer for real-time monitoring. The measured acceleration is the overall vibration acceleration of the on-load tap changer; a current sensor is installed at the contact position to collect the contact current; a voltage sensor is used to monitor the voltage at both ends of the contact to generate a contact voltage; an infrared temperature sensor is installed at the contact position to monitor the contact temperature change in real time; and a strain gauge is used to directly measure the spring stress.

[0063] Step 2: Extract the characteristics of the state parameters within the monitoring period to obtain the state characteristic parameters, which include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring period, the vibration acceleration mean of the on-load tap changer within the monitoring period, and the spring stress change of the spring within the monitoring period;

[0064] In this embodiment, the principle for generating the state characteristic parameters is:

[0065] The formula used to generate the contact resistance change rate is:

[0066]

[0067] Among them, R c (t) represents the contact resistance at time t, V z(t) represents the contact voltage at time t, I z (t) represents the contact current at time t, t represents the index of the acquisition time in the monitoring period, and t∈[1,S], S represents the total number of acquisition times, ΔR c Represents the contact resistance change rate, R c (t-1) represents the contact resistance at time t-1;

[0068] Contact resistance reflects the degree of contact quality of the contacts and is used to evaluate the electrical performance of the contacts, affecting the heat source power and contact stability.

[0069] The formula for generating the current fluctuation is:

[0070] ΔI z =max I z (t)-minI z (t)

[0071] Among them, ΔI z Indicates current fluctuation, max I z (t) represents the maximum contact current collected during the monitoring period, minI z (t) represents the minimum contact current collected during the monitoring period;

[0072] Current fluctuation refers to the amplitude of current fluctuation, which reflects the instability of current during the switching process. The larger the current fluctuation, the more likely the risk of poor contact.

[0073] The heat source power is generated according to the formula:

[0074]

[0075] Where Q represents the heat source power;

[0076] Heat source power refers to the heat generated by current flowing through the contact resistance. It is used to evaluate the thermal performance and heat dissipation capacity of the contact. The heat source power affects the material properties of the contact through temperature rise and accelerates mechanical fatigue.

[0077] The formula used to generate the rate of temperature rise is:

[0078]

[0079] Where W represents the temperature rise rate, T(t) represents the contact temperature at time t, T(t-1) represents the contact temperature at time t-1, and ΔT(t) represents the time difference between collecting T(t) and T(t-1);

[0080] The temperature rise rate indicates the speed of change of contact temperature and reflects the heat loss. The higher the temperature rise rate, the higher the heat loss, and the switch may have insufficient heat dissipation or poor contact.

[0081] The formula for generating the mean value of the vibration acceleration of the on-load tap-changer is:

[0082]

[0083] Where A represents the average value of the vibration acceleration of the on-load tap changer, a t represents the vibration acceleration of the on-load tapchanger collected at time t;

[0084] The average vibration acceleration reflects whether there is looseness or abnormal vibration in the mechanical parts of the switch, and reflects the intensity of mechanical vibration. The higher the acceleration, the more likely it is that the switch will be loose, have excessive impact or abnormal vibration, and the contacts, springs or other mechanical components are damaged or loose.

[0085] The formula for generating the spring stress variation is:

[0086]

[0087] Among them, Δσ 弹簧 represents the change in spring stress, σ 弹簧 (t) represents the spring stress collected at time t, σ 弹簧 (t-1) represents the spring stress collected at time t-1.

[0088] The stress change of the spring reflects the state of the spring. When the stress change of the spring maintains a large fluctuation for a long time, it may cause spring fatigue and insufficient contact pressure, affecting the contact resistance and electrical performance.

[0089] Step 3: Based on the state characteristic parameters, an electrical stability score, a thermal stability score, and a mechanical stability score are generated to evaluate the electrical state, the heating state, and the mechanical state of the on-load tap changer respectively, and a comprehensive stability score for comprehensive evaluation of the on-load tap changer is generated by combining the above three scores;

[0090] In this embodiment, the formula for generating the electrical stability score is:

[0091] S1=max(0,100-k1·ΔR c -k2·ΔI z )

[0092] Wherein, S1 represents the electrical stability score, k1 and k2 represent the weight coefficients of the contact resistance change rate and the current fluctuation, respectively, and k1+k2=1, k1=k2;

[0093] 100 represents the full score of the electrical system, i.e. the highest health state, k1·ΔR cIndicates the effect of the contact resistance change rate on electrical stability, ΔR c The larger the value, the lower the score, reflecting problems such as contact wear and poor contact. t It indicates the influence of current fluctuation on electrical stability. Current fluctuation may be caused by arc effect, unstable contact or fluctuation of grid condition, and k1=0.5, k2=0.5. The electrical stability score reflects the electrical condition of the switch during operation. The higher the score, the more stable the electrical performance of the switch and the better the contact and switching quality.

[0094] The formula used to generate the thermal stability score is:

[0095] S2=max(0,100-k3·W-k4·Q)

[0096] Among them, S2 represents the thermal stability score, k3 and k4 represent the weight coefficients of the temperature rise rate and the heat source power respectively, k3+k3=1, and k3<k4;

[0097] k3·W represents the influence of temperature rise rate on thermal stability. The higher the temperature rise rate, the greater the contact resistance or the higher the heat source power, resulting in too fast temperature rise rate of the switch. k4·Q represents the influence of heat source power on thermal stability. Heat source power is determined by current and contact resistance and is the main source of heat loss. Heat source power is the direct source of thermal effect. Therefore, the weight coefficient of Q is larger, k3=0.4, k3=0.6. The thermal stability score comprehensively reflects the thermal performance stability of the switch. The higher the score, the smaller the thermal effect of the switch and the temperature rise is within a reasonable range.

[0098] The formula used to generate the Mechanical Stability Score is:

[0099] S3=max(0,100-k5·A-k6·Δσ 弹簧 )

[0100] Among them, S3 represents the mechanical stability score, k5 and k6 represent the weight coefficients of the vibration acceleration mean and the spring stress change respectively, k5+k6=1, and k5<k6.

[0101] k5·A represents the effect of mechanical vibration acceleration on mechanical stability. A large vibration acceleration indicates that the component is loose or fatigued, resulting in a decrease in mechanical performance. k6·Δσ 弹簧 Indicates the effect of spring stress changes on mechanical stability. When the spring stress fluctuates greatly, it leads to insufficient contact pressure, affecting electrical and mechanical properties. Because the change of spring stress directly affects the contact pressure, Δσ 弹簧The impact on switch performance is greater, k5=0.3, k6=0.7; the mechanical stability score comprehensively reflects the mechanical stability and structural health of the switch. The higher the score, the better the mechanical condition of the switch, without major vibration or fatigue.

[0102] The formula used to generate the overall stability score is:

[0103] X=w1·S1+w2·S2+w3·S3

[0104] Wherein, X represents the comprehensive stability score, w1, w2, and w3 represent the weight coefficients of the electrical stability score, the thermal stability score, and the mechanical stability score, respectively, and w1+w2+w3=1.

[0105] The comprehensive stability score reflects the result of the comprehensive assessment of the health of the switch in combination with electrical stability, thermal stability and mechanical stability. The comprehensive stability is proportional to electrical stability, thermal stability and mechanical stability. The higher the comprehensive stability score, the higher the stability of the on-load tap changer. When the comprehensive stability score decreases, the reason for the decrease in the comprehensive stability score can be determined by analyzing the decrease in electrical stability, thermal stability and mechanical stability. Based on the different use scenarios of the on-load tap changer, the weight coefficient is dynamically adjusted. In the scenario of high load and long-term operation, the electrical performance of the switch has a major impact. Therefore, the weight is relatively large, w1=0.5, w2=0.3, w3=0.2; in a high temperature and high humidity environment, thermal performance is the main risk factor, so the weight is relatively large, w1=0.3, w2=0.5, w3=0.2.

[0106] Step 4: Construct an on-load tap changer stability assessment model based on the deep learning network. Obtain the comprehensive stability score of the on-load tap changer in the monitoring period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment. The state includes normal state, critical state and abnormal state. The comprehensive stability score of the on-load tap changer at the historical moment is used as input, and the state is used as a label to train the on-load tap changer stability assessment model.

[0107] In this embodiment, the structure of the deep learning network is:

[0108] Input layer: contains 1 neuron, which is used to input the comprehensive stability score of the on-load tap changer;

[0109] The first hidden layer: contains 64 neurons, activated by the ReLU function;

[0110] The second hidden layer: contains 64 neurons, activated by the ReLU function;

[0111] The third hidden layer: contains 32 neurons, activated by the ReLU function;

[0112] Output layer: contains 3 neurons, which are used to output the stability rating of the on-load tap changer.

[0113] Step 5: Input the comprehensive stability score of the on-load tap changer in the monitoring period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

[0114] See also Figure 2 The present invention also provides a stability evaluation system for an on-load tap changer for a UHV converter transformer, the system being used to implement the stability evaluation method for the on-load tap changer for a UHV converter transformer, specifically comprising:

[0115] A data acquisition module is used to collect state parameters of the on-load tap changer in a monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress;

[0116] A feature extraction module is used to extract features of state parameters within the monitoring time period to obtain state feature parameters, wherein the state feature parameters include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring time period, the vibration acceleration mean value of the on-load tap changer within the monitoring time period, and the spring stress change amount of the spring within the monitoring time period;

[0117] A characteristic scoring module is used to generate an electrical stability score, a thermal stability score, and a mechanical stability score for respectively evaluating the electrical state, the heating state, and the mechanical state of the on-load tap changer based on the state characteristic parameters, and to generate a comprehensive stability score for comprehensively evaluating the on-load tap changer by combining the above three scores;

[0118] A model training module is used to build an on-load tap changer stability assessment model based on a deep learning network, obtain the comprehensive stability score of the on-load tap changer in the monitoring time period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment, the state includes a normal state, a critical state and an abnormal state, and use the comprehensive stability score of the on-load tap changer at the historical moment as input and the state as a label to train the on-load tap changer stability assessment model;

[0119] The evaluation and judgment module is used to input the comprehensive stability score of the on-load tap changer in the monitoring time period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

[0120] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0121] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A stability evaluation method for an on-load tap changer for a UHV converter transformer, characterized in that: The specific steps include: Step 1: Collect the state parameters of the on-load tap changer in the monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress; Step 2: Extract the characteristics of the state parameters within the monitoring period to obtain the state characteristic parameters, which include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring period, the vibration acceleration mean of the on-load tap changer within the monitoring period, and the spring stress change of the spring within the monitoring period; Step 3: Based on the state characteristic parameters, an electrical stability score, a thermal stability score, and a mechanical stability score are generated to evaluate the electrical state, the heating state, and the mechanical state of the on-load tap changer respectively, and a comprehensive stability score for comprehensive evaluation of the on-load tap changer is generated by combining the above three scores; Step 4: Construct an on-load tap changer stability assessment model based on the deep learning network. Obtain the comprehensive stability score of the on-load tap changer in the monitoring period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment. The state includes normal state, critical state and abnormal state. The comprehensive stability score of the on-load tap changer at the historical moment is used as input, and the state is used as a label to train the on-load tap changer stability assessment model. Step 5: Input the comprehensive stability score of the on-load tap changer in the monitoring period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

2. The stability evaluation method for an on-load tap changer for an ultra-high voltage converter transformer according to claim 1 is characterized in that: The step 1 collects data at the same time interval during the monitoring period, installs an acceleration sensor at the contact position of the on-load tap changer for real-time monitoring, and the measured acceleration is the overall vibration acceleration of the on-load tap changer; installs a current sensor at the contact position to collect the contact current; monitors the voltage at both ends of the contact through a voltage sensor to generate a contact voltage; installs an infrared temperature sensor at the contact position to monitor the contact temperature change in real time; and directly measures the spring stress through a strain gauge.

3. The stability evaluation method for an on-load tap changer for an ultra-high voltage converter transformer according to claim 1 is characterized in that: The principle for generating the state characteristic parameters in step 2 is: The formula used to generate the contact resistance change rate is: Among them, R c (t) represents the contact resistance at time t, V z (t) represents the contact voltage at time t, I z (t) represents the contact current at time t, t represents the index of the acquisition time in the monitoring period, and t∈[1, S], S represents the total number of acquisition times, ΔR c Represents the contact resistance change rate, R c (t-1) represents the contact resistance at time t-1; The formula for generating the current fluctuation is: ΔI z =maxI z (t)-minI z (t) Among them, ΔI z Indicates current fluctuation, maxI z (t) represents the maximum contact current collected during the monitoring period, minI z (t) represents the minimum contact current collected during the monitoring period; The heat source power is generated according to the formula: Where Q represents the heat source power; The formula used to generate the rate of temperature rise is: Where W represents the temperature rise rate, T(t) represents the contact temperature at time t, T(t-1) represents the contact temperature at time t-1, and ΔT(t) represents the time difference between collecting T(t) and T(t-1); The formula for generating the mean value of the vibration acceleration of the on-load tap-changer is: Where A represents the average value of the vibration acceleration of the on-load tap changer, a t represents the vibration acceleration of the on-load tapchanger collected at time t; The formula for generating the spring stress variation is: Among them, Δσ 弹簧 represents the change in spring stress, σ 弹簧 (t) represents the spring stress collected at time t, σ 弹簧 (t-1) represents the spring stress collected at time t-1.

4. The stability evaluation method for an on-load tap changer for an ultra-high voltage converter transformer according to claim 3 is characterized in that: The electrical stability score is generated based on the formula: S1=max(0,100-k1·ΔR c -k2·ΔI z ) Wherein, S1 represents the electrical stability score, k1 and k2 represent the weight coefficients of the contact resistance change rate and the current fluctuation, respectively, and k1+k2=1, k1=k2; The formula used to generate the thermal stability score is: S2=max(0,100-k3·W-k4·Q) Among them, S2 represents the thermal stability score, k3 and k4 represent the weight coefficients of the temperature rise rate and the heat source power respectively, k3+k3=1, and k3<k4; The formula used to generate the Mechanical Stability Score is: S3=max(0,100-k5·A-k6·Δσ 弹簧 ) Among them, S3 represents the mechanical stability score, k5 and k6 represent the weight coefficients of the vibration acceleration mean and the spring stress change respectively, k5+k6=1, and k5<k6.

5. The stability evaluation method of an on-load tap changer for a UHV converter transformer according to claim 6 is characterized in that: The formula used to generate the overall stability score is: X=w1·S1+w2·S2+w3·S3 Wherein, X represents the comprehensive stability score, w1, w2, and w3 represent the weight coefficients of the electrical stability score, the thermal stability score, and the mechanical stability score, respectively, and w1+w2+w3=1.

6. A stability assessment system for an on-load tap changer for a UHV converter transformer, characterized in that: The system is used to implement the stability evaluation method for an on-load tap changer for an ultra-high voltage converter transformer according to any one of claims 1 to 5, and specifically comprises: A data acquisition module is used to collect state parameters of the on-load tap changer in a monitoring period before the current moment, the state parameters including vibration acceleration, contact current, contact voltage, contact temperature and spring stress; A feature extraction module is used to extract features of state parameters within the monitoring time period to obtain state feature parameters, wherein the state feature parameters include the contact resistance change rate, current fluctuation, heat source power and temperature rise rate of the contact within the monitoring time period, the vibration acceleration mean value of the on-load tap changer within the monitoring time period, and the spring stress change amount of the spring within the monitoring time period; A characteristic scoring module is used to generate an electrical stability score, a thermal stability score, and a mechanical stability score for respectively evaluating the electrical state, the heating state, and the mechanical state of the on-load tap changer based on the state characteristic parameters, and to generate a comprehensive stability score for comprehensively evaluating the on-load tap changer by combining the above three scores; A model training module is used to build an on-load tap changer stability assessment model based on a deep learning network, obtain the comprehensive stability score of the on-load tap changer in the monitoring time period before the previous historical moment in the same way, and judge the state of the on-load tap changer at the historical moment, the state includes a normal state, a critical state and an abnormal state, and use the comprehensive stability score of the on-load tap changer at the historical moment as input and the state as a label to train the on-load tap changer stability assessment model; The evaluation and judgment module is used to input the comprehensive stability score of the on-load tap changer in the monitoring time period before the current moment into the trained on-load tap changer stability evaluation model to obtain the state of the on-load tap changer at the current moment.

Images