Method and device for pre-judging abnormity of oil-immersed mutual inductor and computer equipment
Through the multivariate half-staircase method, the state scores of the oil pressure, wide frequency domain and vibration data of the oil-immersed transformer are solved, and the problem of real-time comprehensive monitoring and prediction in the existing technology is not possible, real-time prediction of the status abnormalities of the oil-immersed transformer is achieved, and the safety and stability of the power grid is improved.
Patent Information
- Application Number
- CN202311559044.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-21
- Publication Date
- 2025-03-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is difficult to realize real-time comprehensive monitoring and prediction of oil-immersed transformers, and it is impossible to effectively detect and predict equipment abnormal status.
The multivariate half-lead method is used to collect the oil pressure, wide frequency domain and vibration data of the oil-immersed transformer in real time, and the state scores of these data through the multivariate half-lead method to determine whether the equipment needs maintenance.
Real-time prediction of abnormal states of oil-immersed transformers is achieved, and monitoring and prediction are more comprehensive and accurate, which helps to improve the safe and stable operation of the power grid.
Smart Images
Figure CN119719555A_ABST
Abstract
Description
[Technical field]
[0001] The invention belongs to the technical field of electrical equipment, and in particular relates to a detection technology for oil-immersed transformer equipment. [Background technology]
[0002] Oil-immersed instrument transformers are one of the important electrical equipment in the power system. The failure of the instrument transformer will not only affect the normal power consumption of users, but also directly threaten the stable operation of the power grid. The status assessment of oil-immersed instrument transformers is the premise and basis for the status maintenance of power transformers. It can effectively understand the operating status of oil-immersed instrument transformers and provide early fault warnings, which is very important for improving the reliability and stability of the power system.
[0003] As the scale of power grid equipment grows substantially, the number and types of oil-immersed transformers are also increasing day by day, and real-time monitoring of the status of equipment faces great challenges.
[0004] When an abnormality occurs inside the current transformer, the internal oil pressure will change significantly. Based on this, the existing technology measures the oil pressure value and change value inside the oil-immersed current transformer in real time, and judges whether there is an abnormality or fault inside the transformer according to the normal oil pressure inside the transformer and the pressure value of the fault. However, there are many other factors that can cause abnormality of the oil-immersed transformer, and the existing technology cannot fully monitor and predict. [Summary of the invention]
[0005] The technical problem to be solved by the present invention is to provide an oil-immersed transformer abnormality prediction method based on a multi-element half-ladder reduction method, so as to solve the problem of real-time comprehensive monitoring and prediction of abnormal states of oil-immersed transformers.
[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:
[0007] A method for predicting abnormality of an oil-immersed transformer based on a multivariate half-ladder descending method comprises the following steps:
[0008] Real-time collection of three index factors of the monitored oil-immersed transformer, the three index factors being oil pressure, wide frequency domain and vibration data;
[0009] The multivariate half-step method is used to score the status of the real-time monitored oil pressure, wide frequency domain and vibration data; based on the scoring results, it is determined whether the oil-immersed transformer needs maintenance.
[0010] Preferably, the half-stepping model function adopted by the multivariate half-stepping method is:
[0011]
[0012] Among them, a and b are the thresholds under this function, and x is the real-time monitoring value of oil pressure, wide frequency domain and vibration data; when f(x)∈[0,a], the equipment is in poor condition and needs maintenance;
[0013] When f(x)∈(a,b], the device status is general;
[0014] When f(x)∈(b,1], the equipment is in good condition and no maintenance is required.
[0015] Preferably, a=0.3, and b=0.7.
[0016] Preferably, a real-time updated oil-immersed transformer status evaluation database is formed based on the monitored operating data of the oil-immersed transformer over the years and the historical data when the fault occurs;
[0017] The a and b thresholds are derived from the three indicator factor parameters when the database is put into operation and when the failure begins, and are updated in real time according to the changes in the database:
[0018] a=1 / n(a1+a2+a3+…+a n )
[0019] b=1 / n(b1+b2+b3+…b n ).
[0020] Preferably, a multivariate half-step down method is used to score the status information of the real-time monitored oil pressure, wide frequency domain and vibration data respectively, and when any one of the status information scores determines that the equipment state is poor, it is determined that the oil-immersed transformer needs to be repaired.
[0021] Preferably, a multivariate half-step down method is used to perform status information scoring on the real-time monitored oil pressure, wide frequency domain and vibration data respectively. When any one of the status information scores determines that the equipment state is poor, and another one of the status information scores determines that the equipment state is average or poor, it is determined that the oil-immersed transformer needs maintenance.
[0022] On the other hand, a device for predicting abnormalities of an oil-immersed transformer is provided, including a monitoring device unit and a real-time diagnosis unit. The monitoring device unit includes a monitoring device oil pressure sensor for real-time acquisition of the oil pressure of the monitored oil-immersed transformer, a monitoring device wide-frequency domain sensor for real-time acquisition of the wide-frequency domain of the monitored oil-immersed transformer, and a monitoring device vibration sensor for real-time acquisition of the vibration of the monitored oil-immersed transformer; the real-time diagnosis unit uses a multivariate half-step-down method to score the status information of the real-time monitored oil pressure, wide-frequency domain and vibration data, and determines whether the oil-immersed transformer needs maintenance based on the scoring results.
[0023] Finally, a computer device is also provided, comprising at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the oil-immersed transformer abnormality prediction method based on the multivariate half-ladder method.
[0024] The technical solution adopted by the present invention uses a multivariate half-step-down method. According to the historical operating data of the oil-immersed transformer of the substation and the historical data when the fault occurred, the sample capacity is innovatively provided according to the historical database. Based on the database, the real-time state parameters of various influencing factors of the oil-immersed transformer detected by the prediction method are calculated by the half-step-down method to obtain a state evaluation score. The state of the oil-immersed transformer is evaluated by this score, and the real-time prediction of the abnormal state of the oil-immersed transformer is realized. The three indicator factors of the oil-immersed transformer include oil pressure, wide frequency domain and vibration data. The monitoring and prediction are more comprehensive and accurate, which is conducive to the safe and stable operation of the power grid.
[0025] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings.
Brief Description of the Drawings
[0026] The invention will be further described below with reference to the accompanying drawings:
[0027] Figure 1 The present invention is a flow chart of the abnormality prediction method of an oil-immersed transformer based on the multi-element half-ladder reduction method. [Specific implementation method]
[0028] The technical solutions of the embodiments of the present invention are explained and described below in conjunction with the drawings of the embodiments of the present invention, but the following embodiments are only preferred embodiments of the present invention, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the protection scope of the present invention.
[0029] Embodiment 1
[0030] An abnormality prediction device for an oil-immersed transformer includes a monitoring device unit and a real-time diagnosis unit. The monitoring device unit includes a monitoring device oil pressure sensor for real-time acquisition of the oil pressure of the monitored oil-immersed transformer, a monitoring device wide frequency domain sensor for real-time acquisition of the wide frequency domain of the monitored oil-immersed transformer, and a monitoring device vibration sensor for real-time acquisition of the vibration of the monitored oil-immersed transformer.
[0031] The real-time diagnosis unit uses a multivariate half-step-down method to score the status information of the oil pressure, wide frequency domain and vibration data monitored in real time, and determines whether the oil-immersed transformer needs to be repaired based on the scoring result.
[0032] Embodiment 2
[0033] like Figure 1 As shown, a method for predicting abnormality of an oil-immersed transformer based on a multivariate half-ladder descending method comprises the following steps:
[0034] The data required for the abnormal prediction method of the oil-immersed transformer is preprocessed, and three indicator factors with important identification strength for the oil-immersed transformer are screened out, namely: oil pressure, wide frequency domain and vibration.
[0035] Real-time collection of oil pressure, wide frequency domain and vibration data of the monitored oil-immersed transformer;
[0036] The multivariate half-step down method is used to score the status information of the three types of index data, namely oil pressure, wide frequency domain and vibration, which are detected in real time by the abnormal prediction method of the oil-immersed transformer. The half-step down model function is as follows:
[0037]
[0038] Where a and b are the thresholds under this function, and x is the measured value, including the real-time monitoring value of oil pressure, wide frequency domain and vibration data. Substituting the measured value into the above f(x) formula, the obtained value is between [0,1].
[0039] When f(x)∈[0,0.3], the equipment is in poor condition and needs maintenance;
[0040] When f(x)∈(0.3,0.7], the device status is general, and the lower the score, the more attention should be paid;
[0041] When f(x)∈(0.7,1], the equipment is in good condition and no maintenance is required.
[0042] The a and b thresholds are obtained from the three index factor parameters with important identification strength when the database is put into operation and the three index factor parameters with important identification strength when the failure begins. The data of the month after the new equipment starts to operate is the good equipment status value, recorded as a; when the equipment fails, the data of the previous month is the poor equipment status value, recorded as b, and is updated in real time according to the changes in the database. The update formulas of the a and b thresholds are as follows:
[0043] a=1 / n(a1+a2+a3+…+a n )
[0044] b=1 / n(b1+b2+b3+…b n ).
[0045] a1…a n is the continuously updated a value, b1…bn is the continuously updated b value.
[0046] There are many ways to determine whether the oil-immersed transformer needs maintenance:
[0047] The multivariate half-step method is used to score the status information of the real-time monitored oil pressure, wide frequency domain and vibration data respectively. When any of the status information scores judges that the equipment status is poor, it is judged that the oil-immersed transformer needs to be repaired.
[0048] The multivariate half-step method is used to score the status information of the real-time monitored oil pressure, wide frequency domain and vibration data respectively. When any one of the status information scores determines that the equipment status is poor and another status information score determines that the equipment status is average or poor, it is determined that the oil-immersed transformer needs to be repaired.
[0049] The monitoring device unit of the present invention is provided with a monitoring device oil pressure sensor for real-time acquisition of the oil pressure of the monitored oil-immersed transformer, a monitoring device wide frequency domain sensor for real-time acquisition of the wide frequency domain of the monitored oil-immersed transformer, and a monitoring device vibration sensor for real-time acquisition of the vibration of the monitored oil-immersed transformer. Since the three index factors include oil pressure, wide frequency domain and vibration data, monitoring and prejudgment are more comprehensive and accurate. Furthermore, the real-time state parameters of various influencing factors of the oil-immersed transformer detected by the prejudgment method are calculated using the half-stepping method to obtain a state evaluation score, and the state of the oil-immersed transformer is evaluated based on this score, realizing real-time prejudgment of abnormal state of the oil-immersed transformer, which is beneficial to the safe and stable operation of the power grid.
[0050] In addition, the present invention implements the method for predicting abnormalities of an oil-immersed transformer based on the multi-element half-step down method through a computer device, and the computer device includes at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method for predicting abnormalities of an oil-immersed transformer based on the multi-element half-step down method.
[0051] The above is only a specific embodiment of the invention, but the protection scope of the invention is not limited thereto. Those skilled in the art should understand that the invention includes but is not limited to the contents described in the drawings and the above specific embodiments. Any modification that does not deviate from the functional and structural principles of the invention will be included in the scope of the claims.
Claims
1. A method for predicting abnormality of an oil-immersed transformer based on a multivariate half-ladder method, characterized in that: The steps include: Real-time collection of three index factors of the monitored oil-immersed transformer, the three index factors being oil pressure, wide frequency domain and vibration data; The multivariate half-step down method is used to evaluate the status of the real-time monitored oil pressure, wide frequency domain and vibration data; Determine whether the oil-immersed transformer needs maintenance based on the scoring results.
2. The method for predicting abnormality of an oil-immersed transformer based on the multivariate half-ladder descending method according to claim 1 is characterized in that: The half-step down model function used in the multivariate half-step down method is: Among them, a and b are the thresholds under this function, and x is the real-time monitoring value of oil pressure, wide frequency domain and vibration data; when f(x)∈[0,a], the equipment is in poor condition and needs maintenance; When f(x)∈(a,b], the device status is general; When f(x)∈(b,1], the equipment is in good condition and no maintenance is required.
3. The method for predicting abnormality of an oil-immersed transformer based on the multivariate half-ladder descending method according to claim 2 is characterized in that: a=0.3, and b=0.
7.
4. The method for predicting abnormality of an oil-immersed transformer based on the multivariate half-ladder descending method according to claim 2 is characterized in that: Based on the historical operating data of the monitored oil-immersed transformers and the historical data when faults occurred, a real-time updated oil-immersed transformer status evaluation database is formed; The a and b thresholds are derived from the three indicator factor parameters when the database is put into operation and when the failure begins, and are updated in real time according to the changes in the database: <h2 style=";text-align:left;direction:ltr">a = 1 / n(a1+a2+a3+…+a<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> ) <h2 style=";text-align:left;direction:ltr">b = 1 / n(b1+b2+b3+…b<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> )。 5. The method for predicting abnormality of an oil-immersed transformer based on the multivariate half-ladder descending method according to claim 1 is characterized in that: The multivariate half-step method is used to score the status information of the real-time monitored oil pressure, wide frequency domain and vibration data respectively. When any of the status information scores judges that the equipment status is poor, it is judged that the oil-immersed transformer needs to be repaired.
6. The method for predicting abnormality of an oil-immersed transformer based on the multivariate half-ladder descending method according to claim 1 is characterized in that: The multivariate half-step method is used to score the status information of the real-time monitored oil pressure, wide frequency domain and vibration data respectively. When any one of the status information scores determines that the equipment status is poor and another status information score determines that the equipment status is average or poor, it is determined that the oil-immersed transformer needs to be repaired.
7. An oil-immersed transformer abnormality prediction device, characterized in that: It includes a monitoring device unit and a real-time diagnosis unit. The monitoring device unit includes a monitoring device oil pressure sensor for real-time acquisition of the oil pressure of the monitored oil-immersed transformer, a monitoring device wide-frequency domain sensor for real-time acquisition of the wide-frequency domain of the monitored oil-immersed transformer, and a monitoring device vibration sensor for real-time acquisition of the vibration of the monitored oil-immersed transformer. The real-time diagnosis unit uses a multivariate half-step-down method to score the status information of the real-time monitored oil pressure, wide-frequency domain and vibration data, and determines whether the oil-immersed transformer needs maintenance based on the scoring results.
8. A computer device, characterized in that: It includes at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the oil-immersed transformer abnormality prediction method based on the multivariate half-step method as described in any one of claims 1 to 6.