CN113945299B - Transformer winding temperature distribution and residual life prediction method - Google Patents
Transformer winding temperature distribution and residual life prediction method Download PDFInfo
- Publication number
- CN113945299B CN113945299B CN202111078692.8A CN202111078692A CN113945299B CN 113945299 B CN113945299 B CN 113945299B CN 202111078692 A CN202111078692 A CN 202111078692A CN 113945299 B CN113945299 B CN 113945299B
- Authority
- CN
- China
- Prior art keywords
- transformer
- temperature
- winding
- neuron
- hidden layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
- G01K11/3206—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres at discrete locations in the fibre, e.g. using Bragg scattering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
Description
技术领域Technical Field
本发明属于电力变压器状态评估技术领域，特别是涉及一种变压器绕组温度分布与剩余寿命预测方法。The invention belongs to the technical field of power transformer status assessment, and in particular relates to a method for predicting transformer winding temperature distribution and remaining life.
背景技术Background technique
变压器作为电网的核心设备之一，承担着电能传输的重要作用。变压器运行时其铁芯、绕组等部件产生的损耗会在内部产生温升，导致变压器绕组绝缘老化加速进而影响变压器的使用寿命。变压器的载荷能力以及剩余寿命主要取决于它的热特性。因此，为防止变压器出现过热，保障其安全稳定运行，亟需研究对变压器的温度和寿命进行预测的方法。As one of the core equipment of the power grid, the transformer plays an important role in power transmission. When the transformer is in operation, the losses in its core, winding and other components will cause internal temperature rise, which will accelerate the aging of the transformer winding insulation and thus affect the service life of the transformer. The load capacity and remaining life of the transformer mainly depend on its thermal characteristics. Therefore, in order to prevent the transformer from overheating and ensure its safe and stable operation, it is urgent to study methods to predict the temperature and life of the transformer.
目前，常规的变压器内部绕组温度获取方法主要有直接测量法、热模拟测量法和间接计算法等。直接测量方法通过在变压器绕组内埋设传感器，利用温度测量仪获取绕组测量点的温度，埋入的温度传感器越多，测量结果越精确。但由于变压器内部散热不均匀，难以保证传感器的安装能够先验性地放置于绕组的热点温度位置。热模拟测量法将附加电流在电热元件上的温升，迭加到变压器顶层油温上，获得变压器绕组热点温度。该方法测量误差较大，实用性较差。间接计算法主要依据实际运行中易于测量的变压器及环境参数，通过计算各关键参数和变压器负载电流值来计算绕组热点温度。由于简化后的热路模型未考虑到诸多影响因素，如：油的粘度系数、负载动态损耗等等，从而无法保证计算结果准确度。因此，亟需提出一种准确的变压器绕组温度分布预测与剩余寿命评估的方法。At present, the conventional methods for obtaining the internal winding temperature of a transformer mainly include direct measurement, thermal simulation measurement, and indirect calculation. The direct measurement method uses a temperature measuring instrument to obtain the temperature of the winding measurement point by burying sensors in the transformer winding. The more temperature sensors are buried, the more accurate the measurement results are. However, due to the uneven heat dissipation inside the transformer, it is difficult to ensure that the installation of the sensor can be placed at the hot spot temperature position of the winding a priori. The thermal simulation measurement method superimposes the temperature rise of the additional current on the electric heating element on the top oil temperature of the transformer to obtain the hot spot temperature of the transformer winding. This method has a large measurement error and poor practicality. The indirect calculation method mainly calculates the hot spot temperature of the winding by calculating the key parameters and the transformer load current value based on the transformer and environmental parameters that are easy to measure in actual operation. Since the simplified thermal circuit model does not take into account many influencing factors, such as: oil viscosity coefficient, load dynamic loss, etc., the accuracy of the calculation results cannot be guaranteed. Therefore, it is urgent to propose an accurate method for transformer winding temperature distribution prediction and remaining life assessment.
发明内容Summary of the invention
针对现有技术中的缺陷，本发明提供了一种变压器绕组温度分布与剩余寿命预测方法，将常规光纤测温法与温度分布预测算法结合，计算速度快，温度分布预测精度高，变压器老化速率与寿命预测准确，便于快速发现处于异常工况下的变压器，有利于保障电力变压器安全稳定运行。本发明的具体技术方案如下：In view of the defects in the prior art, the present invention provides a method for predicting the temperature distribution and remaining life of transformer windings, which combines the conventional optical fiber temperature measurement method with the temperature distribution prediction algorithm, has fast calculation speed, high temperature distribution prediction accuracy, accurate transformer aging rate and life prediction, and is convenient for quickly discovering transformers in abnormal working conditions, which is conducive to ensuring the safe and stable operation of power transformers. The specific technical solutions of the present invention are as follows:
一种变压器绕组温度分布与剩余寿命预测方法，包括以下步骤：A method for predicting temperature distribution and remaining life of transformer windings comprises the following steps:
S1，采集与待测变压器同型号的变压器的运行参数与温升试验数据；S1, collect the operating parameters and temperature rise test data of the transformer of the same model as the transformer to be tested;
S2，在待测变压器完成铁芯制作与绕组绕制后，按特定规则将若干个光纤光栅温度传感器埋设在变压器的绕组匝间，实时测量绕组各离散位置的温度数据；S2, after the core of the transformer to be tested is made and the winding is wound, several fiber grating temperature sensors are buried between the winding turns of the transformer according to specific rules to measure the temperature data of each discrete position of the winding in real time;
S3，基于实时测量得到的绕组各离散位置的温度数据，结合神经网络算法，预测绕组内部各区域的温度数据，预测变压器绕组各饼的温度分布；S3, based on the temperature data of each discrete position of the winding obtained by real-time measurement, combined with the neural network algorithm, predict the temperature data of each area inside the winding and predict the temperature distribution of each cake of the transformer winding;
S4，根据S3中获得的变压器绕组各饼温度分布预测值，利用热老化6度法预测变压器的老化速率与剩余寿命。S4, predicting the aging rate and remaining life of the transformer by using the 6-degree thermal aging method according to the predicted value of the temperature distribution of each wafer of the transformer winding obtained in S3.
优选地，所述步骤S1中所述同型号变压器为同规格、已投入运行的电力变压器。Preferably, the transformer of the same model in step S1 is a power transformer of the same specification that has been put into operation.
优选地，所述步骤S1中所述运行参数与温升试验数据包括变压器自身参数、顶层油温、散热器进出口温度、绕组热点温度信息。Preferably, the operating parameters and temperature rise test data in step S1 include transformer parameters, top oil temperature, radiator inlet and outlet temperatures, and winding hot spot temperature information.
优选地，所述变压器自身参数包括变压器线圈高度、直径，铁芯距旁轭的长、宽、高，油箱的三围尺寸。Preferably, the transformer parameters include transformer coil height, diameter, length, width and height of the core to the side yoke, and dimensions of the oil tank.
优选地，所述步骤S2中的特定规则为：在变压器绕组顶部以下10％-20％处为局部热点区域，在局部热点区域每饼线圈埋设的光纤光栅温度传感器数量多于其他常规温度区域每饼线圈埋设的光纤光栅温度传感器数量。Preferably, the specific rule in step S2 is: 10%-20% below the top of the transformer winding is a local hot spot area, and the number of fiber grating temperature sensors buried in each coil in the local hot spot area is greater than the number of fiber grating temperature sensors buried in each coil in other conventional temperature areas.
优选地，光纤光栅温度传感器的埋设方法为：沿变压器绕组顶部各饼之间的缝隙埋设并固定于绝缘块槽内，将测温通道的尾纤从绕组顶部接入贯通板。Preferably, the fiber Bragg grating temperature sensor is buried along the gap between the cakes at the top of the transformer winding and fixed in the insulating block groove, and the pigtail of the temperature measurement channel is connected to the through plate from the top of the winding.
优选地，所述步骤S3具体包括以下步骤：Preferably, the step S3 specifically includes the following steps:
设x1,x2,...,xn为光纤光栅温度传感器测得的绕组各离散位置的温度数据，作为神经元网络的输入，输入神经网络的温度数据总个数为n；设y1,y2,...,ym为神经元计算后输出的变压器绕组温度预测量，经过神经网络计算后输出的总个数为m；wij为输入层第i个神经元与隐含层第j个神经元之间的连接权值，wjk为隐含层第j个神经元与输出层第k个神经元之间的连接权值；Let x 1 , x 2 , ..., x n be the temperature data of each discrete position of the winding measured by the fiber Bragg grating temperature sensor, as the input of the neural network, and the total number of temperature data input to the neural network is n; let y 1 , y 2 , ..., y m be the predicted temperature of the transformer winding output after the neural network calculation, and the total number of outputs after the neural network calculation is m; w ij is the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, and w jk is the connection weight between the j-th neuron in the hidden layer and the k-th neuron in the output layer;
则中间隐含层第j个温度输入的加权和为：Then the weighted sum of the jth temperature input in the middle hidden layer is:
对于隐含层神经元，激发函数为：For the hidden layer neurons, the activation function is:
对于隐含层第j个神经元有：For the jth neuron in the hidden layer, we have:
Hj是隐含层第j个神经元的输出，其计算公式如下： Hj is the output of the jth neuron in the hidden layer, and its calculation formula is as follows:
Hj＝f(netj)；(3)H j = f ( net j ); (3)
则输出误差为：The output error is:
l为隐含层神经元总个数。l is the total number of neurons in the hidden layer.
其中，Yk为神经元输出期望，基于所述步骤S1中采集的同型号变压器运行参数与温升试验数据得到；Wherein, Yk is the expected output of the neuron, which is obtained based on the operating parameters and temperature rise test data of the same type of transformer collected in step S1;
基于输出误差，对输出层和隐含层进行修正，如下：Based on the output error, the output layer and hidden layer are corrected as follows:
输出层权值修正：Output layer weight correction:
wjk2＝wjk+ηHjek；(5)w jk2 =w jk +ηH j e k ; (5)
其中，η为学习率，是神经网络的网络参数；wjk2为隐含层第j个神经元与输出层第k个神经元之间连接权值的修正值；Among them, η is the learning rate, which is the network parameter of the neural network; w jk2 is the correction value of the connection weight between the jth neuron in the hidden layer and the kth neuron in the output layer;
隐含层权值修正：Hidden layer weight correction:
其中，wij2为输入层第i个神经元与隐含层第j个神经元之间连接权值的修正值；Where, w ij2 is the correction value of the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer;
基于修正后的输出层权值以及隐含层权值，可得变压器绕组各饼的预测温度分布：Based on the corrected output layer weights and hidden layer weights, the predicted temperature distribution of each cake of the transformer winding can be obtained:
其中，Hj2表示修正后的隐含层第j个神经元， Among them, H j2 represents the jth neuron in the modified hidden layer,
优选地，所述步骤S4中利用热老化6度法预测变压器的老化速率与剩余寿命具体包括：Preferably, the step S4 of predicting the aging rate and the remaining life of the transformer by using the 6-degree thermal aging method specifically includes:
所述热老化6度法指变压器内部温度每上升6K，老化率增大一倍，基于此，得到各热点温度下的相对老化速率为：The 6-degree thermal aging method means that the aging rate doubles for every 6K increase in the internal temperature of the transformer. Based on this, the relative aging rate at each hot spot temperature is obtained as follows:
V＝2(t-98)/6；(8)V = 2(t-98)/6; (8)
其中t为变压器内部温度，单位是摄氏度℃；Where t is the internal temperature of the transformer, in degrees Celsius;
所述变压器剩余寿命利用已损失寿命获取：The remaining life of the transformer is obtained by using the lost life:
其中，L为变压器剩余寿命；S为变压器设计寿命；V为变压器运行在t1～t2时间段内的相对老化率。Wherein, L is the remaining life of the transformer; S is the design life of the transformer; and V is the relative aging rate of the transformer during the period from t 1 to t 2 .
本发明的有益效果为：一方面，本发明通过多组光纤光栅温度传感器直接测量变压器内部绕组离散点温度，结合神经网络算法，拟合出绕组间连续数据，预测变压器绕组各饼的温度分布，其中所述神经网络算法用于拟合离散点的温度数据，预测变压器内部绕组各区域的连续温度分布，绕组各区域指的是将绕组各饼均分为多个区域，对各区域位置进行温度预测，通过学习来抽取及逼近输入温度和输出温度的非线性关系；另一方面，本发明根据取得的变压器热点温度，利用热老化6度法预测变压器老化速率与剩余寿命；本发明取得的结果有利于对变压器载荷状况进行调整，对变压器异常状况进行警告，便于发现异常工况下的变压器，有利于保障电力变压器安全稳定运行，具备推广前景。The beneficial effects of the present invention are as follows: on the one hand, the present invention directly measures the temperature of discrete points of the transformer internal windings through multiple groups of fiber grating temperature sensors, and combines with a neural network algorithm to fit the continuous data between the windings and predict the temperature distribution of each cake of the transformer winding, wherein the neural network algorithm is used to fit the temperature data of discrete points and predict the continuous temperature distribution of each region of the transformer internal winding, each region of the winding refers to dividing each cake of the winding into multiple regions, and predicting the temperature of each region position, and extracting and approximating the nonlinear relationship between the input temperature and the output temperature through learning; on the other hand, the present invention predicts the aging rate and the remaining life of the transformer according to the obtained hot spot temperature of the transformer using the 6-degree thermal aging method; the results obtained by the present invention are conducive to adjusting the load condition of the transformer, warning the abnormal condition of the transformer, facilitating the discovery of the transformer under abnormal working conditions, and conducive to ensuring the safe and stable operation of the power transformer, and has a prospect for promotion.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍。在所有附图中，类似的元件或部分一般由类似的附图标记标识。附图中，各元件或部分并不一定按照实际的比例绘制。In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.
图1为本发明实施例基于光纤传感的变压器绕组温度分布与剩余寿命预测方法的流程图；FIG1 is a flow chart of a method for predicting temperature distribution and remaining life of transformer windings based on optical fiber sensing according to an embodiment of the present invention;
图2为本发明中光纤温度传感器测量点埋设细节图；FIG2 is a detailed diagram of the buried measurement points of the optical fiber temperature sensor in the present invention;
图3为本发明光纤温度传感器常规温度区域阵列以及热点温度区域阵列；FIG3 is a conventional temperature region array and a hot spot temperature region array of the optical fiber temperature sensor of the present invention;
图4为本发明神经网络结构；FIG4 is a neural network structure of the present invention;
附图标记说明：1、绕组第十饼，2、绕组第九饼，3、绕组第八饼，4、绕组第七饼，5、绕组第六饼，6、绕组第五饼，7、绕组第四饼，8、绕组第三饼，9、绕组第二饼，10、绕组第一饼，11、光纤光栅传感器，12、传感器常规温度区域阵列，13、传感器热点温度区域阵列，14、阵列接头。Explanation of the accompanying drawings: 1. Winding tenth cake, 2. Winding ninth cake, 3. Winding eighth cake, 4. Winding seventh cake, 5. Winding sixth cake, 6. Winding fifth cake, 7. Winding fourth cake, 8. Winding third cake, 9. Winding second cake, 10. Winding first cake, 11. Fiber Bragg grating sensor, 12. Sensor conventional temperature zone array, 13. Sensor hot spot temperature zone array, 14. Array joint.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”和“包含”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and/or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or combinations thereof.
还应当理解，在本发明说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本发明。如在本发明说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.
还应当进一步理解，在本发明说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。It should be further understood that the term "and/or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
如图1所示，一种变压器绕组温度分布与剩余寿命预测方法，包括以下步骤：As shown in FIG1 , a method for predicting temperature distribution and remaining life of transformer windings includes the following steps:
S1，采集与待测变压器同型号的变压器的运行参数与温升试验数据；所述同型号变压器为同规格、已投入运行的电力变压器。所述运行参数与温升试验数据包括变压器自身参数、顶层油温、散热器进出口温度、绕组热点温度信息。所述变压器自身参数包括变压器线圈高度、直径，铁芯距旁轭的长、宽、高，油箱的三围尺寸。S1, collect the operating parameters and temperature rise test data of the transformer of the same model as the transformer to be tested; the transformer of the same model is a power transformer of the same specification and has been put into operation. The operating parameters and temperature rise test data include the transformer's own parameters, top oil temperature, radiator inlet and outlet temperature, and winding hot spot temperature information. The transformer's own parameters include the transformer coil height and diameter, the length, width, and height of the core from the side yoke, and the three dimensions of the oil tank.
S2，在待测变压器完成铁芯制作与绕组绕制后，按特定规则将若干个光纤光栅温度传感器埋设在变压器的绕组匝间，实时测量绕组各离散位置的温度数据。特定规则为：在变压器绕组顶部以下10％-20％处为局部热点区域，在局部热点区域每饼线圈埋设的光纤光栅温度传感器数量多于其他常规温度区域每饼线圈埋设的光纤光栅温度传感器数量。如图2所示，按该特定规则将多个光纤光栅传感器11埋设在变压器的绕组匝间，实时测量绕组各离散位置的温度数据；其中，绕组共绕制10绕，包括绕组第十饼1、绕组第九饼2、绕组第八饼3、绕组第七饼4、绕组第六饼5、绕组第五饼6、绕组第四饼7、绕组第三饼8、绕组第二饼9、绕组第一饼10。具体地，在局部热点区域每饼埋设2个传感器，在常规温度区域各饼中埋设1个传感器，光纤光栅传感器组成了测量高/低压绕组温度的传感器阵列，高/低压绕组各自对应1条传感器常规温度区域阵列12与1条传感器热点温度区域阵列13，如图3所示，所用光纤光栅传感器直径为3mm，尾纤为聚四氟乙烯材质，采用FC/APC接头，各阵列的接头为阵列接头14。光纤光栅温度传感器的埋设方法为：沿变压器绕组顶部各饼之间的缝隙埋设并固定于绝缘块槽内，将测温通道的尾纤从绕组顶部接入贯通板。S2, after the core manufacturing and winding of the transformer to be tested are completed, several fiber grating temperature sensors are buried between the turns of the transformer winding according to specific rules, and the temperature data of each discrete position of the winding is measured in real time. The specific rule is: 10%-20% below the top of the transformer winding is a local hot spot area, and the number of fiber grating temperature sensors buried per coil in the local hot spot area is greater than the number of fiber grating temperature sensors buried per coil in other conventional temperature areas. As shown in Figure 2, according to the specific rule, multiple fiber grating sensors 11 are buried between the turns of the transformer winding, and the temperature data of each discrete position of the winding is measured in real time; wherein, the winding is wound 10 times in total, including the tenth winding 1, the ninth winding 2, the eighth winding 3, the seventh winding 4, the sixth winding 5, the fifth winding 6, the fourth winding 7, the third winding 8, the second winding 9, and the first winding 10. Specifically, two sensors are buried in each cake in the local hot spot area, and one sensor is buried in each cake in the normal temperature area. The fiber Bragg grating sensor forms a sensor array for measuring the temperature of the high/low voltage windings. The high/low voltage windings each correspond to one sensor normal temperature area array 12 and one sensor hot spot temperature area array 13, as shown in Figure 3. The fiber Bragg grating sensor used has a diameter of 3mm, the pigtail is made of polytetrafluoroethylene, and uses FC/APC connectors. The connectors of each array are array connectors 14. The method of burying the fiber Bragg grating temperature sensor is as follows: bury it along the gap between the cakes at the top of the transformer winding and fix it in the insulating block groove, and connect the pigtail of the temperature measurement channel from the top of the winding to the through plate.
S3，基于实时测量得到的绕组各离散位置的温度数据，结合神经网络算法，预测绕组内部各区域的温度数据，预测变压器绕组各饼的温度分布。具体包括以下步骤：S3, based on the temperature data of each discrete position of the winding obtained by real-time measurement, combined with the neural network algorithm, predict the temperature data of each area inside the winding and predict the temperature distribution of each cake of the transformer winding. Specifically, it includes the following steps:
设x1,x2,...,xn为光纤光栅温度传感器测得的绕组各离散位置的温度数据，作为神经元网络的输入，个数为n；设y1,y2,...,ym为神经元计算后输出的变压器绕组温度预测量，个数为m；wij为输入层第i个神经元与隐含层第j个神经元之间的连接权值，wjk为隐含层第j个神经元与输出层第k个神经元之间的连接权值；Let x 1 ,x 2 ,...,x n be the temperature data of each discrete position of the winding measured by the fiber Bragg grating temperature sensor, as the input of the neural network, the number is n; let y 1 ,y 2 ,...,y m be the predicted values of the transformer winding temperature output after the neuron calculation, the number is m; w ij is the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, w jk is the connection weight between the j-th neuron in the hidden layer and the k-th neuron in the output layer;
则中间隐含层第j个温度输入的加权和为：Then the weighted sum of the jth temperature input in the middle hidden layer is:
对于隐含层神经元，激发函数为：For the hidden layer neurons, the activation function is:
对于隐含层第j个神经元有：For the jth neuron in the hidden layer, we have:
Hj是隐含层第j个神经元的输出，其计算公式如下： Hj is the output of the jth neuron in the hidden layer, and its calculation formula is as follows:
Hj＝f(netj)；(3)Hj＝f(netj); (3)
则输出误差为：The output error is:
l为隐含层神经元总个数。l is the total number of neurons in the hidden layer.
其中，Yk为神经元输出期望，基于所述步骤S1中采集的同型号变压器运行参数与温升试验数据得到；Wherein, Yk is the expected output of the neuron, which is obtained based on the operating parameters and temperature rise test data of the same type of transformer collected in step S1;
基于输出误差，对输出层和隐含层进行修正，如下：Based on the output error, the output layer and hidden layer are corrected as follows:
输出层权值修正：Output layer weight correction:
wjk2＝wjk+ηHjek；(5)w jk2 =w jk +ηH j e k ; (5)
其中，η为学习率，是神经网络的网络参数；wjk2为隐含层第j个神经元与输出层第k个神经元之间连接权值的修正值；Among them, η is the learning rate, which is the network parameter of the neural network; w jk2 is the correction value of the connection weight between the jth neuron in the hidden layer and the kth neuron in the output layer;
隐含层权值修正：Hidden layer weight correction:
其中，wij2为输入层第i个神经元与隐含层第j个神经元之间连接权值的修正值；Where, w ij2 is the correction value of the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer;
基于修正后的输出层权值以及隐含层权值，可得变压器绕组各饼的预测温度分布：Based on the corrected output layer weights and hidden layer weights, the predicted temperature distribution of each cake of the transformer winding can be obtained:
yk是经过神经网络计算后预测的变压器内部绕组温度，将绕组每饼均分为多个区域，对各区域位置进行温度预测；k为变压器绕组各区域的编号，如：将每饼均分为4块区域，第一饼的第一块区域的k＝1，第一饼的第二块区域的k＝2，第一饼的第三块区域的k＝3，第一饼的第四块区域的k＝4；y k is the predicted internal winding temperature of the transformer after neural network calculation. Each winding cake is divided into multiple regions, and the temperature of each region is predicted; k is the number of each region of the transformer winding, such as: each cake is divided into 4 regions, k=1 for the first region of the first cake, k=2 for the second region of the first cake, k=3 for the third region of the first cake, and k=4 for the fourth region of the first cake;
第二饼的第一块区域中k＝5，第二饼的第二块区域中k＝6，第二饼的第三块区域中k＝7，第二饼的第四块区域中k＝8，以此类推。In the first area of the second pie, k=5, in the second area of the second pie, k=6, in the third area of the second pie, k=7, in the fourth area of the second pie, k=8, and so on.
其中，Hj2表示修正后的隐含层第j个神经元， Among them, H j2 represents the jth neuron in the modified hidden layer,
上述算法中，所述神经网络算法用于拟合离散点的温度数据，预测变压器内部绕组各区域的连续温度分布。所述的绕组各区域指的是将绕组各饼均分为多个区域，对各区域位置进行温度预测，通过学习来抽取及逼近输入温度和输出温度的非线性关系。所述绕组各位置的连续温度分布，指将绕组各饼均分为多个区域，对每饼的各区域位置进行温度预测。In the above algorithm, the neural network algorithm is used to fit the temperature data of discrete points and predict the continuous temperature distribution of each area of the transformer internal winding. The winding areas refer to dividing each winding cake into multiple areas, predicting the temperature of each area, and extracting and approximating the nonlinear relationship between input temperature and output temperature through learning. The continuous temperature distribution of each position of the winding refers to dividing each winding cake into multiple areas and predicting the temperature of each area of each cake.
S4，根据S3中获得的变压器绕组各饼温度分布预测值，利用热老化6度法预测变压器的老化速率与剩余寿命。S4, predicting the aging rate and remaining life of the transformer by using the 6-degree thermal aging method according to the predicted value of the temperature distribution of each wafer of the transformer winding obtained in S3.
所述热老化6度法指变压器内部温度每上升6K，老化率增大一倍，基于此，得到各热点温度下的相对老化速率为：The 6-degree thermal aging method means that the aging rate doubles for every 6K increase in the internal temperature of the transformer. Based on this, the relative aging rate at each hot spot temperature is obtained as follows:
V＝2(t-98)/6；(8)V = 2(t-98)/6; (8)
其中t为变压器内部温度，单位是摄氏度℃。Where t is the internal temperature of the transformer in degrees Celsius.
所述变压器剩余寿命利用已损失寿命获取：The remaining life of the transformer is obtained by using the lost life:
其中，L为变压器剩余寿命；S为变压器设计寿命；V为变压器运行在t1～t2时间段内的相对老化率。Wherein, L is the remaining life of the transformer; S is the design life of the transformer; and V is the relative aging rate of the transformer during the period from t 1 to t 2 .
此外，所述的光纤光栅温度传感器埋设位置在绕组绝缘的外部，所测温度为贴近导线的绝缘层的温度。根据传热学的导热机理，铜线或铝线表面和绝缘纸外表面存在温度差异。对此，测量值修正公式如下：In addition, the fiber Bragg grating temperature sensor is buried outside the winding insulation, and the measured temperature is the temperature of the insulation layer close to the conductor. According to the heat conduction mechanism of heat transfer, there is a temperature difference between the surface of the copper wire or aluminum wire and the outer surface of the insulation paper. In this regard, the measurement value correction formula is as follows:
其中，q为绕组表面热流密度；λ为绝缘层导热系数；δ为绝缘层厚度；Treal为温度真实值；Ttest为光纤光栅温度传感器的测量值。Wherein, q is the heat flux density on the winding surface; λ is the thermal conductivity of the insulation layer; δ is the thickness of the insulation layer; T real is the actual temperature value; and T test is the measured value of the fiber Bragg grating temperature sensor.
一方面，本发明通过多组光纤光栅传感器直接测量变压器内部绕组离散点温度，结合神经网络算法，拟合出绕组间连续数据，预测变压器绕组各饼的温度分布，其中所述神经网络算法用于拟合离散点的温度数据，预测变压器内部绕组各区域的连续温度分布，绕组各区域指的是将绕组各饼均分为多个区域，对各区域位置进行温度预测，通过学习来抽取及逼近输入温度和输出温度的非线性关系；另一方面，本发明根据取得的变压器热点温度，利用热老化6度法预测变压器老化速率与剩余寿命；本发明取得的结果利于对变压器载荷状况进行调整，对变压器异常状况进行警告，便于发现异常工况下的变压器，有利于保障电力变压器安全稳定运行，具备推广前景。On the one hand, the present invention directly measures the temperature of discrete points of the transformer internal windings through multiple groups of fiber grating sensors, and combines with a neural network algorithm to fit the continuous data between the windings and predict the temperature distribution of each cake of the transformer winding, wherein the neural network algorithm is used to fit the temperature data of discrete points and predict the continuous temperature distribution of each region of the transformer internal winding. Each region of the winding refers to dividing each cake of the winding into multiple regions, and predicting the temperature of each region position, and extracting and approximating the nonlinear relationship between the input temperature and the output temperature through learning; on the other hand, the present invention predicts the aging rate and remaining life of the transformer based on the obtained hot spot temperature of the transformer using the 6-degree thermal aging method; the results obtained by the present invention are conducive to adjusting the load condition of the transformer, warning the abnormal condition of the transformer, and facilitating the discovery of the transformer under abnormal working conditions, which is conducive to ensuring the safe and stable operation of the power transformer and has a prospect for promotion.
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
在本申请所提供的实施例中，应该理解到，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元可结合为一个单元，一个单元可拆分为多个单元，或一些特征可以忽略等。In the embodiments provided in the present application, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units may be combined into one unit, one unit may be split into multiple units, or some features may be ignored.
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围，其均应涵盖在本发明的权利要求和说明书的范围当中。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078692.8A CN113945299B (en) | 2021-09-15 | 2021-09-15 | Transformer winding temperature distribution and residual life prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078692.8A CN113945299B (en) | 2021-09-15 | 2021-09-15 | Transformer winding temperature distribution and residual life prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113945299A CN113945299A (en) | 2022-01-18 |
| CN113945299B true CN113945299B (en) | 2024-07-02 |
Family
ID=79328441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111078692.8A Active CN113945299B (en) | 2021-09-15 | 2021-09-15 | Transformer winding temperature distribution and residual life prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113945299B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598061A (en) * | 2018-12-03 | 2019-04-09 | 西南交通大学 | A kind of monitoring method of transformer group mean life loss |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101447048B (en) * | 2008-12-30 | 2011-08-03 | 上海发电设备成套设计研究院 | A method and life management system for transformer insulation life prediction |
| CN102096030B (en) * | 2010-12-10 | 2013-04-17 | 西安交通大学 | Method for estimating residual insulation service life of power transformer based on operating data |
| CN103176058A (en) * | 2013-03-27 | 2013-06-26 | 国家电网公司 | Device for measuring transformer oil paper insulation test piece |
| CN103364658A (en) * | 2013-06-28 | 2013-10-23 | 国网电力科学研究院武汉南瑞有限责任公司 | Method for predicting service life of transformer based on fiber grating temperature measurement system |
| CN103376166B (en) * | 2013-06-28 | 2017-06-16 | 山西省电力公司太原供电分公司 | The arrangement and method for embedding of a kind of inside transformer fiber-optical grating temperature sensor |
| CN106874534A (en) * | 2016-12-28 | 2017-06-20 | 国网内蒙古东部电力有限公司检修分公司 | A kind of transformer overload capability assessment method |
| CN206339317U (en) * | 2017-01-10 | 2017-07-18 | 青岛数能电气工程有限公司 | A kind of Transformer Winding temperature on-line monitoring device |
| CN108120521B (en) * | 2017-12-08 | 2020-06-26 | 囯网河北省电力有限公司电力科学研究院 | Transformer winding hot spot temperature prediction method and terminal equipment |
| CN109668651B (en) * | 2019-02-28 | 2024-08-02 | 广东中鹏电气有限公司 | Pre-burying method of fiber bragg grating of transformer and transformer temperature measurement system manufactured by pre-burying method |
| CN110132447A (en) * | 2019-04-17 | 2019-08-16 | 上海电力学院 | A Fiber Bragg Grating-Based On-Line Monitoring System for Hot Spot Temperature of Transformer Windings |
-
2021
- 2021-09-15 CN CN202111078692.8A patent/CN113945299B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598061A (en) * | 2018-12-03 | 2019-04-09 | 西南交通大学 | A kind of monitoring method of transformer group mean life loss |
Non-Patent Citations (1)
| Title |
|---|
| "基于GA-BP 神经网络的变压器绕组热点温度预测研究";王兴桐等;《东北电力技术》;第42卷(第2期);第1.1节、第3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113945299A (en) | 2022-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110083908A (en) | Cable conductor temperature predicting method based on finite element analysis | |
| CN101672699B (en) | Electric cable conductor transient-state temperature determining method and determining device | |
| CN111027187B (en) | Simplified analysis method for transformer multi-physical field winding structure based on thermal parameter equivalence | |
| CN115270622A (en) | Method for predicting transformer hot spot temperature based on numerical calculation and linear regression model | |
| CN106482848B (en) | A method for dynamic temperature acquisition of three-core cable conductor based on M-P generalized inverse | |
| Duan | Real-time hotspot tracing and model analysis of a distributed optical fiber sensor integrated power transformer | |
| CN113343447A (en) | IGBT junction temperature estimation method, system and medium under low voltage ride through working condition | |
| Abdali et al. | Magnetic-thermal analysis of distribution transformer: Validation via optical fiber sensors and thermography | |
| CN109190242B (en) | A method for estimating line impedance in the household section | |
| Srinivasan et al. | Prediction of transformer insulation life with an effect of environmental variables | |
| CN110487844A (en) | A kind of appraisal procedure of power cable insulation layer temperature and failure of insulation | |
| CN114878970B (en) | Analysis method of radial distribution characteristics of transient temperature of latent fault based on arc thermal characteristics | |
| Enescu et al. | Dynamic thermal rating of electric cables: A conceptual overview | |
| CN113945299B (en) | Transformer winding temperature distribution and residual life prediction method | |
| CN111337797A (en) | XLPE power cable main insulation non-uniform thermal aging state evaluation method based on modified Debye model | |
| Zhang et al. | Incipient Fault Detection-Based Active Protection of Photovoltaic DC Integration System | |
| Zhang et al. | An experimental investigation of critical current and current distribution behavior of parallel placed HTS tapes | |
| CN118311489A (en) | Online monitoring system and method of DC bus capacitor bank based on digital twin | |
| CN118862564A (en) | A finite element-based simulation analysis method for temperature field of electric energy metering box | |
| CN118070529A (en) | A method for calculating transient hot spot temperature of transformer | |
| Wang et al. | Thermal Distribution Characteristics Related to the Transformer Fine Structure Predicted by CFD-Based Spline Interpolation | |
| CN117826025A (en) | Method and system for measuring empty load loss, capacity and short circuit impedance of transformer | |
| He et al. | Investigating temperature rise dynamics at hot-spots within dry-Type transformer windings: A comparative analysis across varied loading rates and an extrapolative computational model | |
| CN107908827A (en) | The acquisition methods of transient state temperature rise between a kind of two telegram in reply cables containing delay switch | |
| CN107918697A (en) | The threephase cable transient state temperature rise acquisition methods of skin temperature comb laying are not depended on |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |