JP5387877B2 - Method for estimating the remaining life of oil-filled electrical equipment - Google Patents

Method for estimating the remaining life of oil-filled electrical equipment Download PDF

Info

Publication number
JP5387877B2
JP5387877B2 JP2008068870A JP2008068870A JP5387877B2 JP 5387877 B2 JP5387877 B2 JP 5387877B2 JP 2008068870 A JP2008068870 A JP 2008068870A JP 2008068870 A JP2008068870 A JP 2008068870A JP 5387877 B2 JP5387877 B2 JP 5387877B2
Authority
JP
Japan
Prior art keywords
polymerization
estimation model
oil
average
deterioration index
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
Application number
JP2008068870A
Other languages
Japanese (ja)
Other versions
JP2009222620A (en
Inventor
哲郎 松井
政喜 佐久間
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuji Electric Co Ltd
Original Assignee
Fuji Electric Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fuji Electric Co Ltd filed Critical Fuji Electric Co Ltd
Priority to JP2008068870A priority Critical patent/JP5387877B2/en
Publication of JP2009222620A publication Critical patent/JP2009222620A/en
Application granted granted Critical
Publication of JP5387877B2 publication Critical patent/JP5387877B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
  • Testing Relating To Insulation (AREA)
  • Housings And Mounting Of Transformers (AREA)

Description

本発明は、油入変圧器等の油入電気機器の余寿命を絶縁紙の劣化状態に基づいて推定する方法に関するものである。   The present invention relates to a method for estimating the remaining life of an oil-filled electrical device such as an oil-filled transformer based on the deterioration state of insulating paper.

一般に、油入電気機器に使われている材料としては、銅、アルミニウム等の導電材料、絶縁油や絶縁紙、プレスボード等の絶縁材料、けい素鋼帯の鉄心材料、鉄やステンレス鋼等の構造材料がある。
これらの材料のうち、電気機器内で経年劣化が認められるのは、絶縁油や絶縁紙等の絶縁材料であり、絶縁油については、油劣化防止装置(開放型、空気密封型、窒素密封型等がある)の働きもあって劣化は非常に緩慢であり、重要な特性である絶縁破壊電圧の低下度は小さい。
これに対し、絶縁紙については、経年劣化による絶縁破壊電圧の低下度は小さいが、機械的強度の低下度は大きい(すなわち、紙がぼろぼろになる)。絶縁紙の機械的強度の低下が進行すると、突入電流や外部短絡時に発生する電磁力に起因した機械的ストレスによって絶縁紙に亀裂や損壊が発生し、絶縁破壊を起こす危険性が増大する。
In general, materials used in oil-filled electrical equipment include conductive materials such as copper and aluminum, insulating materials such as insulating oil and paper, pressboard, iron core materials of silicon steel strip, iron and stainless steel, etc. There are structural materials.
Among these materials, it is insulation materials such as insulating oil and insulating paper that are subject to deterioration over time in electrical equipment. For insulating oil, oil deterioration prevention devices (open type, air-sealed type, nitrogen-sealed type) Etc.), the deterioration is very slow and the breakdown voltage, which is an important characteristic, is small.
On the other hand, for insulating paper, the degree of decrease in dielectric breakdown voltage due to aging is small, but the degree of mechanical strength is large (that is, the paper is raged). As the mechanical strength of the insulating paper is lowered, the insulating paper is cracked or broken due to mechanical stress caused by an inrush current or an electromagnetic force generated at the time of an external short circuit, and the risk of causing dielectric breakdown increases.

従って、油入電気機器の寿命は、絶縁紙の機械的強度、特に巻線導体絶縁紙の劣化度合いの影響を強く受ける。つまり、油入電気機器の余寿命とは、巻線導体絶縁紙の絶縁破壊、すなわち、絶縁紙の劣化状態によって決定付けられると考えてよい。   Therefore, the life of the oil-filled electrical device is strongly influenced by the mechanical strength of the insulating paper, particularly the degree of deterioration of the winding conductor insulating paper. That is, it may be considered that the remaining life of the oil-filled electrical device is determined by the dielectric breakdown of the winding conductor insulating paper, that is, the deterioration state of the insulating paper.

絶縁紙は、多数のセルロース分子が重合してできた重合体であり、セルロースを構成する基本分子の数を重合度という。新品のクラフト紙の場合の平均重合度は、約1000であり、この平均重合度は、絶縁紙の劣化によりセルロース分子の鎖が切断されることによって低下していく。例えば、30年使用した油入変圧器では、平均重合度が初期の約40〜60%(平均重合度400〜600)に減少すると言われている。   Insulating paper is a polymer made by polymerizing a large number of cellulose molecules, and the number of basic molecules constituting cellulose is called the degree of polymerization. The average degree of polymerization in the case of new kraft paper is about 1000, and this average degree of polymerization is lowered by breaking the chain of cellulose molecules due to deterioration of the insulating paper. For example, in an oil-filled transformer used for 30 years, the average degree of polymerization is said to decrease to about 40 to 60% of the initial degree (average degree of polymerization of 400 to 600).

また、日本電機工業会規格JEM1463−1993では、1000[kVA]を超える油入変圧器及び油入リアクトルの絶縁紙(コイル絶縁紙)の平均重合度の評価基準を、以下の表1のように定めている。一般的には、この規格に従い、平均重合度が450になると思われる時点を油入変圧器の寿命と定義している。   In addition, in the Japan Electrical Manufacturers' Association standard JEM1463-1993, the evaluation standard of the average degree of polymerization of insulating paper (coil insulating paper) of oil-filled transformers and oil-filled reactors exceeding 1000 [kVA] is as shown in Table 1 below. It has established. In general, according to this standard, the time when the average degree of polymerization is supposed to be 450 is defined as the life of the oil-filled transformer.

Figure 0005387877
Figure 0005387877

しかしながら、稼働中の油入変圧器から絶縁紙を採取することは容易ではなく、一般に絶縁紙の平均重合度や引張り強さを測定することは困難である。
上記の点に鑑み、変圧器内部の採取可能な絶縁物(プレスボード、リード絶縁紙等)の平均重合度や、絶縁紙の平均重合度とも相関性がある分解過程の生成物としてCO+CO量やフルフラール(セルロースの分解過程で生成されるアルデヒドの一種)の量を測定し、これらの絶縁紙劣化指標を用いて劣化診断、余寿命推定を行っている(例えば、電気学会技術報告第922号「経年変圧器の信頼性維持技術の現状と動向」や、電気共同研究第54巻第5号(その1)等を参照)。
However, it is not easy to extract insulating paper from an oil-filled transformer in operation, and it is generally difficult to measure the average degree of polymerization and tensile strength of insulating paper.
In view of the above points, CO 2 + CO as a product of the decomposition process having a correlation with the average degree of polymerization of the insulator (press board, lead insulating paper, etc.) that can be collected inside the transformer and the average degree of polymerization of the insulating paper The amount and the amount of furfural (a kind of aldehyde produced in the process of cellulose decomposition) are measured, and deterioration diagnosis and remaining life estimation are performed using these insulating paper deterioration indicators (for example, IEEJ Technical Report No. 922). No. “Current Status and Trends in Transformer Transformer Reliability Maintenance Technology” and Electric Joint Research Vol. 54, No. 5 (Part 1)).

CO+CO量を測定する方法(以下、単にCO+CO法という)では、油中ガス分析を行い、絶縁紙の最終的な劣化生成物であるCO+CO量から平均重合度を推定して劣化診断を行う。このCO+CO法を用いた油入変圧器の劣化・余寿命診断システムは、例えば特許文献1に記載されている。
これに対し、フルフラール量を測定して平均重合度を推定する方法(以下、単にフルフラール法という)では、絶縁油を脱気処理してもフルフラールの85%が油中に残り、気体中に拡散しないと共に、絶縁紙への吸着率は温度に依存せず約85%と一定であるため、上述したCO+CO法に比べれば高精度な診断が可能であると言われている。このフルフラール法(またはCO+CO法)を用いた油入電気機器の劣化診断方法は、例えば特許文献2に記載されている。
In the method of measuring the amount of CO 2 + CO (hereinafter simply referred to as “CO 2 + CO method”), gas analysis in oil is performed, and the average degree of polymerization is estimated from the amount of CO 2 + CO that is the final degradation product of insulating paper. Perform deterioration diagnosis. An oil-immersed transformer deterioration / remaining life diagnosis system using this CO 2 + CO method is described in Patent Document 1, for example.
On the other hand, in the method of estimating the average degree of polymerization by measuring the amount of furfural (hereinafter simply referred to as the furfural method), 85% of the furfural remains in the oil and diffuses into the gas even if the insulating oil is degassed. In addition, since the adsorption rate to the insulating paper does not depend on the temperature and is constant at about 85%, it is said that highly accurate diagnosis is possible as compared with the above-described CO 2 + CO method. A degradation diagnosis method for oil-filled electrical equipment using this furfural method (or CO 2 + CO method) is described in Patent Document 2, for example.

しかし、CO+CO法、フルフラール法の何れにおいても、推定した平均重合度の値に大きな幅がある。例えば、図4に示すように、測定した油入電気機器のフルフラール量に対して平均重合度残率で約20%の幅があり、これは電気機器の余寿命に換算すると数十年に相当する程度の誤差である。
上記の誤差の発生は油入電気機器の運転状態や設計諸元等の違いにより、フルフラール量や平均重合度の値も影響を受けるためであると考えられる。
However, in both the CO 2 + CO method and the furfural method, the estimated average degree of polymerization has a wide range. For example, as shown in FIG. 4, the average residual degree of polymerization has a width of about 20% with respect to the measured amount of furfural of the oil-filled electrical equipment, which corresponds to several decades when converted to the remaining life of the electrical equipment. It is an error of the grade to do.
The occurrence of the error is considered to be because the amount of furfural and the average degree of polymerization are also affected by differences in the operating state and design specifications of the oil-filled electrical device.

上記のように、CO+CO法、フルフラール法の何れも、油入電気機器の劣化・余寿命診断に当たって精度上、改善の余地がある。これは、これらの方法が基本的に絶縁紙の劣化を表す単一の指標を用いて劣化診断を行っており、運転状態や設計諸元等を総合的に考慮して判断する手法ではないことに起因している。 As described above, both the CO 2 + CO method and the furfural method have room for improvement in terms of accuracy in diagnosing deterioration and remaining life of oil-filled electrical equipment. This is because these methods basically perform deterioration diagnosis using a single index that represents the deterioration of the insulation paper, and are not a method that makes a comprehensive decision based on operating conditions, design specifications, etc. Due to

これに対し、絶縁油中の複数の絶縁紙劣化指標を用いて絶縁紙の平均重合度を推定する油入電気機器の劣化診断方法が、特許文献3によって公知となっている。
この従来技術では、絶縁油中のフルフラール量,CO量,CO量,水分量,酸素量,水素量の各測定値、油入電気機器の運転履歴、保守履歴、及び、設計諸元の全てまたは一部の組み合わせを入力因子群とし、絶縁紙の平均重合度を出力因子として、ニューラルネットワーク等のモデルの同定または学習を行うことにより、平均重合度推定モデルを複数構築し、前記入力因子群を各推定モデルにそれぞれ入力して得られた複数の平均重合度推定値を加工して絶縁紙の平均重合度を推定しており、油入電気機器の運転を停止することなく高精度な劣化診断を可能とするものである。
On the other hand, Patent Document 3 discloses a deterioration diagnosis method for oil-filled electrical equipment that estimates an average degree of polymerization of insulating paper using a plurality of insulating paper deterioration indexes in insulating oil.
In this prior art, all measured values of furfural amount, CO 2 amount, CO amount, moisture amount, oxygen amount, hydrogen amount in insulating oil, operation history of oil-filled electrical equipment, maintenance history, and design specifications are all included. Alternatively, a plurality of average polymerization degree estimation models are constructed by identifying or learning a model such as a neural network by using some combinations as input factor groups and using the average polymerization degree of insulating paper as an output factor. The average degree of polymerization of insulating paper is estimated by processing multiple average degree of polymerization estimates obtained by inputting each to each estimation model, and highly accurate deterioration without stopping the operation of oil-filled electrical equipment Diagnosis is possible.

特開2004−55858号公報(段落[0017]〜[0019]、図1,図3等)Japanese Patent Laying-Open No. 2004-55858 (paragraphs [0017] to [0019], FIG. 1, FIG. 3, etc.) 特開平7−272939号公報(段落[0037]〜[0042]、図3,図4等)Japanese Patent Laid-Open No. 7-272939 (paragraphs [0037] to [0042], FIG. 3, FIG. 4 etc.) 特開2006−308515号公報(段落[0031]〜[0043],図1,図5等)Japanese Patent Laying-Open No. 2006-308515 (paragraphs [0031] to [0043], FIG. 1, FIG. 5, etc.)

しかしながら、特許文献3に係る従来技術は、現時点(データの測定時点)における絶縁油中の各種劣化指標、運転環境(負荷率、稼働年数等)を用いて現時点の平均重合度を推定し、現在の運転環境がそのまま将来にわたって不変であることを前提として診断する方法である。
このため、負荷設備の増設や系統構成の変更、年月の経過等によって運転環境が変化した場合には、油入電気機器の高精度な劣化診断、余寿命推定が困難になるという問題があった。
そこで本発明の解決課題は、将来の運転環境の変化を考慮して絶縁紙劣化指標を推定し、これに基づいた平均重合度推定値を用いることによって油入電気機器の余寿命を高精度に推定可能とした余寿命推定方法を提供することにある。
However, the conventional technique according to Patent Document 3 estimates the average degree of polymerization at the present time using various deterioration indexes in the insulating oil at the present time (data measurement time) and the operating environment (load factor, operation years, etc.), It is a method of diagnosing on the assumption that the driving environment of the vehicle will remain unchanged in the future.
For this reason, when the operating environment changes due to the addition of load equipment, changes in system configuration, or the passage of time, there is a problem that it is difficult to perform highly accurate deterioration diagnosis and remaining life estimation of oil-filled electrical equipment. It was.
Therefore, the problem to be solved by the present invention is to estimate the insulation paper deterioration index in consideration of future changes in the operating environment, and to use the estimated average polymerization degree based on this to increase the remaining life of oil-filled electrical equipment with high accuracy. An object of the present invention is to provide a remaining life estimation method that can be estimated.

上記課題を解決するため、請求項1に係る発明は、油入電気機器の絶縁油に含まれる劣化指標成分量を用いて油入電気機器の絶縁紙の平均重合度を推定し、この平均重合度推定値を用いて油入電気機器の余寿命を推定する方法において、
実績データとして、少なくとも前記劣化指標成分量と電気機器の稼働年数、負荷率等の運転環境とが入力され、前記平均重合度推定値を出力する平均重合度推定モデルを作成する第1ステップと、
実績データとして、少なくとも前記運転環境が入力され、前記劣化指標成分量を出力する絶縁紙劣化指標推定モデルを作成する第2ステップと、
前記平均重合度推定モデルの構築に用いた入力データと同種の測定データを前記平均重合度推定モデルに入力して、現時点における平均重合度を推定する第3ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の将来予測される運転環境データを前記絶縁紙劣化指標推定モデルに入力して、将来想定される運転環境における劣化指標成分量を推定する第4ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の現在の運転環境データを前記絶縁紙劣化指標推定モデルに入力して、現時点における劣化指標成分量を推定し、この推定値と現時点における劣化指標成分量の実測値とから求めた補正値を用いて、前記第4ステップにより推定した劣化指標成分量を補正する第5ステップと、
ステップにより補正した劣化指標成分量を用いて、将来想定される運転環境における平均重合度を前記平均重合度推定モデルにより推定する第ステップと、
ステップにより推定した、将来想定される運転環境における平均重合度から寿命低下率を求め、この寿命低下率と現時点における平均重合度推定値とを用いて電気機器の余寿命を推定する第ステップと、を備えたものである。
In order to solve the above-mentioned problem, the invention according to claim 1 estimates the average degree of polymerization of insulating paper of oil-filled electrical equipment using the amount of deterioration index component contained in the insulating oil of oil-filled electrical equipment, and this average polymerization. In the method of estimating the remaining life of oil-filled electrical equipment using the degree estimate,
A first step of creating an average polymerization degree estimation model that inputs at least the deterioration index component amount and the operating environment of the electric equipment, the operating environment such as the load factor, and outputs the average polymerization degree estimation value as actual data;
A second step of creating an insulating paper deterioration index estimation model that outputs at least the operating environment as output data and outputs the deterioration index component amount;
A third step of inputting the measurement data of the same type as the input data used for constructing the average polymerization degree estimation model to the average polymerization degree estimation model, and estimating a current average polymerization degree;
Estimate the amount of degradation index components in the expected operating environment by inputting the predicted future operating environment data of the same type as the input data used to construct the insulating paper degradation index estimation model into the insulating paper degradation index estimation model. And a fourth step
The current operating environment data of the same type as the input data used for the construction of the insulation paper deterioration index estimation model is input to the insulation paper deterioration index estimation model to estimate the current deterioration index component amount. A fifth step of correcting the deterioration index component amount estimated in the fourth step using a correction value obtained from the actual measurement value of the deterioration index component amount in
A sixth step of estimating an average degree of polymerization in a driving environment assumed in the future using the average degree of polymerization estimation model using the deterioration index component amount corrected in the fifth step;
6 was estimated by step, determine the lifetime reduction ratio from an average polymerization degree of driving environment envisioned future, seventh to estimate the remaining life of the electrical device using the average degree of polymerization estimate in this lifetime reduction rate and the current And a step.

請求項2に係る発明は、油入電気機器の絶縁油に含まれる劣化指標成分量を用いて油入電気機器の絶縁紙の平均重合度を推定し、この平均重合度推定値を用いて油入電気機器の余寿命を推定する方法において、
実績データとして、少なくとも前記劣化指標成分量と電気機器の稼働年数、負荷率等の運転環境とが入力され、前記平均重合度推定値を出力する平均重合度推定モデルを作成する第1ステップと、
実績データとして、少なくとも前記運転環境が入力され、前記劣化指標成分量を出力する絶縁紙劣化指標推定モデルを作成する第2ステップと、
前記平均重合度推定モデルの構築に用いた入力データと同種の測定データを前記平均重合度推定モデルに入力して、将来の任意時点における平均重合度を推定する第3ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の将来予測される運転環境データを前記絶縁紙劣化指標推定モデルに入力して、将来の任意時点以降において想定される運転環境における劣化指標成分量を推定する第4ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の現在の運転環境データを前記絶縁紙劣化指標推定モデルに入力して、現時点における劣化指標成分量を推定し、この推定値と現時点における劣化指標成分量の実測値とから求めた補正値を用いて、前記第4ステップにより推定した劣化指標成分量を補正する第5ステップと、
ステップにより補正した劣化指標成分量を用いて、将来の任意時点以降において想定される運転環境における平均重合度を前記平均重合度推定モデルにより推定する第ステップと、
ステップにより推定した、将来の任意時点以降において想定される運転環境における平均重合度から寿命低下率を求め、この寿命低下率と将来の任意時点における平均重合度推定値とを用いて電気機器の余寿命を推定する第ステップと、を備えたものである。
The invention according to claim 2 estimates the average degree of polymerization of the insulating paper of the oil-filled electrical equipment using the amount of deterioration index component contained in the insulating oil of the oil-filled electrical equipment, and uses this average degree of polymerization estimate to estimate the oil In the method of estimating the remaining life of the input electrical equipment,
A first step of creating an average polymerization degree estimation model that inputs at least the deterioration index component amount and the operating environment of the electric equipment, the operating environment such as the load factor, and outputs the average polymerization degree estimation value as actual data;
A second step of creating an insulating paper deterioration index estimation model that outputs at least the operating environment as output data and outputs the deterioration index component amount;
A third step of inputting the measurement data of the same type as the input data used to construct the average polymerization degree estimation model to the average polymerization degree estimation model, and estimating the average polymerization degree at an arbitrary future time point;
Deterioration in the operating environment assumed after an arbitrary time in the future by inputting into the insulating paper deterioration index estimation model the same predicted future operating environment data as the input data used for the construction of the insulating paper deterioration index estimation model A fourth step of estimating the index component amount;
The current operating environment data of the same type as the input data used for the construction of the insulation paper deterioration index estimation model is input to the insulation paper deterioration index estimation model to estimate the current deterioration index component amount. A fifth step of correcting the deterioration index component amount estimated in the fourth step using a correction value obtained from the actual measurement value of the deterioration index component amount in
A sixth step of estimating an average degree of polymerization in an operating environment assumed after an arbitrary time in the future using the average degree of polymerization estimation model using the deterioration index component amount corrected in the fifth step;
The life reduction rate is obtained from the average degree of polymerization in the operating environment assumed after the arbitrary time in the future estimated by the sixth step, and the electrical equipment is obtained by using this life reduction rate and the estimated average degree of polymerization at the arbitrary time in the future. A seventh step of estimating the remaining life of

請求項3に係る発明は、請求項1または2に記載した油入機器の余寿命推定方法において、前記絶縁紙劣化指標推定モデルとして、前記電気機器の稼働年数及び負荷率を入力として前記劣化指標成分量を出力するニューラルネットワークを用いるものである。   The invention according to claim 3 is the method for estimating the remaining life of an oil-filled device according to claim 1 or 2, wherein the deterioration index is input as the insulation paper deterioration index estimation model using the operating years and load factor of the electric device as inputs. A neural network that outputs component amounts is used.

請求項4に係る発明は、請求項1または2に記載した油入機器の余寿命推定方法において、前記絶縁紙劣化指標推定モデルとして、前記電気機器の稼働年数及び負荷率が類似した複数の事例データの平均値を用いて劣化指標成分量を推定するものである。   The invention according to claim 4 is the method for estimating the remaining life of the oil-filled device according to claim 1 or 2, wherein the insulation paper deterioration index estimation model is a plurality of cases where the operating years and load factor of the electrical device are similar. The deterioration index component amount is estimated using the average value of the data.

本発明によれば、将来想定される運転環境の変化を考慮してフルフラール量等の絶縁紙劣化指標を推定し、これに基づいた平均重合度推定値を用いるため、現時点の運転環境のみを考慮している従来技術に比べて、油入電気機器の余寿命を高精度に推定することができる。   According to the present invention, an insulation paper deterioration index such as a furfural amount is estimated in consideration of a change in the expected operating environment in the future, and an average polymerization degree estimation value based on this is used, so only the current operating environment is considered. Compared to the conventional technology, the remaining life of the oil-filled electrical device can be estimated with high accuracy.

以下、図に沿って本発明の実施形態を説明する。
まず、図1は本実施形態の余寿命推定方法を示すフローチャートである。この実施形態では、平均重合度推定モデルのほかに絶縁紙劣化指標推定モデルを導入し、これらの推定モデルを用いて油入電気機器の余寿命を推定するものである。
なお、上記各推定モデルには、ニューラルネットワーク、重回帰式、アンサンブル処理手段(単純平均値や加重平均値等を求める手段)等を用いることが可能であるが、以下では主としてニューラルネットワークを用いる場合について説明する。
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
First, FIG. 1 is a flowchart showing a remaining life estimation method of the present embodiment. In this embodiment, an insulating paper deterioration index estimation model is introduced in addition to the average polymerization degree estimation model, and the remaining life of the oil-filled electrical device is estimated using these estimation models.
For each estimation model, a neural network, multiple regression equation, ensemble processing means (means for obtaining a simple average value, a weighted average value, etc.), etc. can be used. Will be described.

次に、本実施形態に係る余寿命推定方法を図1に示すステップごとに説明する。
(1)過去の実績データ収集ステップ(S1)
油入電気機器の絶縁紙の平均重合度推定モデル及び絶縁紙劣化指標推定モデルを構築するために、ニューラルネットワークの学習データとして、油入電気機器の実績データを収集する。実績データの種類としては、絶縁油を分析して得られる各種の絶縁紙劣化指標成分量(例えば、フルフラール量、CO+CO量、水分量、酸素量、水素量等であり、単に劣化指標ともいう)、当該電気機器の運転環境(例えば、稼働年数、負荷率等)、当該電気機器の設計諸元(例えば、絶縁油劣化防止方式、冷却方式、絶縁紙の量、絶縁油の量等)、及び、絶縁紙の平均重合度である。
また、絶縁油が交換されている場合や脱気処理が行われている場合には、上記の各種劣化指標を補正する必要があるため、絶縁油の交換履歴、脱気処理履歴等の情報も必要になる。
Next, the remaining life estimation method according to the present embodiment will be described for each step shown in FIG.
(1) Past performance data collection step (S1)
In order to construct an average polymerization degree estimation model and insulation paper deterioration index estimation model of insulating paper of oil-filled electrical equipment, actual data of oil-filled electrical equipment is collected as learning data of a neural network. The types of actual data include various insulating paper deterioration index component amounts (for example, furfural amount, CO 2 + CO amount, moisture amount, oxygen amount, hydrogen amount, etc.) obtained by analyzing insulating oil. ), Operating environment of the electrical equipment (for example, operating years, load factor, etc.), design specifications of the electrical equipment (for example, insulation oil deterioration prevention method, cooling method, amount of insulating paper, amount of insulating oil, etc.) And the average degree of polymerization of the insulating paper.
In addition, when the insulating oil has been replaced or when deaeration processing is being performed, it is necessary to correct the various deterioration indicators described above, so information such as insulating oil replacement history and deaeration processing history is also available. I need it.

(2)平均重合度推定モデルの構築ステップ(S2)
ステップS1により収集した実績データを用いて、平均重合度推定モデルを構築する。実績データのうち、平均重合度をニューラルネットワークの出力因子として用い、その他の因子を入力因子として用いる。
(2) Step of constructing average polymerization degree estimation model (S2)
An average polymerization degree estimation model is constructed using the result data collected in step S1. Of the actual data, the average degree of polymerization is used as an output factor of the neural network, and other factors are used as input factors.

(3)絶縁紙劣化指標推定モデルの構築ステップ(S3)
ステップS1により収集した実績データを用いて、絶縁紙劣化指標推定モデルを構築する。実績データのうち、前述した各種劣化指標をニューラルネットワークの出力因子として用い、運転環境(例えば、稼働年数、負荷率)を入力因子として用いる。
(3) Step of constructing an insulation paper degradation index estimation model (S3)
An insulation paper deterioration index estimation model is constructed using the actual data collected in step S1. Among the performance data, the above-described various deterioration indexes are used as output factors of the neural network, and the operating environment (for example, operation years, load factor) is used as the input factor.

(4)診断対象の測定データ入力ステップ(S4)
診断対象の油入電気機器について、前記ステップS2で用いた入力因子、具体的には、絶縁油を分析して得られる各種劣化指標、当該電気機器の運転環境、設計諸元を、測定データとして学習済みの平均重合度推定モデルに入力する。
(4) Measurement data input step for diagnosis (S4)
For the oil-filled electrical equipment to be diagnosed, the input factors used in step S2, specifically, the various deterioration indicators obtained by analyzing the insulating oil, the operating environment of the electrical equipment, and the design specifications are used as measurement data. Input into the trained average polymerization degree estimation model.

(5)平均重合度推定ステップ(S5)
ステップS4で入力したデータに対応する現時点の絶縁紙の平均重合度を、平均重合度推定モデルにより推定する。
ここで、図2は、時間軸に対する平均重合度の推定値の変化を示す概念的なグラフである。図2では、油入電気機器の運転開始時における絶縁紙の平均重合度(初期重合度)Dp0を1000とし、本ステップS5により得た現時点における平均重合度推定値をD(例えば600)にて示してある。
(5) Average polymerization degree estimation step (S5)
The current average degree of polymerization of the insulating paper corresponding to the data input in step S4 is estimated using an average degree of polymerization estimation model.
Here, FIG. 2 is a conceptual graph showing a change in the estimated value of the average degree of polymerization with respect to the time axis. In Figure 2, the average degree of polymerization of the insulating paper at the start of the operation oil-filled electrical apparatus (initial degree of polymerization) D p0 and 1000, an average degree of polymerization estimates at the present time obtained by the present step S5 D p (e.g. 600) Is shown.

(6)現在の運転環境における余寿命推定ステップ(S6)
ステップS5で得られた現時点の平均重合度推定値から、当該電気機器の余寿命を推定する。
絶縁紙の平均重合度(初期状態で1000)は絶縁紙の劣化に伴って徐々に減少していき、平均重合度が基準値(JEM1463−1993では450)に達した時点が絶縁紙すなわち電気機器の寿命と定義されている。
絶縁紙の平均重合度から電気機器の寿命または余寿命を推定する方法は、例えば、参考文献「電気共同研究第54巻第5号(その1):油入変圧器の保守管理」に記載されている。その詳細は省略するが、数式1を用いて寿命低下率rを算出し、この寿命低下率rを用いて現時点から平均重合度が450になるまでの年数を算出すれば、それが余寿命となる。
[数式1]
=Dp0(1−r)
ただし、
:運転開始からn年後の平均重合度推定値
p0:初期の平均重合度
r:寿命低下率
(6) Remaining life estimation step in the current operating environment (S6)
From the current average degree of polymerization estimated value obtained in step S5, the remaining life of the electric device is estimated.
The average degree of polymerization of the insulating paper (1000 in the initial state) gradually decreases as the insulating paper deteriorates, and when the average degree of polymerization reaches the reference value (450 in JEM1463-1993), the insulating paper, that is, the electric equipment Is defined as the lifetime of
A method for estimating the life or remaining life of electrical equipment from the average degree of polymerization of insulating paper is described in, for example, the reference “Electrical Joint Research Vol. 54, No. 5 (Part 1): Maintenance Management of Oil-filled Transformers” ing. Although details thereof are omitted, if the life reduction rate r is calculated using Equation 1 and the number of years until the average degree of polymerization reaches 450 from the present time using this life reduction rate r, it is determined that the remaining life is Become.
[Formula 1]
D p = D p0 (1-r) n
However,
D p : Estimated average degree of polymerization after n years from the start of operation D p0 : Initial average degree of polymerization r: Life reduction rate

仮に、現時点が運転開始から20年経過している(n=20)とし、ステップS5により得られた現時点の平均重合度推定値Dが600である時、数式1による以下の演算によって寿命低下率rを算出することができる。
600=1000(1−r)20
r≒0.025
つまり、図2において、初期の平均重合度Dp0(=1000)が寿命低下率r(≒0.025)で徐々に減少していき、n(=20)年経過後の現時点において推定される平均重合度Dが600になる。図2における特性線P1は、初期の平均重合度Dp0(=1000)の点と現時点における平均重合度Dが600の点とにより決定される。
Assuming the present time has passed 20 years since the start of operation (n = 20), when the average polymerization degree of the estimated value D p of current obtained by the step S5 is 600, shorter service life by the following calculation by Equation 1 The rate r can be calculated.
600 = 1000 (1-r) 20
r≈0.025
That is, in FIG. 2, the initial average degree of polymerization D p0 (= 1000) gradually decreases with the life reduction rate r (≈0.025), and is estimated at the present time after n (= 20) years. The average degree of polymerization Dp is 600. The characteristic line P1 in FIG. 2 is determined by the point of the initial average degree of polymerization D p0 (= 1000) and the point at which the current average degree of polymerization D p is 600.

次に、この寿命低下率r(≒0.025)が今後も一定であると仮定して、数式1により、平均重合度が寿命レベル、つまり450になるまでの年数(運転開始からの経過年数)nを求める。すなわち、特性線P1が平均重合度450の線と交差する時の経過年数nを求めるものである。
数式1によれば、
450≒1000(1−0.025)
であるから、n≒31となり、図示するように、電気機器の運転開始から約31年後(現時点から約11年後)に寿命を迎えることになる。
なお、数式1に現時点の平均重合度推定値(=600)を適用する場合には、現時点から平均重合度が寿命レベルになるまでの年数をn’とすると、
450≒600(1−0.025)n’
により、n’≒11となる。
Next, assuming that the life reduction rate r (≈0.025) will remain constant in the future, the number of years until the average degree of polymerization reaches the life level, that is, 450 (the number of years elapsed from the start of operation) according to Equation 1. ) Find n. That is, the number of years elapsed n when the characteristic line P1 intersects the line having an average degree of polymerization of 450 is obtained.
According to Equation 1,
450≈1000 (1-0.025) n
Therefore, n≈31, and, as shown in the figure, the life is reached about 31 years after the start of operation of the electric equipment (about 11 years after the present time).
In addition, when applying the present average degree of polymerization estimated value (= 600) to Equation 1, when n ′ is the number of years from the present time until the average degree of polymerization reaches the lifetime level,
450≈600 (1-0.025) n ′
Therefore, n′≈11.

(7)絶縁紙劣化指標推定値の補正値計算ステップ(S7)
次に、ステップS3により構築した絶縁紙劣化指標推定モデルに、測定データとして現在の運転環境(稼働年数、負荷率)を入力して絶縁紙劣化指標を推定する。そして、この推定値を、実測した各種の劣化指標と比較することにより、劣化指標推定値の補正値を計算する。
(7) Insulating paper deterioration index estimated value correction value calculation step (S7)
Next, the current operating environment (the number of years of operation and the load factor) is input as measurement data to the insulating paper deterioration index estimation model constructed in step S3 to estimate the insulating paper deterioration index. Then, the correction value of the deterioration index estimated value is calculated by comparing this estimated value with various actually measured deterioration indexes.

以下、本ステップの内容を、絶縁紙劣化指標であるフルフラール量を例に挙げて具体的に説明する。
ステップS3により構築した絶縁紙劣化指標推定モデルは、運転環境として稼働年数、負荷率を入力としてフルフラール量を出力するモデルであるが、勿論、入力因子はこれらの2種類に限らず、当該電気機器の設計諸元(例えば、絶縁油劣化防止方式、冷却方式、絶縁紙の量、絶縁油の量等)等の、絶縁紙劣化指標に影響を与える因子を用いても良い。
本ステップでは、まず、絶縁紙劣化指標推定モデルに上記の稼働年数、負荷率等を入力し、現時点におけるフルフラール量を推定する。
Hereinafter, the contents of this step will be specifically described by taking the amount of furfural as an insulating paper deterioration index as an example.
The insulation paper deterioration index estimation model constructed in step S3 is a model that outputs the fullfural amount with the operating years and the load factor as inputs as the operating environment. Of course, the input factor is not limited to these two types, and the electric equipment Factors that affect the insulating paper deterioration index such as the design specifications (for example, the insulating oil deterioration prevention method, the cooling method, the amount of insulating paper, the amount of insulating oil, etc.) may be used.
In this step, first, the years of operation, the load factor, etc. are input to the insulating paper deterioration index estimation model, and the amount of furfural at the present time is estimated.

フルフラール量に関する絶縁紙劣化指標推定モデルを関数fで表すと、数式2となる。
[数式2]
=f(Y,LF,・・・)
ただし、
:現時点のフルフラール量推定値
:現時点の稼働年数
LF:現時点の負荷率
When the insulating paper deterioration index estimation model regarding the amount of furfural is expressed by a function f, Formula 2 is obtained.
[Formula 2]
F 0 = f (Y 0 , LF 0 ,...)
However,
F 0 : Estimated value of furfural amount at present Y 0 : Years of operation at present LF 0 : Load factor at present

ここで、現時点におけるフルフラール量の実測値をFとすると、例えば、以下の数式3または数式4により、絶縁紙劣化指標としてのフルフラール量の推定値の補正値(補正量または補正率)を求めることができる。
[数式3]
補正量=F−F
[数式4]
補正率=F/F
ここでは、絶縁紙劣化指標としてフルフラール量を例に挙げて説明したが、平均重合度推定モデルにおいて入力因子として用いる他の劣化指標についても、同様にして推定値の補正値を求める。
なお、関数fの精度が高く、フルフラール量の実測値Fが推定値Fと等しい場合には、数式3の補正量がゼロ、数式4の補正率が1となり、言い換えれば補正を行う必要はない。
Here, when the actual measured value of the furfural amount at present is F, for example, the correction value (correction amount or correction rate) of the estimated value of the furfural amount as an insulating paper deterioration index is obtained by the following Equation 3 or Equation 4. Can do.
[Formula 3]
Correction amount = F−F 0
[Formula 4]
Correction rate = F / F 0
Here, the furfural amount has been described as an example of the insulating paper deterioration index, but correction values of estimated values are similarly obtained for other deterioration indices used as input factors in the average polymerization degree estimation model.
When the accuracy of the function f is high and the measured value F of the furfural amount is equal to the estimated value F 0 , the correction amount of Equation 3 is zero and the correction rate of Equation 4 is 1, in other words, it is necessary to perform correction. Absent.

ここで、絶縁紙劣化指標推定モデルとしては、前述したニューラルネットワークを用いる他に、データベースに蓄積された事例を用いて類似したデータの平均値を用いる方法が考えられる。
すなわち、稼働年数Y、負荷率LFを検索キーとして、Y±x年、かつLF±y%の範囲で該当するフルフラール量のデータをデータベースから抽出し、稼働年数Y年、負荷率LF%に類似したフルフラール量のデータを複数得る。そして、これらの抽出されたデータの平均値を計算し、これを現在の運転環境に対応したフルフラール量Fとして推定する。なお、上記x年、y%は任意に設定する。
データベースから抽出された類似データのフルフラール量FをF,F,F,……,Fとすると、Fは数式5によって求めることができる。
Here, as the insulation paper deterioration index estimation model, in addition to using the above-described neural network, a method using an average value of similar data using examples stored in a database can be considered.
That is, using the operation years Y 0 and the load factor LF 0 as search keys, the data of the corresponding fullfural amount in the range of Y 0 ± x years and LF 0 ± y% is extracted from the database, and the operation years Y 0 years, load A plurality of furfural amount data similar to the rate LF 0 % is obtained. Then, the average value of these extracted data is calculated, and this is estimated as the furfural amount F 0 corresponding to the current operating environment. The x year and y% are arbitrarily set.
If the furfural amount F i of the similar data extracted from the database is F 1 , F 2 , F 3 ,..., F n , F 0 can be obtained by Equation 5.

Figure 0005387877
Figure 0005387877

(8)将来運転環境(将来想定される運転環境)での絶縁紙劣化指標推定ステップ(S8)
ステップS3により構築した絶縁紙劣化指標推定モデルと、ステップS7で得た補正値とを用いて、将来運転環境における絶縁紙劣化指標を推定する。
前述の通り、フルフラール量に関する絶縁紙劣化指標推定モデルを関数fで表すと、以下の数式6または数式7によって将来運転環境におけるフルフラール量を推定することができる。
[数式6]
=f(Y,L,・・・)+補正量
[数式7]
=f(Y,L,・・・)×補正率
ただし、
:将来のフルフラール量推定値
:将来の稼働年数
:将来の負荷率
(8) Insulating paper deterioration index estimation step in the future operating environment (presumed operating environment) (S8)
Using the insulating paper deterioration index estimation model constructed in step S3 and the correction value obtained in step S7, the insulating paper deterioration index in the future operating environment is estimated.
As described above, when the insulating paper deterioration index estimation model related to the furfural amount is expressed by the function f, the furfural amount in the future operating environment can be estimated by the following Equation 6 or Equation 7.
[Formula 6]
F f = f (Y f , L f ,...) + Correction amount [Formula 7]
F f = f (Y f , L f ,...) × correction rate where
F f : Estimated value of future furfural amount Y f : Future operation years L f : Future load factor

数式6または数式7によれば、将来のフルフラール量Fについては、前述した数式2のように絶縁紙劣化指標推定モデルである関数fのみによって推定するのではなく、フルフラール量の推定値と実測値とのずれに基づく補正値(補正量または補正率)をも考慮して推定することを意味している。
ここでは、絶縁紙劣化指標としてフルフラール量を例に挙げて説明したが、平均重合度推定モデルにおいて入力因子として用いる他の劣化指標についても、同様に将来運転環境における成分量を推定する。
According to Equation 6 or Equation 7, the future furfural amount F f is not estimated only by the function f which is an insulating paper deterioration index estimation model as in Equation 2 described above, but the estimated value and actual measurement of the furfural amount. This means that the estimation is performed in consideration of a correction value (correction amount or correction rate) based on a deviation from the value.
Here, the furfural amount has been described as an example of the insulating paper deterioration index, but the component amount in the future operating environment is similarly estimated for other deterioration indexes used as input factors in the average polymerization degree estimation model.

(9)将来運転環境での平均重合度推定ステップ(S9)
将来の運転環境と、ステップS8により推定した将来運転環境における絶縁紙劣化指標と、当該電気機器の設計諸元等を平均重合度推定モデルに入力し、将来運転環境での平均重合度を算出する。
(9) Step of estimating average polymerization degree in the future operating environment (S9)
The future operating environment, the insulation paper deterioration index in the future operating environment estimated in step S8, the design specifications of the electric device, etc. are input to the average polymerization degree estimation model, and the average degree of polymerization in the future operating environment is calculated. .

(10)将来運転環境での余寿命推定ステップ(S10)
数式8を用いて、ステップS9により推定した将来運転環境での平均重合度から寿命低下率rを求め、この寿命低下率rを用いて余寿命を推定する。
[数式8]
Pf=DP0(1−r
ただし、
Pf:ステップS9により推定した将来の運転環境での平均重合度
p0:初期の平均重合度
:将来の運転環境における寿命低下率
(10) Remaining life estimation step in future operating environment (S10)
Using Equation 8, determine the lifetime reduction rate r f from the average degree of polymerization in the future operation environment estimated by the step S9, the estimated remaining life by using the lifetime reduction rate r f.
[Formula 8]
D Pf = D P0 (1-r f ) n
However,
D Pf : Average degree of polymerization in the future operating environment estimated in step S9 D p0 : Initial average degree of polymerization r f : Life reduction rate in the future operating environment

ここで、数式8は、初期の平均重合度Dp0と、n年経過後の将来運転環境における平均重合度DPfとが与えられれば、寿命低下率rが求められることを示しており、例えば、経過年数nを20年(すなわち現時点)とすると、図2における特性線P2と現時点の時間軸との交点の平均重合度DPfが、ステップS9により推定した将来運転環境での平均重合度となる。
従って、例えば、ステップS9により推定した将来運転環境での平均重合度DPfを700、経過年数nを20年として数式8を計算すると、
700=1000(1−r20
≒0.018
となり、将来運転環境における寿命低下率rを求めることができる。
Here, Formula 8 shows that the life reduction rate r f is obtained if the initial average degree of polymerization D p0 and the average degree of polymerization D Pf in the future operating environment after elapse of n years are given, For example, if the elapsed time n is 20 years (that is, the current time), the average degree of polymerization DPf at the intersection of the characteristic line P2 in FIG. 2 and the current time axis is the average degree of polymerization in the future operating environment estimated in step S9. It becomes.
Therefore, for example, when the average degree of polymerization D Pf in the future operating environment estimated in step S9 is 700, and the elapsed time n is 20 years, Equation 8 is calculated.
700 = 1000 (1-r f ) 20
r f ≈0.018
Thus, the life reduction rate r f in the future operating environment can be obtained.

次に、現時点の平均重合度推定値D(=600)から、上記寿命低下率rにより平均重合度が減少していくものと仮定して、寿命レベルになる時点(平均重合度が450になる時点)までの年数(現時点からの経過年数)n’を数式9によって求める。
[数式9]
450≒600(1−0.018)n’
つまり、前記特性線P2と寿命低下率rが等しい図2における特性線P2’と平均重合度が450となる線との交点の、現時点からの経過年数n’を求める。
数式9を解くと、n’≒16となるから、現時点において余寿命n’は約16年、つまり運転開始からの寿命は約36年となる。
Next, it is assumed that the average degree of polymerization decreases from the current average degree of polymerization estimated value D p (= 600) according to the lifetime reduction rate r f (the average degree of polymerization is 450). N ′ (number of years since the present time) n ′ is obtained by Equation 9.
[Formula 9]
450≈600 (1-0.018) n ′
That is, the elapsed number of years n ′ from the present time at the intersection of the characteristic line P2 ′ in FIG. 2 having the same life reduction rate r f and the characteristic line P2 and the line having an average degree of polymerization of 450 is obtained.
Solving Equation 9, since n′≈16, the remaining life n ′ is about 16 years at the present time, that is, the life from the start of operation is about 36 years.

(11)余寿命比較ステップ(S11)
ステップS6により推定した余寿命n’は約11年であったが、将来運転環境を考慮した絶縁紙劣化指標に基づいてステップS10により推定した結果、余寿命n’は約16年となった。すなわち、将来運転環境の変化を考慮に入れると、余寿命が5年ほど延びることが判る。
(11) Remaining life comparison step (S11)
The remaining life n ′ estimated in step S6 was about 11 years, but as a result of estimation in step S10 based on the insulating paper deterioration index considering the future operating environment, the remaining life n ′ was about 16 years. That is, it is understood that the remaining life is extended by about 5 years when the change of the future operating environment is taken into consideration.

なお、図2における特性線P3は、将来の任意の時点(a年後)以降において想定される運転環境を考慮してステップS8により劣化指標を推定し、この劣化指標推定値を用いてステップS9により平均重合度推定値Dpaを求め、更にステップS10により余寿命を推定するための特性線である。
このように、現時点だけでなく将来の任意の時点以降において想定される運転環境を考慮して劣化指標及び平均重合度を推定し、余寿命の推定を行っても良い。
Note that the characteristic line P3 in FIG. 2 estimates the deterioration index in step S8 in consideration of the operation environment assumed after an arbitrary future time point (after a year), and uses the estimated deterioration index value in step S9. Is a characteristic line for obtaining the average degree of polymerization estimated value Dpa by the above and further estimating the remaining life in step S10.
In this way, the remaining life may be estimated by estimating the deterioration index and the average degree of polymerization in consideration of not only the present time but also the future operating environment assumed at any future time.

また、本実施形態により推定した余寿命をそのまま最終的な結論とするのではなく、複数の時点で本実施形態により推定した余寿命の平均値を求めたり、過去の時点における平均重合度の推定値を始点とした時の余寿命の傾向を考慮する等の方法により、余寿命推定値を補正して最終的な結論としても良い。   In addition, the remaining life estimated by the present embodiment is not used as a final conclusion as it is, but an average value of remaining lives estimated by the present embodiment at a plurality of time points is obtained, or an average degree of polymerization at a past time point is estimated. A final conclusion may be made by correcting the estimated remaining life value by a method such as considering the tendency of the remaining life when the value is the starting point.

最後に、本実施形態を実現するためのシステム構成例について、図6を参照しつつ説明する。
このシステムは、データ入力手段10、データベース20、絶縁紙劣化指標推定手段30、絶縁紙劣化指標推定モデル31、平均重合度推定手段40、平均重合度推定モデル41、余寿命推定手段50、及びデータ出力手段60から構成されており、実際のシステム構成としては、パーソナルコンピュータ等の汎用電子計算機及びこの計算機に実装されたプログラムとして実現可能である。なお、図3における各推定手段30,40,50は、主としてプログラムにより実現される機能である。
Finally, an example of a system configuration for realizing the present embodiment will be described with reference to FIG.
This system includes a data input means 10, a database 20, an insulating paper deterioration index estimation means 30, an insulating paper deterioration index estimation model 31, an average polymerization degree estimation means 40, an average polymerization degree estimation model 41, a remaining life estimation means 50, and data. An actual system configuration can be realized as a general-purpose electronic computer such as a personal computer and a program installed in the computer. In addition, each estimation means 30, 40, 50 in FIG. 3 is a function mainly realized by a program.

データ入力手段10は、ネットワーク上の他の計算機と連携して種々のデータを入力したり、画面系からキーボードを用いて入力することもできる。また、リムーバブルな電子的記憶媒体を用いて入力することも可能である。このデータ入力手段10は、各推定モデル31,41を構築し、またはこれらの推定モデル31,41を用いて各推定手段30,40が絶縁紙劣化指標や平均重合度を推定するために必要な各種データを入力するものであり、油入電気機器の実績データ、測定データとしての各種劣化指標、当該電気機器の運転環境、当該電気機器の設計諸元、絶縁紙の平均重合度等を入力する。
データベース20には、データ入力手段10による入力データが、各推定モデル31,41の構築や各推定手段30,40による推定のために格納される。
The data input means 10 can also input various data in cooperation with other computers on the network, or input from the screen system using a keyboard. It is also possible to input using a removable electronic storage medium. The data input means 10 is necessary for constructing the estimation models 31 and 41, or for the estimation means 30 and 40 to estimate the insulation paper deterioration index and the average degree of polymerization using the estimation models 31 and 41. Inputs various data, such as actual data of oil-filled electrical equipment, various degradation indicators as measurement data, operating environment of the electrical equipment, design specifications of the electrical equipment, average degree of polymerization of insulating paper, etc. .
In the database 20, input data by the data input means 10 is stored for the construction of the estimation models 31 and 41 and estimation by the estimation means 30 and 40.

絶縁紙劣化指標推定モデル31及び平均重合度推定モデル41は、前述したようにニューラルネットワークや重回帰式等により実現され、絶縁紙劣化指標推定手段30、平均重合度推定手段40は、上記推定モデル31,41を用いてそれぞれフルフラール量等の劣化指標と絶縁紙の平均重合度とを推定するものである。なお、絶縁紙劣化指標推定手段30では、前述した劣化指標推定値の補正値も演算可能である。
また、余寿命推定手段50は、現時点及び将来の運転環境における油入電気機器の余寿命を推定する。
As described above, the insulating paper deterioration index estimation model 31 and the average polymerization degree estimation model 41 are realized by a neural network, a multiple regression equation, or the like, and the insulating paper deterioration index estimation means 30 and the average polymerization degree estimation means 40 are the above estimation models. 31 and 41 are used to estimate the degradation index such as the amount of furfural and the average degree of polymerization of the insulating paper, respectively. The insulating paper deterioration index estimation means 30 can also calculate a correction value for the above-described deterioration index estimated value.
The remaining life estimation means 50 estimates the remaining life of the oil-filled electrical device in the current and future operating environment.

データ出力手段60は、余寿命推定手段50による推定結果をCRTや液晶ディスプレイ上に表示したり、プリンタ装置等を用いて印字出力する。
なお、上記のシステム構成例はあくまでも例示的に示したものであり、他の形態のシステム構成によっても本発明は実現可能である。
The data output means 60 displays the estimation result by the remaining life estimation means 50 on a CRT or a liquid crystal display, or prints out using a printer device or the like.
Note that the above system configuration examples are merely exemplary, and the present invention can be realized by other types of system configurations.

本発明の実施形態を示すフローチャートである。It is a flowchart which shows embodiment of this invention. 実施形態における、時間軸に対する平均重合度の推定値の変化を示す概念的なグラフである。It is a conceptual graph which shows the change of the estimated value of the average degree of polymerization with respect to the time axis in embodiment. 本実施形態を実現するためのシステム構成例を示す図である。It is a figure which shows the system configuration example for implement | achieving this embodiment. 油入電気機器のフルフラール量と平均重合度残率との関係を示す図である。It is a figure which shows the relationship between the amount of furfural of an oil-filled electrical equipment, and an average degree of polymerization remaining.

符号の説明Explanation of symbols

10:データ入力手段
20:データベース
30:絶縁紙劣化指標推定手段
31:絶縁紙劣化指標推定モデル
40:平均重合度推定手段
41:平均重合度推定モデル
50:余寿命推定手段
60:データ出力手段
10: Data input means 20: Database 30: Insulating paper deterioration index estimation means 31: Insulating paper deterioration index estimation model 40: Average polymerization degree estimation means 41: Average polymerization degree estimation model 50: Remaining life estimation means 60: Data output means

Claims (4)

油入電気機器の絶縁油に含まれる劣化指標成分量を用いて油入電気機器の絶縁紙の平均重合度を推定し、この平均重合度推定値を用いて油入電気機器の余寿命を推定する方法において、
実績データとして、少なくとも前記劣化指標成分量と電気機器の稼働年数、負荷率等の運転環境とが入力され、前記平均重合度推定値を出力する平均重合度推定モデルを作成する第1ステップと、
実績データとして、少なくとも前記運転環境が入力され、前記劣化指標成分量を出力する絶縁紙劣化指標推定モデルを作成する第2ステップと、
前記平均重合度推定モデルの構築に用いた入力データと同種の測定データを前記平均重合度推定モデルに入力して、現時点における平均重合度を推定する第3ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の将来予測される運転環境データを前記絶縁紙劣化指標推定モデルに入力して、将来想定される運転環境における劣化指標成分量を推定する第4ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の現在の運転環境データを前記絶縁紙劣化指標推定モデルに入力して、現時点における劣化指標成分量を推定し、この推定値と現時点における劣化指標成分量の実測値とから求めた補正値を用いて、前記第4ステップにより推定した劣化指標成分量を補正する第5ステップと、
ステップにより補正した劣化指標成分量を用いて、将来想定される運転環境における平均重合度を前記平均重合度推定モデルにより推定する第ステップと、
ステップにより推定した、将来想定される運転環境における平均重合度から寿命低下率を求め、この寿命低下率と現時点における平均重合度推定値とを用いて電気機器の余寿命を推定する第ステップと、
を備えたことを特徴とする油入電気機器の余寿命推定方法。
Estimate the average degree of polymerization of insulating paper in oil-filled electrical equipment using the amount of degradation index component contained in the insulation oil of oil-filled electrical equipment, and estimate the remaining life of oil-filled electrical equipment using this average degree of polymerization estimate In the way to
A first step of creating an average polymerization degree estimation model that inputs at least the deterioration index component amount and the operating environment of the electric equipment, the operating environment such as the load factor, and outputs the average polymerization degree estimation value as actual data;
A second step of creating an insulating paper deterioration index estimation model that outputs at least the operating environment as output data and outputs the deterioration index component amount;
A third step of inputting the measurement data of the same type as the input data used for constructing the average polymerization degree estimation model to the average polymerization degree estimation model, and estimating a current average polymerization degree;
Estimate the amount of degradation index components in the expected operating environment by inputting the predicted future operating environment data of the same type as the input data used to construct the insulating paper degradation index estimation model into the insulating paper degradation index estimation model. And a fourth step
The current operating environment data of the same type as the input data used for the construction of the insulation paper deterioration index estimation model is input to the insulation paper deterioration index estimation model to estimate the current deterioration index component amount. A fifth step of correcting the deterioration index component amount estimated in the fourth step using a correction value obtained from the actual measurement value of the deterioration index component amount in
A sixth step of estimating an average degree of polymerization in a driving environment assumed in the future using the average degree of polymerization estimation model using the deterioration index component amount corrected in the fifth step;
6 was estimated by step, determine the lifetime reduction ratio from an average polymerization degree of driving environment envisioned future, seventh to estimate the remaining life of the electrical device using the average degree of polymerization estimate in this lifetime reduction rate and the current Steps,
A remaining life estimation method for oil-filled electrical equipment, comprising:
油入電気機器の絶縁油に含まれる劣化指標成分量を用いて油入電気機器の絶縁紙の平均重合度を推定し、この平均重合度推定値を用いて油入電気機器の余寿命を推定する方法において、
実績データとして、少なくとも前記劣化指標成分量と電気機器の稼働年数、負荷率等の運転環境とが入力され、前記平均重合度推定値を出力する平均重合度推定モデルを作成する第1ステップと、
実績データとして、少なくとも前記運転環境が入力され、前記劣化指標成分量を出力する絶縁紙劣化指標推定モデルを作成する第2ステップと、
前記平均重合度推定モデルの構築に用いた入力データと同種の測定データを前記平均重合度推定モデルに入力して、将来の任意時点における平均重合度を推定する第3ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の将来予測される運転環境データを前記絶縁紙劣化指標推定モデルに入力して、将来の任意時点以降において想定される運転環境における劣化指標成分量を推定する第4ステップと、
前記絶縁紙劣化指標推定モデルの構築に用いた入力データと同種の現在の運転環境データを前記絶縁紙劣化指標推定モデルに入力して、現時点における劣化指標成分量を推定し、この推定値と現時点における劣化指標成分量の実測値とから求めた補正値を用いて、前記第4ステップにより推定した劣化指標成分量を補正する第5ステップと、
ステップにより補正した劣化指標成分量を用いて、将来の任意時点以降において想定される運転環境における平均重合度を前記平均重合度推定モデルにより推定する第ステップと、
ステップにより推定した、将来の任意時点以降において想定される運転環境における平均重合度から寿命低下率を求め、この寿命低下率と将来の任意時点における平均重合度推定値とを用いて電気機器の余寿命を推定する第ステップと、
を備えたことを特徴とする油入電気機器の余寿命推定方法。
Estimate the average degree of polymerization of insulating paper in oil-filled electrical equipment using the amount of degradation index component contained in the insulation oil of oil-filled electrical equipment, and estimate the remaining life of oil-filled electrical equipment using this average degree of polymerization estimate In the way to
A first step of creating an average polymerization degree estimation model that inputs at least the deterioration index component amount and the operating environment of the electric equipment, the operating environment such as the load factor, and outputs the average polymerization degree estimation value as actual data;
A second step of creating an insulating paper deterioration index estimation model that outputs at least the operating environment as output data and outputs the deterioration index component amount;
A third step of inputting the measurement data of the same type as the input data used to construct the average polymerization degree estimation model to the average polymerization degree estimation model, and estimating the average polymerization degree at an arbitrary future time point;
Deterioration in the operating environment assumed after an arbitrary time in the future by inputting into the insulating paper deterioration index estimation model the same predicted future operating environment data as the input data used for the construction of the insulating paper deterioration index estimation model A fourth step of estimating the index component amount;
The current operating environment data of the same type as the input data used for the construction of the insulation paper deterioration index estimation model is input to the insulation paper deterioration index estimation model to estimate the current deterioration index component amount. A fifth step of correcting the deterioration index component amount estimated in the fourth step using a correction value obtained from the actual measurement value of the deterioration index component amount in
A sixth step of estimating an average degree of polymerization in an operating environment assumed after an arbitrary time in the future using the average degree of polymerization estimation model using the deterioration index component amount corrected in the fifth step;
The life reduction rate is obtained from the average degree of polymerization in the operating environment assumed after the arbitrary time in the future estimated by the sixth step, and the electrical equipment is obtained by using this life reduction rate and the estimated average degree of polymerization at the arbitrary time in the future. A seventh step of estimating the remaining life of
A remaining life estimation method for oil-filled electrical equipment, comprising:
請求項1または2に記載した油入機器の余寿命推定方法において、
前記絶縁紙劣化指標推定モデルとして、前記電気機器の稼働年数及び負荷率を入力として前記劣化指標成分量を出力するニューラルネットワークを用いることを特徴とする油入電気機器の余寿命推定方法。
In the method for estimating the remaining life of an oil-filled device according to claim 1 or 2,
A method for estimating the remaining life of an oil-filled electrical device, wherein a neural network is used as the insulating paper degradation index estimation model, wherein the neural network that outputs the degradation index component amount with the operating years and load factor of the electrical device as inputs is used.
請求項1または2に記載した油入機器の余寿命推定方法において、
前記絶縁紙劣化指標推定モデルとして、前記電気機器の稼働年数及び負荷率が類似した複数の事例データの平均値を用いて劣化指標成分量を推定することを特徴とする油入電気機器の余寿命推定方法。
In the method for estimating the remaining life of an oil-filled device according to claim 1 or 2,
Remaining life of oil-filled electrical equipment, characterized in that, as the insulating paper deterioration index estimation model, the deterioration index component amount is estimated using an average value of a plurality of case data having similar operating years and load factors of the electrical equipment Estimation method.
JP2008068870A 2008-03-18 2008-03-18 Method for estimating the remaining life of oil-filled electrical equipment Active JP5387877B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2008068870A JP5387877B2 (en) 2008-03-18 2008-03-18 Method for estimating the remaining life of oil-filled electrical equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2008068870A JP5387877B2 (en) 2008-03-18 2008-03-18 Method for estimating the remaining life of oil-filled electrical equipment

Publications (2)

Publication Number Publication Date
JP2009222620A JP2009222620A (en) 2009-10-01
JP5387877B2 true JP5387877B2 (en) 2014-01-15

Family

ID=41239557

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2008068870A Active JP5387877B2 (en) 2008-03-18 2008-03-18 Method for estimating the remaining life of oil-filled electrical equipment

Country Status (1)

Country Link
JP (1) JP5387877B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7348607B2 (en) 2021-01-13 2023-09-21 コダマ樹脂工業株式会社 Container closure structure

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10460251B2 (en) * 2015-06-19 2019-10-29 Preferred Networks Inc. Cross-domain time series data conversion apparatus, methods, and systems
JP6360090B2 (en) 2016-03-10 2018-07-18 ファナック株式会社 Machine learning device, laser device, and machine learning method
JP6339655B1 (en) 2016-12-19 2018-06-06 ファナック株式会社 Machine learning device and light source unit manufacturing device for learning alignment procedure of optical component of light source unit
JP6848748B2 (en) * 2017-07-26 2021-03-24 三菱電機株式会社 Remaining life diagnosis method and remaining life diagnosis device for electrical equipment
JP6797780B2 (en) 2017-11-07 2020-12-09 株式会社東芝 Information processing equipment, information processing methods and programs
CN110889228B (en) * 2019-11-28 2023-04-18 国网吉林省电力有限公司电力科学研究院 Transformer oil paper insulation aging prediction method based on chicken swarm optimization BP neural network

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06123679A (en) * 1992-10-09 1994-05-06 Mitsubishi Heavy Ind Ltd Method for diagnosing remaining life of high-temperature equipment
JP3655028B2 (en) * 1996-11-05 2005-06-02 東芝プラントシステム株式会社 Pipe thinning management system
JP2003114294A (en) * 2001-10-04 2003-04-18 Toshiba Corp Monitor, diagnosis, inspection and maintenance system for power-generating plant

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7348607B2 (en) 2021-01-13 2023-09-21 コダマ樹脂工業株式会社 Container closure structure

Also Published As

Publication number Publication date
JP2009222620A (en) 2009-10-01

Similar Documents

Publication Publication Date Title
JP5387877B2 (en) Method for estimating the remaining life of oil-filled electrical equipment
JP5494034B2 (en) Reliability evaluation apparatus, reliability evaluation program, and reliability evaluation method
JP4857597B2 (en) Degradation diagnosis method for oil-filled electrical equipment
KR101160775B1 (en) System and method for evaluating integrity of power transformer
EP2735011B1 (en) Method and system for estimating transformer remaining life
Hillary et al. A tool for estimating remaining life time of a power transformer
KR101046752B1 (en) Transformer life assessment method
Mharakurwa et al. Multiparameter‐Based Fuzzy Logic Health Index Assessment for Oil‐Immersed Power Transformers
Tahir et al. Evaluation of numerical indices for objective interpretation of frequency response to detect mechanical faults in power transformers
JP4623334B1 (en) Method for predicting the possibility of abnormality in oil-filled electrical equipment
KR102597250B1 (en) Method for evaluating lifetime of extra high voltage electric cable
JP4888402B2 (en) Remaining life diagnosis method for oil-filled transformers
JP2009168571A (en) Method for diagnosing degradation of oil-immersed transformer
CN112269105A (en) Moisture prediction and aging evaluation method for field bushing oil-immersed cellulose insulation
Ghazali et al. TNB experience in condition assessment and life management of distribution power transformers
Agarwal et al. Diagnostic and prognostic models for generator step-up transformers
JPH0794334A (en) Deterioration diagnostic system and life predictive system of oil-immersed transformer
Mharakurwa et al. Transformer remnant life estimation and asset management model based on insulation stress assessment
Pradhan et al. Criteria for estimation of end of life of power and station transformers in service
Raetzke et al. Condition assessment of instrument transformers using dielectric response analysis
KR101438158B1 (en) Method and apparatus for predicting life time of transformer
Arabul et al. Determination of transformer board creep parameters under high‐mechanical and thermal stresses
Agarwal et al. Implementation of remaining useful lifetime transformer models in the fleet-wide prognostic and health management suite
KR102124787B1 (en) method for analyzing condition Based Risk of power equipment
JPH0636941A (en) Abnormality predicting system of oil-immersed transformer

Legal Events

Date Code Title Description
A625 Written request for application examination (by other person)

Free format text: JAPANESE INTERMEDIATE CODE: A625

Effective date: 20110117

A711 Notification of change in applicant

Free format text: JAPANESE INTERMEDIATE CODE: A712

Effective date: 20110422

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20130702

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20130822

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20130912

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20130925

R150 Certificate of patent or registration of utility model

Ref document number: 5387877

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

RD02 Notification of acceptance of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: R3D02

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250