本文選題：量子神經(jīng)網(wǎng)絡(luò) + 混合量子衍生神經(jīng)網(wǎng)絡(luò)�。� 參考：《東北石油大學(xué)》2017年碩士論文

【摘要】：油氣層的準(zhǔn)確識別是勘探開發(fā)的重中之重,大多數(shù)識別單純依靠著專家經(jīng)驗(yàn),然而許多的人為因素導(dǎo)致了儲層識別的精準(zhǔn)度不高。在浪費(fèi)大量人力物力的同時(shí),卻沒有達(dá)到人們期待的效果。由于儲層識別中的影響因素之間是存在著非線性的映射關(guān)系,很難用公式來描述其關(guān)系,而神經(jīng)網(wǎng)絡(luò)能夠表達(dá)這種映射關(guān)系。但是傳統(tǒng)神經(jīng)網(wǎng)絡(luò)具有一些已經(jīng)被發(fā)現(xiàn)的缺陷,如逼近能力差、易于陷入局部極小值等。在近年來的研究中,有實(shí)驗(yàn)可證,將量子計(jì)算與神經(jīng)計(jì)算進(jìn)行融合而出現(xiàn)的新的量子神經(jīng)網(wǎng)絡(luò)這一方法對改善神經(jīng)網(wǎng)絡(luò)缺陷具有明顯作用,因此本文中提出將量子神經(jīng)網(wǎng)絡(luò)應(yīng)用到儲層識別中的新方法,以期大幅度提高識別儲層識別準(zhǔn)確率,并為儲層識別問題提供一條新途徑。量子神經(jīng)網(wǎng)絡(luò)涌現(xiàn)且研究的時(shí)間并不是很長,目前可以說是一個(gè)全新的領(lǐng)域,且并未完全成熟,進(jìn)一步深入研究它與其他算法的融合,以期能夠進(jìn)一步提高其性能是十分必要的�；谶@一目的,本文擬提出一種基于量子比特在Bloch球面的繞軸旋轉(zhuǎn)構(gòu)造神經(jīng)網(wǎng)絡(luò)模型的新思想,進(jìn)而研究一種新的量子衍生神經(jīng)網(wǎng)絡(luò)模型及算法,把其應(yīng)用到油氣儲集層識別問題中。該模型可顯著提高其逼近和預(yù)測能力。本文主要研究內(nèi)容如下。首先,設(shè)計(jì)了一種新型量子神經(jīng)網(wǎng)絡(luò)模型。該模型為三層結(jié)構(gòu),輸入層和輸出層為普通神經(jīng)元,隱層為量子神經(jīng)元。量子神經(jīng)元的輸入為量子比特,關(guān)于其映射機(jī)制,首先使輸入比特繞坐標(biāo)軸旋轉(zhuǎn),然后采用泡利矩陣計(jì)算旋轉(zhuǎn)后的坐標(biāo)值,再用Sigmoid函數(shù)將坐標(biāo)值映射為量子神經(jīng)元的輸出。第二,在量子神經(jīng)網(wǎng)絡(luò)的訓(xùn)練方面,本文設(shè)計(jì)了L-M算法和量子蜂群算法。然而這兩種算法都有局限性,首先L-M算法收斂較快,但易于陷入局部極小值,量子蜂群算法雖然具有較好的全局尋優(yōu)能力,但由于采用種群尋優(yōu),因此計(jì)算效率較低。所以本文提出了一種將兩種算法融合的兩階段訓(xùn)練算法。具體研究方案為:首先采用量子蜂群算法實(shí)施網(wǎng)絡(luò)權(quán)值的全局探索,然后采用L-M算法實(shí)施網(wǎng)絡(luò)權(quán)值的局部開發(fā)。第三,針對儲層識別問題,研究基于混合量子衍生神經(jīng)網(wǎng)絡(luò)的識別方法。首先研究儲層分類、儲層識別的影響因素,然后結(jié)合了礦場實(shí)際的測井解釋數(shù)據(jù),提出了基于混合量子衍生神經(jīng)網(wǎng)絡(luò)的儲層識別方法。該方法為儲層識別問題開辟了新道路。
[Abstract]:The accurate identification of oil and gas reservoir is the most important in exploration and development. Most of the identification is based on the experience of experts. However, many human factors lead to the low accuracy of reservoir identification. Waste a lot of manpower and material resources at the same time, but did not achieve the desired results. Because there is a nonlinear mapping relationship between the influencing factors in reservoir identification, it is difficult to describe the relationship by formula, and the neural network can express this mapping relationship. However, the traditional neural network has some defects that have been found, such as poor approximation ability, easy to fall into local minima and so on. In recent years, it has been proved by experiments that the new method of quantum neural network, which combines quantum computing with neural computing, has obvious effect on improving the defect of neural network. Therefore, a new method of applying quantum neural network to reservoir recognition is proposed in this paper, in order to improve the accuracy of reservoir recognition and provide a new way for reservoir recognition. Quantum neural networks appear and research is not very long, it can be said to be a new field, and not fully mature, further in-depth study of its fusion with other algorithms, It is necessary to further improve its performance. For this purpose, this paper proposes a new idea of constructing a neural network model based on the rotation of quantum bits around the Bloch sphere, and then studies a new quantum derivative neural network model and its algorithm. It is applied to the problem of oil and gas reservoir identification. The model can significantly improve its ability of approximation and prediction. The main contents of this paper are as follows. Firstly, a new quantum neural network model is designed. The model is composed of three layers: the input layer and the output layer are ordinary neurons, and the hidden layer is quantum neurons. The input of a quantum neuron is a quantum bit. As to its mapping mechanism, the input bit is first rotated around the coordinate axis, then the rotated coordinate value is calculated by using Pauli matrix, and then the coordinate value is mapped to the output of the quantum neuron by using the Sigmoid function. Secondly, in the training of quantum neural network, L-M algorithm and quantum bee colony algorithm are designed in this paper. However, both algorithms have their limitations. Firstly, L-M algorithm converges fast, but it is easy to fall into local minimum. Quantum bee colony algorithm has better global optimization ability, but because of population optimization, the computational efficiency is low. So this paper proposes a two-stage training algorithm which combines the two algorithms. The specific schemes are as follows: firstly, the quantum bee colony algorithm is used to implement the global exploration of network weights, and then the L-M algorithm is used to implement the local development of network weights. Thirdly, the recognition method based on hybrid quantum derivative neural network is studied for reservoir identification. Firstly, the reservoir classification and the influencing factors of reservoir identification are studied. Then, a method of reservoir identification based on hybrid quantum derivative neural network is proposed by combining the actual logging interpretation data in the field. This method opens up a new way for reservoir identification.
【學(xué)位授予單位】：東北石油大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：P618.13;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李盼池;李國蕊;;混合量子衍生神經(jīng)網(wǎng)絡(luò)模型及算法[J];電子與信息學(xué)報(bào);2016年01期

2 李盼池;周紅巖;;基于受控Hadamard門的量子神經(jīng)網(wǎng)絡(luò)模型及算法[J];計(jì)算機(jī)研究與發(fā)展;2015年01期

3 李楠;侯旋;;自適應(yīng)量子前向?qū)魉惴ㄑ芯縖J];電子與信息學(xué)報(bào);2013年11期

4 郭通;蘭巨龍;李玉峰;江逸茗;;基于量子自適應(yīng)粒子群優(yōu)化徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的網(wǎng)絡(luò)流量預(yù)測[J];電子與信息學(xué)報(bào);2013年09期

5 張翼鵬;陳亮;郝歡;;一種改進(jìn)的量子神經(jīng)網(wǎng)絡(luò)訓(xùn)練算法[J];電子與信息學(xué)報(bào);2013年07期

6 李盼池;王琪超;施光堯;;基于Bloch球面搜索的量子粒子群優(yōu)化算法[J];計(jì)算物理;2013年03期

7 ;Learning algorithm and application of quantum BP neural networks based on universal quantum gates[J];Journal of Systems Engineering and Electronics;2008年01期

8 丁海軍;李峰磊;;蜂群算法在TSP問題上的應(yīng)用及參數(shù)改進(jìn)[J];中國科技信息;2008年03期

9 朱大奇;桑慶兵;;光電雷達(dá)電子部件的量子神經(jīng)網(wǎng)絡(luò)故障診斷算法[J];電子學(xué)報(bào);2006年03期

10 劉錫健;匡建超;;偏最小二乘神經(jīng)網(wǎng)絡(luò)在儲層識別和產(chǎn)能預(yù)測中的應(yīng)用——以陜甘寧盆地中部氣田馬五_1儲層為例[J];礦物巖石;2005年04期

相關(guān)博士學(xué)位論文 前5條

1 李鵬華;量子計(jì)算在動態(tài)遞歸與自組織神經(jīng)網(wǎng)絡(luò)中的機(jī)理及應(yīng)用研究[D];重慶大學(xué);2012年

2 胥德平;時(shí)頻分析新方法研究及其在地震資料儲層識別中的應(yīng)用[D];成都理工大學(xué);2012年

3 王澤明;致密砂巖氣藏儲層特征及有效儲層識別研究[D];中國地質(zhì)大學(xué);2010年

4 陳冬;地震多屬性分析及其在儲層預(yù)測中的應(yīng)用研究[D];中國地質(zhì)大學(xué)（北京）;2008年

5 周日貴;量子神經(jīng)網(wǎng)絡(luò)模型研究[D];南京航空航天大學(xué);2008年

相關(guān)碩士學(xué)位論文 前6條

1 黃偉強(qiáng);基于量子神經(jīng)網(wǎng)絡(luò)的腫瘤細(xì)胞圖像識別研究[D];華東交通大學(xué);2016年

2 許宏龍;基于BP神經(jīng)網(wǎng)絡(luò)技術(shù)的儲層非均質(zhì)性研究[D];長江大學(xué);2016年

3 唐凱;天然氣儲層氣水識別方法研究及其應(yīng)用[D];成都理工大學(xué);2013年

4 張如一;基于希爾伯特黃變換的薄儲層識別方法研究[D];中國海洋大學(xué);2012年

5 王磊;薄層測井曲線校正方法及儲層識別模型研究[D];西南石油大學(xué);2006年

6 賈煥軍;油氣層神經(jīng)網(wǎng)絡(luò)識別方法研究[D];大慶石油學(xué)院;2003年

，

本文編號：1852550