發(fā)布時(shí)間：2018-03-29 17:13

  本文選題：高密度電阻率法　切入點(diǎn)：非線性反演　出處：《山東科技大學(xué)》2017年碩士論文

【摘要】：煤炭企業(yè)在國(guó)民經(jīng)濟(jì)和社會(huì)發(fā)展中起著及其重要的地位。我國(guó)作為世界上主要的產(chǎn)煤國(guó)的同時(shí),也是受礦井災(zāi)害最嚴(yán)重的國(guó)家之一。目前隨著我國(guó)煤炭開采強(qiáng)度不斷加強(qiáng),深度不斷增加,大型煤田越來(lái)越多,礦井地質(zhì)災(zāi)害的威脅也愈來(lái)愈嚴(yán)重。地質(zhì)勘探是煤礦安全生產(chǎn)的基礎(chǔ),在煤礦地質(zhì)災(zāi)害的防治中扮演著舉足輕重的作用。高密度電阻率法作為是一種高效的電阻率勘探方法,在礦山地質(zhì)安全的勘探與評(píng)價(jià)中被廣泛應(yīng)用。在高密度電法資料的解釋方面,目前仍以最小二乘法為代表的線性反演為主,但是這種方法的反演精度并不是很高,因此越來(lái)越多的學(xué)者投入于非線性反演的研究中,基于BP神經(jīng)網(wǎng)絡(luò)的高密度電法的反演成為非線性反演中一個(gè)較為活躍的分支。本文針對(duì)BP神經(jīng)網(wǎng)絡(luò)因權(quán)值閾值隨機(jī)初始化導(dǎo)致的收斂緩慢,易陷入局部最小的不足,結(jié)合神經(jīng)網(wǎng)絡(luò)節(jié)點(diǎn)權(quán)值數(shù)量級(jí)越小,網(wǎng)絡(luò)泛化能力越強(qiáng)的特點(diǎn),采用多目標(biāo)優(yōu)化算法(NSGA-Ⅱ算法)與BP神經(jīng)網(wǎng)絡(luò)算法聯(lián)合演算,以BP神經(jīng)網(wǎng)絡(luò)的訓(xùn)練均方誤差MSE和隱含層參數(shù)的均方根值同時(shí)作為目標(biāo)函數(shù),對(duì)BP神經(jīng)網(wǎng)絡(luò)進(jìn)行多目標(biāo)優(yōu)化,從而提高BP神經(jīng)網(wǎng)絡(luò)對(duì)高密度電法數(shù)據(jù)的反演精度。本文通過(guò)計(jì)算機(jī)模型介紹了基于NSGA-BP神經(jīng)網(wǎng)絡(luò)算法的高密度電法反演方法和具體流程,反演結(jié)果表明NSGA-Ⅱ算法能夠有效優(yōu)化了 BP神經(jīng)網(wǎng)絡(luò)的權(quán)值和閾值,提高BP算法的全局尋優(yōu)性能和神經(jīng)網(wǎng)絡(luò)的泛化能力,比傳統(tǒng)非線性反演算法和單一 BP神經(jīng)網(wǎng)絡(luò)算法的反演結(jié)果更準(zhǔn)確。最后以梁家煤礦ZK60號(hào)地面注漿孔為研究對(duì)象,開展了高密度電法的測(cè)量,應(yīng)用NSGA-BP神經(jīng)網(wǎng)絡(luò)方法進(jìn)行反演分析。結(jié)果表明,該方法能夠有效的應(yīng)用于高密度電法實(shí)測(cè)資料的解釋中,為鉆孔注漿效果評(píng)價(jià)提高可靠的依據(jù)。
[Abstract]:Coal enterprises play an important role in the development of national economy and society. As the main coal-producing countries in the world, China is also one of the countries most seriously affected by mine disasters. With the increasing of depth and the increasing number of large-scale coal fields, the threat of mine geological hazards is becoming more and more serious. Geological exploration is the basis for the safe production of coal mines. It plays an important role in the prevention and control of coal mine geological hazards. High density resistivity method is an efficient resistivity exploration method. It is widely used in the exploration and evaluation of mine geological safety. At present, the linear inversion represented by the least square method is still the main method in the interpretation of high-density electrical data, but the inversion accuracy of this method is not very high. Therefore, more and more scholars are engaged in the research of nonlinear inversion. The inversion of high density electrical method based on BP neural network has become an active branch of nonlinear inversion. In this paper, the convergence of BP neural network due to random initialization of weight threshold is slow, and it is easy to fall into local minimum. Combined with the characteristics that the weight of the neural network is smaller, the generalization ability of the network is stronger, the multi-objective optimization algorithm (NSGA- 鈪，

本文編號(hào)：1682072