【摘要】：大伙房水庫(kù)作為渾河中上游上的控制性骨干工程,其防洪意義尤為重要。大伙房水庫(kù)現(xiàn)行的洪水預(yù)報(bào)模型為大伙房模型(DHF),該模型為集總式模型,由于集總式模型的特性其不考慮水文過(guò)程,因此存在對(duì)各支流的流量及水位等不能有效描述的問(wèn)題,而且該模型的參數(shù)在選擇上是通過(guò)優(yōu)選法選定或人工試錯(cuò)法確定的,并需要實(shí)時(shí)校正,因此對(duì)率定工作者的要求高且率定工作較為繁瑣。鑒于以上不足本文綜合考慮資料數(shù)據(jù)的限制、輸入數(shù)據(jù)、邊界條件和流域特征等客觀因素,建立了一種半分布式BP神經(jīng)網(wǎng)絡(luò)洪水預(yù)報(bào)模型,實(shí)際應(yīng)用中觀察發(fā)現(xiàn)其易陷入局部最小點(diǎn),且預(yù)報(bào)時(shí)長(zhǎng)較短,因此隨后在此基礎(chǔ)上對(duì)其做出改進(jìn),建立了DHF-GA-BP神經(jīng)網(wǎng)絡(luò)耦合洪水預(yù)報(bào)模型,并將建立的模型應(yīng)用于大伙房壩址以上流域進(jìn)行洪水預(yù)報(bào),該改進(jìn)模型結(jié)合了大伙房模型與BP神經(jīng)網(wǎng)絡(luò)的優(yōu)勢(shì),并引入遺傳算法,彌補(bǔ)了半分布式BP神經(jīng)網(wǎng)絡(luò)模型的不足。本文研究的主要內(nèi)容及相應(yīng)結(jié)果如下：(1)建立模型前對(duì)壩址以上流域進(jìn)行分區(qū)。分區(qū)時(shí)以距離各個(gè)水文站最近的自然流域分水線為界,采用DEM數(shù)據(jù)與ArcGIS軟件最終劃分出Ⅰ、Ⅱ和Ⅲ三個(gè)區(qū)域,北口前水文站所在區(qū)為Ⅰ區(qū),占貝水文描述站所在區(qū)為Ⅱ區(qū),南章黨水文站所在區(qū)為Ⅲ區(qū)。(2)對(duì)將要輸入模型中的現(xiàn)有數(shù)據(jù)進(jìn)行預(yù)處理。利用逐步回歸分析法對(duì)初始數(shù)據(jù)進(jìn)行篩選,保證輸入的數(shù)據(jù)對(duì)輸出結(jié)果有顯著影響。篩選結(jié)果Ⅰ、Ⅱ區(qū)均為8個(gè)顯著因子、Ⅲ區(qū)為6個(gè)顯著因子、入庫(kù)斷面即全流域?yàn)?1個(gè)顯著因子。(3)建立半分布式BP神經(jīng)網(wǎng)絡(luò)模型對(duì)大伙房水庫(kù)進(jìn)行實(shí)時(shí)洪水預(yù)報(bào)。預(yù)報(bào)模型分為兩部分,第一部分為子流域流量預(yù)報(bào),第二部分為入庫(kù)斷面流量預(yù)報(bào),第一部分的輸出結(jié)果為第二部分的輸入數(shù)據(jù)。結(jié)果顯示,子流域預(yù)報(bào)和入庫(kù)斷面預(yù)報(bào)的結(jié)果較好且該模型對(duì)子流域內(nèi)的洪水調(diào)度也可起到輔助作用,但在預(yù)報(bào)精度、模型效率以及預(yù)報(bào)時(shí)長(zhǎng)方面仍有待提高,應(yīng)對(duì)其改進(jìn)。(4)改進(jìn)模型建立前預(yù)先應(yīng)用遺傳算法率定大伙房模型參數(shù),使其可以分別應(yīng)用于各子流域的洪水預(yù)報(bào)。檢驗(yàn)期預(yù)報(bào)結(jié)果顯示,預(yù)報(bào)效果較好,部分場(chǎng)次雖有不合格現(xiàn)象但整體預(yù)報(bào)水平仍可滿足正式預(yù)報(bào)需求。(5)針對(duì)半分布式BP神經(jīng)網(wǎng)絡(luò)模型的缺陷進(jìn)行改進(jìn)。應(yīng)用遺傳算法優(yōu)化原BP神經(jīng)網(wǎng)絡(luò)的初始權(quán)重及閾值,結(jié)合遺傳算法率定參數(shù)后的大伙房模型的預(yù)報(bào)成果,形成改進(jìn)的半分布式BP神經(jīng)網(wǎng)絡(luò)模型——DHF-GA-BP神經(jīng)網(wǎng)絡(luò)耦合模型。預(yù)報(bào)結(jié)果顯示,改進(jìn)后的洪水預(yù)報(bào)模型在運(yùn)行效率和預(yù)報(bào)精度上都較原模型有所提高,延長(zhǎng)了預(yù)報(bào)時(shí)長(zhǎng),且在一定程度上避免了遺傳算法率定參數(shù)后的大伙房模型預(yù)報(bào)誤差的累積。
[Abstract]:Dahuofang Reservoir is a controlled backbone project in the middle and upper reaches of Hunhe River, and its flood control significance is particularly important. The current flood forecasting model of Dahuofang Reservoir is the Dahuofang model (DHF), which is a lumped model. Because of the characteristics of the lumped model, it does not consider the hydrological process. Therefore, there is a problem that the flow and water level of each tributary can not be effectively described, and the parameters of the model are determined by optimal selection or artificial trial and error method, and need to be corrected in real time. Therefore, the requirements for calibration workers are high and the calibration work is more tedious. In view of the above shortcomings, considering the limitations of data, input data, boundary conditions and watershed characteristics, a semi-distributed BP neural network flood forecasting model is established in this paper. In practical application, it is found that it is easy to fall into the local minimum point and the forecast time is short. Therefore, on this basis, the DHF-GA-BP neural network coupling flood forecasting model is established. The model is applied to flood forecasting above Dahuofang dam site. The improved model combines the advantages of Dahuofang model and BP neural network, and introduces genetic algorithm to make up for the shortcomings of semi-distributed BP neural network model. The main contents and corresponding results of this paper are as follows: (1) before the establishment of the model, the watershed above the dam site is divided. Taking the natural watershed waterline nearest to each hydrologic station as the boundary, the DEM data and ArcGIS software are used to divide the three areas of 鈪，

本文編號(hào)：2472963