【摘要】：系統(tǒng)仿真、數(shù)據(jù)建模等信息處理方法隨著科學(xué)技術(shù)的不斷進(jìn)步,其應(yīng)用領(lǐng)域也在不斷擴(kuò)展。復(fù)雜非線性動(dòng)態(tài)系統(tǒng)的辨識(shí)精度和建模性能的實(shí)際需求,也對(duì)系統(tǒng)仿真模型和信號(hào)變換機(jī)制的研究提出了更高的要求。本文面向油田勘探開發(fā)中的動(dòng)態(tài)診斷、過程仿真、預(yù)測(cè)分析等典型問題,進(jìn)行基于過程神經(jīng)元網(wǎng)絡(luò)的信息處理機(jī)制、數(shù)據(jù)建模方法與應(yīng)用技術(shù)的研究。論文在對(duì)油田動(dòng)態(tài)信息處理問題和智能數(shù)據(jù)建模方法總結(jié)分析的基礎(chǔ)上,將其歸納為動(dòng)態(tài)診斷、過程模擬、預(yù)測(cè)分析等典型應(yīng)用,采用過程神經(jīng)元網(wǎng)絡(luò)方法進(jìn)行建模處理。通過歸納分析油田動(dòng)態(tài)系統(tǒng)信息匯聚和時(shí)間效應(yīng)累積模式,針對(duì)不同的應(yīng)用目的,提出了適合于不同典型應(yīng)用的時(shí)空聚合算子、激勵(lì)函數(shù)、網(wǎng)絡(luò)模型的構(gòu)建和選擇策略,并對(duì)其理論性質(zhì)進(jìn)行了分析。對(duì)于網(wǎng)絡(luò)結(jié)構(gòu)優(yōu)化和學(xué)習(xí)問題,提出了LMS算法與粒子群算法相結(jié)合、LM算法與量子遺傳算法相結(jié)合的兩種混合優(yōu)化算法,可同時(shí)實(shí)現(xiàn)對(duì)過程神經(jīng)元網(wǎng)絡(luò)結(jié)構(gòu)和學(xué)習(xí)性質(zhì)的優(yōu)化。在應(yīng)用技術(shù)研究中,面向油田開發(fā)系統(tǒng)過程模擬和動(dòng)態(tài)模式識(shí)別兩個(gè)典型問題,建立了基于過程神經(jīng)元網(wǎng)絡(luò)的過程仿真模擬和動(dòng)態(tài)診斷分析的實(shí)現(xiàn)方法和技術(shù)。課題在面向油田動(dòng)態(tài)信息建模的過程神經(jīng)元網(wǎng)絡(luò)構(gòu)建方法與應(yīng)用技術(shù)研究結(jié)果基礎(chǔ)上,以油田開發(fā)井組注采過程模擬和優(yōu)勢(shì)滲流場(chǎng)判別兩個(gè)典型問題進(jìn)行實(shí)際資料處理,取得了較好的應(yīng)用結(jié)果。對(duì)于時(shí)空維信息處理方法的研究具有較大的理論和實(shí)際應(yīng)用價(jià)值。
[Abstract]:With the development of science and technology, the application fields of system simulation, data modeling and other information processing methods are also expanding. The identification accuracy and modeling performance of complex nonlinear dynamic systems require higher requirements for the study of system simulation models and signal transformation mechanisms. Aiming at the typical problems of dynamic diagnosis, process simulation, prediction and analysis in oilfield exploration and development, the information processing mechanism, data modeling method and application technology based on process neural network are studied in this paper. On the basis of summarizing and analyzing the problem of oilfield dynamic information processing and the method of intelligent data modeling, this paper sums it up into typical applications such as dynamic diagnosis, process simulation, prediction and analysis, and adopts the method of process neural network to model and process. Based on the analysis of information gathering and time effect accumulation models of oilfield dynamic system, the strategies of constructing and selecting spatio-temporal aggregation operator, incentive function and network model suitable for different application purposes are put forward. The theoretical properties are analyzed. For the problem of network structure optimization and learning, two hybrid optimization algorithms, LMS algorithm and particle swarm optimization algorithm, and LM algorithm and quantum genetic algorithm are proposed, which can optimize the network structure and learning properties of process neurons at the same time. In the process simulation and dynamic pattern recognition of oilfield development system, the implementation method and technology of process simulation and dynamic diagnosis analysis based on process neural network are established. On the basis of the research results of process neural network and its application technology, two typical problems of injection and production process simulation and predominance seepage field discrimination of oilfield development well group are used to process the actual data. Good application results have been obtained. The research of spatiotemporal dimension information processing method has great theoretical and practical application value.
【學(xué)位授予單位】：東北石油大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TE331;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 鐘詩(shī)勝;樸樹學(xué);丁剛;;改進(jìn)BP算法在過程神經(jīng)網(wǎng)絡(luò)中的應(yīng)用[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2006年06期

2 許少華;何新貴;周繼;王兵;;一種過程支持向量機(jī)及其在動(dòng)態(tài)模式分類中的應(yīng)用[J];控制與決策;2009年02期

3 許少華;李盼池;何新貴;;一種概率過程神經(jīng)元網(wǎng)絡(luò)模型及分類算法[J];智能系統(tǒng)學(xué)報(bào);2009年04期

，

本文編號(hào)：2427034