報(bào)告題目：發(fā)動(dòng)機(jī)燃燒不穩(wěn)定性與基于物理信息神經(jīng)網(wǎng)絡(luò)的研究與應(yīng)用

報(bào) 告 人：趙丹

報(bào)告時(shí)間：2025年2月27日下午2:00

報(bào)告地點(diǎn)：S404

專家簡(jiǎn)介：

      趙丹教授，新西蘭皇家科學(xué)院與工程院兩院院士，歐洲科學(xué)院外籍院士，歐洲科學(xué)與藝術(shù)院外籍院士，博士畢業(yè)于英國劍橋大學(xué)，目前擔(dān)任新西蘭皇家學(xué)會(huì)院士評(píng)選委員，新西蘭坎特伯雷大學(xué)機(jī)械學(xué)院教授，博士生導(dǎo)師，兼研究生招生辦主任，國際聲學(xué)與振動(dòng)學(xué)會(huì)杰出會(huì)士（美國），中國僑聯(lián)特聘專家委員會(huì)委員，教育部 111 計(jì)劃學(xué)術(shù)大師。長(zhǎng)期從事下一代零碳（氨、氫）排放發(fā)動(dòng)機(jī)燃燒、無人機(jī)、空氣動(dòng)力學(xué)與噪音、燃?xì)廨啓C(jī)以及航空航天推進(jìn)系統(tǒng)熱聲不穩(wěn)定性以及控制的研究。在國際SCI期刊發(fā)表論文300 余篇，出版英文專著4本，英文教材1本（第八版），專利 5 項(xiàng)，擔(dān)任國際和國內(nèi)多個(gè)期刊的主編或副主編，SCOPUSH-因子6。

報(bào)告內(nèi)容：Self-sustained thermoacoustic oscillations as observed in low-emission combustion-involved gas turbines and aero-engines involve complicated thermal-fluid-acoustics interaction and rich nonlinear dynamics. Such pulsating oscillations are known as thermoacoustic instability. When it occurs, large-amplitude limit cycle oscillations (LCOs) of thermodynamic parameters are frequently observed. LCOs could cause overheating, flame flashback, and even engine failures. Thus, it is critical to understand and predict the generation mechanisms, nonlinear dynamics behaviors and then develop corresponding control approaches to prevent or control the onset of such instabilities. For this, we develop and extend the conventional Van der Pol (VDP) oscillators by integrating PINNs (Physics-informed neural networks) algorithm with a modeled nonlinear Rijke-type thermoacoustic combustor. The theoretical Rijke tube system (with Galerkin expansion and modified King’s Law implemented) and a CFD simulation model are applied to provide ‘training/calibration data’ for the EVDP (extended VDP)-PINNs model. The optimized EVDP oscillators are confirmed to be capable to capture the key nonlinear characteristics by comparing the transient growth behaviors of thermodynamic perturbations and LCOs’ amplitude and frequency. Further investigations are conducted to obtain Hopf bifurcation and amplitude death (AD) characteristics. Comparison is then made to the coupled EVDP systems. Quite similar Hopf bifurcation features, but differences in regions of AD, are observed In general, we demonstrate an applicable approach to intelligently ‘learn’ a nonlinear thermoacoustic system and to create reliable EVDP oscillator systems, which have great potential to contribute to the development and testing of control approaches, such as the coupling described above, which may replace costly experimental tests.