Hydraulic turbine system identification and predictive control based on GASA-BPNN

Based on the characteristics of nonlinearity,multi-case,and multi-disturbance,it is difficult to establish an accurate parameter mod-el on the hydraulic turbine system which is limited by the degree of fitting between parametric model and actual model,and the design of con-trol algorithm has a certain degree of limitation.Aiming at the modeling and control problems of hydraulic turbine system,this paper proposes hydraulic turbine system identification and predictive control based on genetic algorithm-simulate anneal and back propagation neural network(GASA-BPNN),and the output value predicted by GASA-BPNN model is fed back to the nonlinear optimizer to output the control quantity.The results show that the output speed of the traditional control system increases greatly and the speed of regulation is slow,while the speed of GASA-BPNN predictive control system increases little and the regulation speed is obviously faster than that of the traditional control system.Compared with the output response of the traditional control of the hydraulic turbine governing system,the neural network predictive control-ler used in this paper has better effect and stronger robustness,solves the problem of poor generalization ability and identification accuracy of the turbine system under variable conditions,and achieves better control effect.

Paired quasi-periodic pulsations of hard X-ray emission in a solar flare

We investigate high time resolution data obtained by the Gravitational wave high-energy Electromagnetic Counterpart All-sky Monitor(GECAM)during the flare event on 2022 April 21 at 01:52 UT.Several subpeaks with durations of 4-6 s have been detected in the hard X-ray precursor phase,and the key feature is that they appear in pairs and seem like double-peak struc-tures.These subpeaks are rarely observed in hard X-ray band and confirmed by the microwave obtained by Nobeyama Radio Polarimeters(NoRP)and Radio Solar Telescope Network(RSTN).While an exponential function can describe the continuum component of the time profile from the precursor to part of the impulsive phase.The periods of quasi-periodic pulsations(QPPs)are detected to be about 7.3 and 12.8 s for the precursor and impulsive phase,respectively,with at least 95%confidence level.The paired QPPs are assumed to be double-peak QPPs and then the scenario of current loop coalescence model is found to be in good agreement with our observation.The precursor phase can be interpreted as the oscillating coalescence of two islands,while the impulsive phase can be interpreted as more islands to coalesce one by one to form larger islands.