With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting m...With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.展开更多
We deployed four geo-electric monitoring stations in Sichuan and Yunnan provinces from 2004, using the new generation of equipment (PS-100) and technologies to capture the HRT wave earthquake precursor. Before the Wen...We deployed four geo-electric monitoring stations in Sichuan and Yunnan provinces from 2004, using the new generation of equipment (PS-100) and technologies to capture the HRT wave earthquake precursor. Before the Wenchuan Ms8.0 earthquake, we recorded the HRT wave precursor at the only operating station in Hongge (HG, Δ=465 km) and found that significant impending signal had been recorded at the station in the early morning ( 0―5 am) of 12th of May, 2008. The precursor for this earthquake is consistent with precursors recorded for other strong earthquakes. The measured physical properties (geo-resistivity and telluric-current) show tidal wave period oscillations from several days to several months before the earthquakes and the amplitude of such HT oscillation increases significantly towards the occurrence of an earthquake. These HT and RT waves from the epicenter have a causal relationship with the earthquakes that happened several days later. The arrival time of two RT waves is proportional to the distance from the station to the epicenter. The estimated natural decay of the amplitude is correlated with the natural period (T0) of the earthquake fault, which is proportional to the fault length. From this relationship, we can predict the earthquake magnitude. For magnitude 6―9 earthquakes, the natural period is about 1―6 hours. Such oscillation comes from the epicenter area and they can propagate several thousand kilometers in the Earth's crust. Before a strong earthquake in the shallow crust, the conductive pore fluid will experience major changes before the fault rapture. Such fluid change will emit an oscillation in the pore fluid pressure. This is the mechanism for the HRT wave generation. Since the China Earthquake Administration funded the HRT wave short-term earth-quake prediction project in 2003, the first record of HRT precursor wave has been recorded from the 2004-12-26 Sumatra Mw9.0 earthquake with the largest epicentre distance Δ=2900 km. Thereafter, we have captured HRT waves from more than twenty strong earthquakes, which are well-matched and show repeatability, consistency and regularity. All our observation with the HRT waves demonstrate that HRT wave precursors to earthquakes indeed exist. Strong earthquakes can be predicted and short-term and impending earthquake prediction is achievable in the very near future. From all the observations, including the ones at HG station from Wenchuan Ms8.0 earthquake, we conclude that using HRT wave to predict earthquakes is feasible.展开更多
Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affect...Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affected by the lack of sample data.The peaks over threshold(POT)method and compound extreme value distribution(CEVD)theory are effective methods to expand samples,but they still rely on long-term sea state data.To construct a probabilistic model using shortterm sea state data instead of the traditional annual maximum series(AMS),the binomial-bivariate log-normal CEVD(BBLCED)model is established in this thesis.The model not only considers the frequency of the extreme sea state,but it also reflects the correlation between different sea state elements(wave height and wave period)and reduces the requirement for the length of the data series.The model is applied to the calculation of design wave elements in a certain area of the Yellow Sea.The results indicate that the BBLCED model has good stability and fitting effect,which is close to the probability prediction results obtained from the long-term data,and reasonably reflects the probability distribution characteristics of the extreme sea state.The model can provide a reliable basis for coastal engineering design under the condition of a lack of marine data.Hence,it is suitable for extreme value prediction and calculation in the field of disaster prevention and reduction.展开更多
基金funded by Liaoning Provincial Department of Science and Technology(2023JH2/101600058)。
文摘With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.
文摘We deployed four geo-electric monitoring stations in Sichuan and Yunnan provinces from 2004, using the new generation of equipment (PS-100) and technologies to capture the HRT wave earthquake precursor. Before the Wenchuan Ms8.0 earthquake, we recorded the HRT wave precursor at the only operating station in Hongge (HG, Δ=465 km) and found that significant impending signal had been recorded at the station in the early morning ( 0―5 am) of 12th of May, 2008. The precursor for this earthquake is consistent with precursors recorded for other strong earthquakes. The measured physical properties (geo-resistivity and telluric-current) show tidal wave period oscillations from several days to several months before the earthquakes and the amplitude of such HT oscillation increases significantly towards the occurrence of an earthquake. These HT and RT waves from the epicenter have a causal relationship with the earthquakes that happened several days later. The arrival time of two RT waves is proportional to the distance from the station to the epicenter. The estimated natural decay of the amplitude is correlated with the natural period (T0) of the earthquake fault, which is proportional to the fault length. From this relationship, we can predict the earthquake magnitude. For magnitude 6―9 earthquakes, the natural period is about 1―6 hours. Such oscillation comes from the epicenter area and they can propagate several thousand kilometers in the Earth's crust. Before a strong earthquake in the shallow crust, the conductive pore fluid will experience major changes before the fault rapture. Such fluid change will emit an oscillation in the pore fluid pressure. This is the mechanism for the HRT wave generation. Since the China Earthquake Administration funded the HRT wave short-term earth-quake prediction project in 2003, the first record of HRT precursor wave has been recorded from the 2004-12-26 Sumatra Mw9.0 earthquake with the largest epicentre distance Δ=2900 km. Thereafter, we have captured HRT waves from more than twenty strong earthquakes, which are well-matched and show repeatability, consistency and regularity. All our observation with the HRT waves demonstrate that HRT wave precursors to earthquakes indeed exist. Strong earthquakes can be predicted and short-term and impending earthquake prediction is achievable in the very near future. From all the observations, including the ones at HG station from Wenchuan Ms8.0 earthquake, we conclude that using HRT wave to predict earthquakes is feasible.
文摘Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affected by the lack of sample data.The peaks over threshold(POT)method and compound extreme value distribution(CEVD)theory are effective methods to expand samples,but they still rely on long-term sea state data.To construct a probabilistic model using shortterm sea state data instead of the traditional annual maximum series(AMS),the binomial-bivariate log-normal CEVD(BBLCED)model is established in this thesis.The model not only considers the frequency of the extreme sea state,but it also reflects the correlation between different sea state elements(wave height and wave period)and reduces the requirement for the length of the data series.The model is applied to the calculation of design wave elements in a certain area of the Yellow Sea.The results indicate that the BBLCED model has good stability and fitting effect,which is close to the probability prediction results obtained from the long-term data,and reasonably reflects the probability distribution characteristics of the extreme sea state.The model can provide a reliable basis for coastal engineering design under the condition of a lack of marine data.Hence,it is suitable for extreme value prediction and calculation in the field of disaster prevention and reduction.
