Search scope:
排序: Display mode:
Hui Liu, Zhihao Long, Zhu Duan, Huipeng Shi
Engineering 2020, Volume 6, Issue 8, Pages 944-956 doi: 10.1016/j.eng.2020.05.009
Particulate matter with an aerodynamic diameter no greater than 2.5 μm (PM2.5) concentration forecasting is desirable for air pollution early warning. This study proposes an improved hybrid model, named multi-feature clustering decomposition (MCD)–echo state network (ESN)–particle swarm optimization (PSO), for multi-step PM2.5 concentration forecasting. The proposed model includes decomposition and optimized forecasting components. In the decomposition component, an MCD method consisting of rough sets attribute reduction (RSAR), k-means clustering (KC), and the empirical wavelet transform (EWT) is proposed for feature selection and data classification. Within the MCD, the RSAR algorithm is adopted to select significant air pollutant variables, which are then clustered by the KC algorithm. The clustered results of the PM2.5 concentration series are decomposed into several sublayers by the EWT algorithm. In the optimized forecasting component, an ESN-based predictor is built for each decomposed sublayer to complete the multi-step forecasting computation. The PSO algorithm is utilized to optimize the initial parameters of the ESN-based predictor. Real PM2.5 concentration data from four cities located in different zones in China are utilized to verify the effectiveness of the proposed model. The experimental results indicate that the proposed forecasting model is suitable for the multi-step high-precision forecasting of PM2.5 concentrations and has better performance than the benchmark models.
Keywords: PM2.52.5浓度预测 PM2.52.5浓度聚类 经验小波分解 多步预测
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Engineering 2021, Volume 7, Issue 12, Pages 1751-1765 doi: 10.1016/j.eng.2020.10.023
Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.
Keywords: Dissolved oxygen concentrations forecasting Time-series multi-step forecasting Multi-factor analysis Empirical wavelet transform decomposition Multi-model optimization ensemble
Wang Chengmin
Strategic Study of CAE 2009, Volume 11, Issue 6, Pages 107-110
Is earthquake predictable? This question has been discussed a lot by earthquake researchers and common people after the Wenchuan Earthquake.The specialists in Chinese Earthquake Prediction Consultation Committee started the aftershock prediction research after the earthquake to support emergency rescue and disaster relief with practical action.From May 15 to August 15, the committee formally reported prediction results for 3 times and the three strong aftershocks, i.e.M 6.0 earthquake on May 18 in Jiangyou, M 6.4 earthquake on May 25 in Qingchuan and M 6.1 earthquake on August 1 in Beichuan, have been correctly predicted.Through predicting aftershock isn't so difficult as predicting main shock, those people who think earthquake can be predicted after decades of generations and despise the academic viewpoint that earthquake is predictable should think over the fact that the prediction of all three aftershocks was correct without any miss report, and treat the academic viewpoint equally.
Keywords: Wenchuan Earthquake aftershock of Wenchuan Earthquake earthquake short -impending prediction
基于ARIMA和Kalman滤波的道路交通状态实时预测 Article
东伟 徐,永东 王,利民 贾,勇 秦,宏辉 董
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 287-302 doi: 10.1631/FITEE.1500381
Keywords: ARIMA模型;Kalman滤波;建模;训练;预测
Research on Nonlinear Combination Forecasting Approach Based on BP-AGA
Wang Shuo,Zhang Youfu,Jin Juliang
Strategic Study of CAE 2005, Volume 7, Issue 4, Pages 83-87
A nonlinear combination forecasting model was established by using neural network and accelerating genetic algorithm (AGA) in the paper. AGA was used to optimize the network parameters as BP approach was slow with training network. Optimization results of AGA were taken as original values of BP approach, the network was trained with BP approach. Network convergence rate was increased with running BP approach and AGA alternately. Meanwhile the part least problem was improved. Examples were presented finally, as a result, the forecasting precision high in evidence.
Keywords: neural network accelerating genetic algorithm nonlinear combination forecasting forecasting precision
Discussions in prediction and precaution about haze
Zhang Kui
Strategic Study of CAE 2015, Volume 17, Issue 1, Pages 103-113
Aimed at the harmfulness of low visibility weather, using digital information method found the relationship between occurrence, development of haze and geothermal, and the change of atmospheric structure characteristics. Prediction and precaution of haze need to correctly grasp tumble state of the lower atmosphere near the earth and thermal structural features. The formation of haze both has anthropogenic emissions also has the release of underground pollutants and dirty gas caused by natural geothermal. And geothermal can be taken as premonitory information of haze weather forecast. To improve the atmospheric environment, people need to improve emissions technology, also need to study the natural sources of pollution problems.
Keywords: visibility; haze; digital information prediction method; precaution
Technically feasible approach to earthquake prediction
Liu Defu,Kang Chunli
Strategic Study of CAE 2009, Volume 11, Issue 6, Pages 159-165
Earthquake prediction is an undertaking of public welfare.But earthquakes cannot be successfully predicted at present due to technological reasons.Earthquake prediction should be studied earnestly to adapt the demand of society for earthquake prediction at present.In order to study the possiblity of predicting the Wenchuan M8.0 Earthquake occurred on May 12,2008, based on the earthquake information itsself, this paper has suggesed a kind of numerical modeling method for predicting the earthquake magnitudes,and a method for predicting seismogenic areas by means of the Outgoing-Long-Wave-Radiation (OLR) information of satellite remote sensing. The results show that it is a technically feasible approach.
Keywords: earthquake OLR numerical modeling predicting
Analysis of US National Research Council’s Persistent Forecasting System of Disruptive Technologies
Zhang Xiaolin
Strategic Study of CAE 2018, Volume 20, Issue 6, Pages 117-121 doi: 10.15302/J-SSCAE-2018.06.019
The National Research Council’s (NRC) report on Persistent Forecasting of Disruptive Technologies analyzes the key issues of disruptive technology forecasting and proposes an ideal persistent forecasting system model. On this basis, the paper summarizes the connotation and challenges of disruptive technology forecasting, presents the attributes of the ideal persistent forecasting system, and analyzes the system model and its functions. Finally, the enlightenment of the research on disruptive technology forecasting is proposed, thus to provide reference for relevant research work in China.
Keywords: disruptive technologies persistent forecasting ideal forecasting system
Review on the prediction before the Wenchuan Earthquake
Guo Zengjian,Guo Anning
Strategic Study of CAE 2009, Volume 11, Issue 6, Pages 166-168
According to the index of solar activity we predicted in 2006 that during 2007 ~2008 an earthquake M >7 will possibly occur in segment between Tianshui and Kangding.Based on the flood-earthquake chain along the latitude circle of 30°,we predicted in the end of 2007 that an earthquake M6 ~7 will possibly occur in Kangding region in 2008.
Keywords: earthquake prediction valley of solar activity flood-earthquake chain
Dai Shuhe
Strategic Study of CAE 1999, Volume 1, Issue 3, Pages 63-68
The universe of methodology for predicting the damage to structural materials and remaining life of process equipment is a branch of subject of a newly developing discipline - FORECASTING. The technique for predicting the damage to structural materials and remaining life of process equipment based on the use of experience of multi-discipline is a comprehensive technology in the field of modern technical management of facilities. Some contents of this technique have been selected among the subjects of emerging technologies to be developed over this century.
In this study, a series of new techniques for predicting the damage to structural materials and remaining life of porcess equipment have been developed, which are based on principles of approximate and plausible reasonings for uncertain parameters of fuzziness by fuzzy set theory; of quantitative metallographic technique by methods of stereoscopy and visual treatment technique.The technique proposed is of great significances for ensuring safe, high efficiency and long period operations in modernized large-scale and high parameter facilities of chemical, petrochemical, nuclear and electric power plants.
The main contributions of the technique proposed in this work are on engineering applications which provide major benefits in economics and society. The technique will be a bright future in use.
Keywords: damage to structural materials life prediction process equipment
Analysis of GM(1,1)Model and Its Application in Fire Risk Prediction
Chen Zijin,Wang Fuliang,Lu Shouxiang
Strategic Study of CAE 2007, Volume 9, Issue 5, Pages 91-94
Theoretical analysis of grey prediction model GM(1, 1) is present in this paper. Monotonicity of predicted value and its variation tendency predicted by GM(1, 1)model is proved. Based on the monotonicity of predicted value and its variation tendency, applicability criterion of GM(1, 1) is brought forward. Example applications of the criterion in fire risk grey prediction are discussed.
Keywords: fire forecast GM(1 1) rate of the fire injured
Statistic and review of China’s earthquake prediction score
Gao Jianguo
Strategic Study of CAE 2009, Volume 11, Issue 6, Pages 129-131
Earthquake is difficult to forecast, but it doesn't happen without signs or unknown,our country has the case summary for every large earthquake.Statistics clearly show that there have been 77 predictions about middle -term, short -term or imminent earthquakes in the last 40 years.Therefore, success in Chinese earthquake prediction could not be denied only because of failure in Wenchuan Earthquake prediction.China's earthquake prediction score should be positive,and Wenchuan Earthquake is not a "strange shock" without any precursor.
Keywords: earthquake earthquake prediction nearly 30 years’earthquake prediction statistics in china
Predicting SARS for Guangdong, Beijing and Mainland China 2003 Cases
Wang Jianfeng
Strategic Study of CAE 2003, Volume 5, Issue 8, Pages 23-29
The study is aimed at choosing a better predictive model for the accurate description of SARS in Guangdong, Beijing and Mainland China in 2003. Observation and general experience have shown a sigmoid type of curve consisted of four phases comparable to the phases of the SARS growth in 2003 : an initial lagging period, a period of accelerating change, a period of decelerating change, and a stationary period. In order to model the SARS system, a generalized Logistic growth function has been adopted in the paper. With the officially published data, the main features of evolution of the SARS population size have been obtained using the generalized Logistic growth model by optimizing technique. Then, for getting evolutionary process prediction, several classical S-models such as the Pearl, the Gompertz, Von Bertalanffy, and Richards are tested. The practice of calculations has found that the Gompertz model gives the most accurate results where fitting criteria are estimated as residual sum of squares (RSS).
Keywords: SARS generalized Logistic growth model Gompertz function prediction optimization
Forecast Study on Medium and Long Term Energy Demand in Rural Area of China
Deng Keyun,He Liang
Strategic Study of CAE 2000, Volume 2, Issue 7, Pages 16-21
Rural energy forecast belongs to the category of regional energy forecast. To forecast the demand of energy consumption in rural area of China will be useful for drawing out the rural energy strategy with rural sustainable development. Based on analysis and calculation this paper brings forward the conventional scheme and the strengthening renewable energy utilization scheme.The energy consumption in rural region is mainly divided into two components, i.e. used for economic development and for farmer households living. Following the progress in implementation of the state key project “Small Rural City - township Construction” most of rural population will be urbanized locally. It is expected by the year of 2020 and 2050, there will be about 670 and 480 millions of pepole living in rural area, and in the case of the “strengthening” scheme, the total commodity energy demand is about 1290 and 1632 Mt coal equivalent ,respectively.If the energy consumption in village and town enterprises is not included in two schemes, the total energy demand in rural area will be 970 〜1080 Mt coal equivalent in 2050. The coal consumption will account for 31.7% of the total.
Keywords: rural energy demand forecast
Research of the Exponential Smoothing Technology forForecasting Slope Displacement
Shen Liangfeng
Strategic Study of CAE 2007, Volume 9, Issue 6, Pages 94-97
Exponential smoothing is an efficient method for forecasting and decision-making. The forecasting model of exponential smoothing to forecast the displacement at Observation Point 5 of certain city hazardous landslide is applied in this paper. According to the characteristics of observation forecast formula with linear trend of the twice exponential smoothing, appropriate formulae calculating at, bt and suitable exponential smoothing value are selected and used to make a forecast. The forecast results show that the errors between the forecast values and the observation values are very little. And it shows that this model may be well applied to the forecast of the displacement in the deformation of slopes.
Keywords: exponential smoothing forecasting slope displacement self-adaptive filtering
Title Author Date Type Operation
A New Model Using Multiple Feature Clustering and Neural Networks for Forecasting Hourly PM2.5 Concentrations, and Its Applications in China
Hui Liu, Zhihao Long, Zhu Duan, Huipeng Shi
Journal Article
A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Journal Article
The scientific faith that earthquake is predictable should be insisted—the successful prediction of three strong aftershocks of Wenchuan Earthquake
Wang Chengmin
Journal Article
Research on Nonlinear Combination Forecasting Approach Based on BP-AGA
Wang Shuo,Zhang Youfu,Jin Juliang
Journal Article
Analysis of US National Research Council’s Persistent Forecasting System of Disruptive Technologies
Zhang Xiaolin
Journal Article
A Study on Methodology for Predicting the Damage to Structural Materials and Remaining Life of Process Equipment
Dai Shuhe
Journal Article
Analysis of GM(1,1)Model and Its Application in Fire Risk Prediction
Chen Zijin,Wang Fuliang,Lu Shouxiang
Journal Article
Forecast Study on Medium and Long Term Energy Demand in Rural Area of China
Deng Keyun,He Liang
Journal Article