Landslide time prediction method based on APSO-HMM

The invention discloses a landslide time prediction method based on APSO-HMM, and the method comprises the steps: 1, carrying out the preprocessing of collected landslide full-period displacement data, and carrying out the multi-state division of the collected displacement data in a time sequence di...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	WAN JIASHAN, WU JINHUA, YU WANFENG, PAN XULEI
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	ANALOGOUS ARRANGEMENTS USING OTHER WAVES CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES MEASURING MEASURING ANGLES MEASURING AREAS MEASURING IRREGULARITIES OF SURFACES OR CONTOURS MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS PHYSICS RADIO DIRECTION-FINDING RADIO NAVIGATION SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR TESTING
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The invention discloses a landslide time prediction method based on APSO-HMM, and the method comprises the steps: 1, carrying out the preprocessing of collected landslide full-period displacement data, and carrying out the multi-state division of the collected displacement data in a time sequence direction; step 2, training the landslide displacement data subjected to state division by using a Baum-welch algorithm, and training and constructing a landslide evolution state model APSO-HMM by using adaptive particle swarm optimization hidden Markov model parameters with disturbance factors; and step 3, the landslide evolution state model performs state decoding on the real-time acquired data by using a Viterbi algorithm to obtain a state sequence corresponding to the time sequence, and takes the current estimated state as the input of a Dijkstra algorithm, so that the possible occurrence time of the landslide is pre-judged. According to the method, the initial parameters of the hidden Markov model are optimized.