2 results about "Pattern correlation" patented technology

This invention belongs to the field of soft measurement modeling technology and discloses a soft measurement modeling method based on mode-related spatiotemporal diffusion generation, which includes the following steps: (1) acquiring data of multi-mode dynamic processes; (2) data partitioning and preprocessing operations; (3) establishing a mode-related spatiotemporal diffusion model and generating virtual samples; (4) predicting pressure variables of three-phase flow processes and evaluating model performance. This invention proposes a soft measurement modeling method based on mode-related spatiotemporal diffusion generation. By using the DSTN-Net noise prediction network to capture the dependence of dynamic data in the time and space dimensions, the mode learner learns the multi-mode distribution characteristics and distinguishes the data distribution of different modes, which can generate virtual samples with high similarity to the original samples, thereby improving the prediction performance of the soft measurement model in the case of small samples.

The invention relates to the technical field of mine safety and disaster prevention and control, in particular to an intelligent dangerous omen identification and early warning method for deep coal mine composite geologic body chain type disasters. The method comprises the steps that a chain type disaster evolution unit is introduced, stress, hydraulic power and structural response characteristics are comprehensively considered under mining disturbance constraints, and a composite geologic body analysis unit with a clear action boundary, a main control structure level and a disaster evolution path is constructed; carrying out directional collection, state reconstruction and co-evolution analysis on multi-source heterogeneous sensing information on the basis of the unit, and converting original monitoring data into an insurance omen generation variable; mode association identification is carried out based on steady-state risk omen variables, and intelligent mapping from risk omen to disaster modes is realized; and dynamically determining an insurance mega threshold in combination with a chain type disaster mode, and performing correction by fusing a mechanism model to form a disaster grade output and early warning closed loop. According to the invention, early identification, intelligent early warning and decision support of deep coal mine composite geologic body chain disasters are realized.