3results about How to "Fewer input parameters" patented technology

The application discloses a sintering flue gas CO concentration optimization control method based on key influencing factor identification, and belongs to the technical field of flue gas emission reduction, and comprises the following steps: acquiring sintering production process data and corresponding sintering flue gas CO emission concentration measured values, and constructing a model sample set after pretreatment; constructing an improved grey wolf optimization algorithm, optimizing parameters of a regression algorithm, and building a sintering process CO concentration soft measurement fitting model based on the optimized regression algorithm; performing feature importance analysis by using a SHAP method, retraining the fitting model after key influencing factors are identified, and obtaining a simplified model; collecting key influencing factor data in real time, predicting CO concentration and gradient by using the simplified model; screening a regulation and control feature item that can make CO concentration decrease the most, fusing gradient descent and PPO reinforcement learning control instructions, and realizing multi-time scale optimization control of CO concentration. The application can accurately predict and efficiently reduce sintering flue gas CO concentration.

The application provides an extreme environment fire spread rate prediction method, device, equipment and medium, which can be applied to the technical field of forest fire prevention and prediction, and the method comprises the following steps: using a pre-constructed combustion experiment platform to perform combustion experiments under different environmental conditions, and obtaining environmental parameters, fuel parameters and actual measured values of fire spread rates under different environmental conditions; a fire spread rate prediction model is constructed, and the prediction model is expressed as a benchmark fire spread rate multiplied by multiple correction terms; the environmental parameters, the fuel parameters and the actual measured values of the fire spread rates obtained through the combustion experiments are used to fit the benchmark fire spread rate in the prediction model and the to-be-fitted parameters contained in each correction term, so that a fitted prediction model is obtained; and the environmental parameters and the fuel parameters of a target region are input into the fitted prediction model, so as to determine a fire spread rate prediction value of the target region.

This application provides a method, apparatus, equipment, and medium for predicting fire spread rate in extreme environments, which can be applied to the field of forest fire prevention and prediction technology. The method includes: conducting combustion experiments under different environmental conditions using a pre-constructed combustion experiment platform to obtain environmental parameters, fuel parameters, and measured values ​​of fire spread rate under different environmental conditions; constructing a fire spread rate prediction model, which is represented as a baseline fire spread rate multiplied by multiple correction terms; fitting the baseline fire spread rate and the parameters to be fitted included in each correction term in the prediction model using the environmental parameters, fuel parameters, and measured values ​​of fire spread rate obtained from the combustion experiment to obtain a fitted prediction model; and inputting the environmental parameters and fuel parameters of the target area into the fitted prediction model to determine the predicted value of the fire spread rate of the target area.