Prediction model for the water jet falling point in fire extinguishing based on a GA-BP neural network

Abstract

Past research on the process of extinguishing a fire typically used a traditional linear water jet falling point model and the results ignored external factors, such as environmental conditions and the status of the fire engine, even though the water jet falling point location prediction was often associated with these parameters and showed a nonlinear relationship. This paper constructed a BP (Back Propagation) neural network model. The fire gun nozzle characteristics were included as model inputs, and the water discharge point coordinates were the model outputs; thus, the model could precisely predict the water discharge point with small error and high precision to determine an accurate firing position and allow for the timely adjustment of the spray gun. To improve the slow convergence and local optimality problems of the BP neural network (BPNN), this paper further used a genetic algorithm to optimize the BPNN (GA-BPNN). The BPNN can be used to optimize the weights in the network to train them for global optimization. A genetic algorithm was introduced into the neural network approach, and the water jet landing prediction model was further improved. The simulation results showed that the prediction accuracy of the GA-BP model was better than that of the BPNN alone. The established model can accurately predict the location of the water jet, making the prediction results more useful for firefighters.

Two-Stage Water Jet Landing Point Prediction Model for Intelligent Water Shooting Robot

“…Simulation verification is to verify the correctness of the proposed method in the paper, and to check whether the online fine-tuning algorithm can adjust the parameters of the model correctly and in real-time according to the loss. In addition, we also compared the performance of the model with the neural network method in [ 25 ]; the test on the real platform is to verify the actual effect of the proposed two-stage model.…”

“…Methods based on deep learning generally use neural networks to fit the model, which reduces the amount of manual calculation and is simple to implement. Zhang et al [ 25 ] and Li et al [ 26 ] used the back-propagation neural network model to predict the landing point of the water jet, taking into account the muzzle height, jet pressure, wind direction, and other characteristics of the water jet and used them as the input of the model, the model outputs the coordinates of the jet’s landing point. They designed a three-layer network model and changed the number of nodes in the hidden layer many times to find the optimal solution for the model’s calculation speed and accuracy.…”

“…They designed a three-layer network model and changed the number of nodes in the hidden layer many times to find the optimal solution for the model’s calculation speed and accuracy. Zhang et al [ 25 ] also used genetic algorithms to optimize the network model to solve the problems of slow model convergence and local optimal solutions. Deep learning methods are highly accurate in specific environments, but cannot respond fast enough to changing external environments.…”

Estimating the Influence of the Wind Exposure on the Motion of an Extinguishing Substance

“…In [8], a neural network was used to construct a model of water jet supply. The selection of network parameters was carried out using a genetic algorithm.…”

“…into the expression for y(t) from (5) let's finally obtain determine the maximum range x m of the extinguishing agent supply. For this purpose, let's rewrite(8) as follows m .The quantity z for a given a priori value of the parameter a is determined by the solution of the transcendental equation f(z)=ga -2 [z+ln(1-z)].If a=(0.15÷0.45) s -1 ; h=(1.0÷1.5), then solutions for (10) can be represented as…”