BP artificial neuron network's injector performance predicting method based on the use of deep Adaboost algorithm

Abstract

The invention provides a BP artificial neuron network's injector performance predicting method based on the use of deep Adaboost algorithm. The method comprises: collecting relevant parameters of a given injector; according to the neuron network's topological structure, determining the number of the neurons in the neuron network's input layer, the hidden layer and the output layer; inputting samples and starting to train the neuron network created from the step 2 and repeating the training several times; forming a week classifier after each training; recording the error of each training result; creating a strong classification function; synthesizing the weak classifiers into strong classifiers; creating a super-strong classification function according to the corresponding weights assigned according to the prediction result; synthesizing the strong classifiers into a super-strong classifier wherein the super-strong classifier is a deep BP- Adaboost neuron network; acquiring the real-time measurement data of the given injector; and inputting the data to the created and completed BP- Adaboost neuron network to obtain the output vector, or the prediction value. The method of the invention achieves high-precision predictions and consumes a shorter time to do so.

Description

technical field [0001] The invention relates to a method for predicting the performance of an injector, in particular to a method for predicting the performance of an injector based on a BP artificial neuron network using a deep Adaboost algorithm. Background technique [0002] The ejector can be driven by low-grade energy sources such as industrial residual pressure, waste heat, waste heat, solar heat, and geothermal energy to generate a stream of high-pressure fluid, make it pass through the working nozzle to generate a vacuum, and suck in low-pressure fluid. After mixing The pressure of the fluid is increased through the diffuser, and finally a medium-pressure fluid is obtained, that is, the pressure of the low-pressure fluid is increased to achieve the effect of compression. Because of its simple structure, convenient maintenance, low cost, and no need to consume electricity, it has a good energy-saving and emission-reduction effect. Under the background of tight energy ...

AI Technical Summary

Problems solved by technology

However, because the internal flow of the injector is very complicated, including primary congestion, secondary congestion, supersonic flow, various shock waves, fan-shaped diffusion, fluid mixing, etc., the accuracy of the parameters obtained by using the traditional one-dimensional physical model is low, and the effect is relatively low. Poor, the average error is more than 5-10%, and the maximum error can reach more than 15%

If the method of computational fluid dynamics is used, it will take too long and consume manpower and material resources, which is not suitable for design and related cycle research

The above status quo has brought adverse effects on the design and application of injectors, related cycle research and other work

Images