Boiler combustion optimization method based on adaptive neuro-fuzzy PID control

Abstract

The invention discloses a boiler combustion optimization method based on adaptive neuro-fuzzy PID control. The boiler combustion optimization method comprises the following steps: (1) determining thestructure of an adaptive neuro-fuzzy inference system (ANFIS) which consists of three dual-input single-output Sugeno systems connected in parallel, wherein input comprises an error e and an error change ec and output is the change amount (delta Kp, delta Ki and delta Kd) of three parameters of a PID controller; (2) fuzzifying the input and the output, determining antecedent parameters of an initial ANFIS, setting training parameters, and training the initial ANFIS; (3) combining the ANFIS with the PID controller to form an adaptive neuro-fuzzy PID controller, obtaining parameters (Kp, Ki andKd) of the adaptive neuro-fuzzy PID controller, and finally applying the output of the adaptive neuro-fuzzy PID controller to a frequency converter to complete the control of rotational speed of fans.Therefore, the boiler combustion optimization method based on the adaptive neuro-fuzzy PID control can achieve the objectives of improving combustion efficiency, achieving combustion optimization, saving energy and reducing emission.

Description

technical field [0001] The invention belongs to the field of intelligent control and automatic control, and in particular relates to a boiler combustion optimization method based on adaptive neurofuzzy PID control. Background technique [0002] Boiler is a kind of energy conversion equipment, which is indispensable in thermal power generation, mining, ships, civil heating, etc. As one of the three major main equipments of thermal power plants, power plant boilers will not only reduce the benefits of thermal power plants, waste coal resources, and produce NO x It will also cause environmental pollution. [0003] The boiler combustion system of a thermal power plant is the basis of the entire follow-up production, and whether the air-to-coal ratio is reasonable or not determines whether the combustion is complete. On the one hand, the boiler combustion system is a multivariable, nonlinear, strong coupling, strong interference, and large lag system, and its precise mathematic...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a boiler combustion optimization method based on adaptive neuro-fuzzy PID control, using adaptive neuro-fuzzy inference systems (Adaptive Neuro-Fuzzy Inference Systems, referred to as ANFIS), to solve the PID control in most boiler combustion systems at present Parameters cannot be self-tuned, and the degree of membership in fuzzy PID control is strongly dependent on expert knowledge and experience

Images