Auto-tuning PID generator control system based on artificial neural network

Abstract

The invention is an auto-tuning PID generator control system based on an artificial neural network. The control system mainly comprises an artificial neural network control module, a PID control module, a state detection module, an execution module and a generator output module. Control parameters Kp, Ki and Kd of the PID control module are automatically tuned by the artificial neural network control module. With the adoption of the technical scheme provided by the invention, the control system can automatically adapt to change in system parameters such as the generator state or the external environment; the robustness and the operational reliability of the control system are greatly improved; the control precision is greatly improved; the energy utilization efficiency of the generator set is increased; the exhaust gas emission of the generator is reduced; and the noise and the vibration are reduced. In addition, the control system adopts the artificial neural network training and the identification-control separation mode, so that the cost of the control system is greatly reduced, and the control system has a high cost performance.

Description

technical field [0001] The invention relates to a generator control system, in particular to an artificial neural network-based self-tuning PID digital generator intelligent control system and a corresponding method. Background technique [0002] The generator set is mainly composed of an engine, a generator and an electronic control system, which can convert the chemical energy of fuel into electrical energy, and has a wide range of applications, such as: emergency electricity, field work, disaster relief, outdoor life and travel, yacht and vehicle autonomy Backup power supply, mobile communication base station and many other occasions. [0003] On the basis of traditional power generation technology, the digital generator set using multi-pole permanent magnet generator introduces power electronics technology, expands the generator technology into generator power supply technology, and realizes the high performance of the generator. The core component of the digital genera...

AI Technical Summary

Problems solved by technology

However, there are many imperfections in conventional PID control, the most important of which is the PID controller K p , K i and K d The problem of setting the three parameters, and once the setting is calculated, these three parameters are fixed in the whole control process, but in practice, because the combustion process of the engine mixture is very complicated, especially when the state of the engine parts When the manufacturing error is large, more complex nonlinear time-varying system characteristics will appear. The output torque and speed of the engine are affected by many factors and cannot be modeled accurately. The calculated PID controller is set in a certain state and environment Parameters, once the working environment or the state of the generator set parts change during mass production, these set controller parameters are not applicable, and it is difficult for the conventional PID control system to achieve the best control effect, and the digital generator set is prone to Problems such as stalling, traveling, and large deviation of steady-state speed

Images