Phase Angle and Amplitude PID Adaptive Method Based on BP Neural Network 3D Magnetic Characteristic Measurement

Abstract

The invention discloses a phase angle amplitude PID adaptive method based on BP neural network three-dimensional magnetic characteristic measurement. In the process of signal processing, this method adopts the frequency domain method, which is easier to control than the time domain method, decomposes each harmonic into the frequency domain, and performs independent closed-loop control on the amplitude and phase angle respectively. Search the amplitude to minimize the error between the output voltage and the expected voltage, and then find the phase angle that minimizes the output error. Using PID can quickly find the appropriate amplitude and phase angle, and then the output waveform vectors in the three directions are synthesized to be A standard spherical or ellipsoidal shape enables the actual waveform to quickly and accurately approach the desired waveform. When the excitation frequency and amplitude change, the weights of the hidden layer and output layer of the neural network will change accordingly, and then the PID parameters will change adaptively with the feedback adjustment process of the waveform, making the magnetic measurement process fast and accurate Greatly improved, greatly reduced response time.

Description

technical field [0001] The invention relates to the fields of artificial neural network and three-dimensional magnetic characteristic measurement, in particular to a phase angle amplitude PID self-adaptive method based on BP neural network three-dimensional magnetic characteristic measurement. Background technique [0002] The three-dimensional magnetic property measurement is to apply a standard three-dimensional magnetic field to the magnetic material through the three-dimensional magnetic property measurement system to obtain the magnetic properties of different materials, including the dependence of the hysteresis loop, magnetic permeability and loss properties on frequency, temperature and other conditions. The research on the three-dimensional magnetic properties of magnetic materials will help to optimize the structural design of the iron core components of electrical equipment and reduce the core loss of transformers and motors. In the measurement of magnetic charact...

AI Technical Summary

Problems solved by technology

However, in waveform feedback control, as the actual output gradually approaches the desired output, the original PID parameters cannot make the error quickly approach the given error range

Especially when the excitation current increases and the excitation frequency increases to a certain extent, the original PID parameters cannot make the output voltage converge to the expected voltage, and will always oscillate around the expected value, affecting the speed and accuracy of magnetic characteristic measurement

Images