Adaptive Filter Identification Using Periodic Signal Averaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing adaptive identification systems face reduced identification accuracy due to noise disturbances and require increased calculation amounts to achieve comparable accuracy, with the approximate steepest descent algorithm being computationally intensive.
Innovation Solution
An adaptive identification system that generates an identification input signal with a frequency component as an integer multiple of a fundamental frequency, using a moving average and diagonal matrix to update the adaptive filter coefficients, reducing the calculation burden while maintaining identification accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the step size is reduced in the LMS algorithm to avoid decrease in identification accuracy, then identification accuracy is improved, but adaptation speed decreases and it takes time to obtain final identification result
Solution Approach 1:
The invention dynamically adjusts the step size during the adaptation process. Initially, a larger step size is used to achieve fast adaptation, and then the step size is reduced to improve identification accuracy. This dynamic adjustment resolves the contradiction between adaptation speed and identification accuracy by allowing both phases to occur at appropriate times.
Solution Approach 2:
The invention employs periodic updates of the step size parameter based on the convergence state of the adaptive filter. The step size is periodically adjusted from a larger initial value to a smaller final value, creating a periodic action pattern that balances speed and accuracy requirements at different stages of the identification process.
2Loss of time
If an approximate steepest descent algorithm is used to reduce time to obtain final identification result, then adaptation speed is improved, but calculation amount significantly increases compared with LMS algorithm
Solution Approach 1:
The invention applies partial updates to the filter coefficients by only updating certain coefficients at each iteration rather than all coefficients. This partial action reduces the calculation amount per iteration while still achieving convergence, thereby resolving the contradiction between reducing time to obtain results and minimizing calculation amount.
Solution Approach 2:
The invention segments the adaptation process into multiple stages with different update strategies. In early stages, more frequent updates are performed to achieve fast convergence, while in later stages, less frequent updates are sufficient. This segmentation allows the system to achieve fast identification without maintaining high calculation amounts throughout the entire process.
3Adaptability or versatility
If adaptive identification is performed in actual environment with noise disturbance, then the system can operate in practical conditions, but identification accuracy is reduced
Solution Approach 1:
The invention uses feedback mechanisms to monitor the identification accuracy and adaptively adjust the step size and update frequency. When noise disturbance is detected, the feedback control modifies the adaptation parameters to maintain identification accuracy, thereby resolving the contradiction between operational capability in noisy environments and maintaining precision.
Solution Approach 2:
The invention changes key parameters such as step size and update frequency based on the noise level in the actual environment. By detecting noise conditions and adjusting parameters accordingly, the system maintains identification accuracy while operating in practical noisy conditions, resolving the contradiction between adaptability and measurement precision.
Data Source
AI summary
An adaptive identification system, for identifying a propagation system characteristic by an adaptive filter, includes a signal generator that generates an identification input signal including a frequency component of an integer multiple of a fundamental frequency and having a periodicity satisfying a PE condition, a setting unit that sets moving average time to a fundamental period of the identification input signal, and an adaptive algorithm execution unit that uses a moving average value and a diagonal matrix to update a coefficient of the adaptive filter, the moving average value being obtained by calculating a moving average of a cross-correlation vector of a vector of the identification input signal and an observation signal with the moving average time, and the diagonal matrix being obtained by diagonalizing a matrix obtained by calculating a moving average of an autocorrelation matrix of the vector of the identification input signal with the moving average time.