Cuckoo harmony search mechanism-based IIR (infinite impulse response) digital filter generating method

Abstract

The present invention provides a cuckoo harmony search mechanism-based IIR (infinite impulse response) digital filter generating method. Initialization is carried out, the fitness value of each cuckoo harmony in a cuckoo harmony memory bank is calculated, and the situational knowledge and normative knowledge of a belief space are initialized; a cuckoo harmony tone is randomly selected from the cuckoo harmony memory bank, if rand1 is smaller than PAR, fine adjustment is performed on the cuckoo harmony tone; if rand1 is larger than PAR, the cuckoo harmony tone is updated; the fitness value of the new cuckoo harmony in the cuckoo harmony memory bank is larger than the largest fitness value of the cuckoo harmonies in the cuckoo harmony memory bank, the new cuckoo harmony is replaced; the cuckoo harmonies in the cuckoo harmony memory bank are changed randomly, the fitness values of the cuckoo harmonies in the cuckoo harmony memory bank are calculated, a cuckoo harmony with a small fitness value is selected, and the situational knowledge and normative knowledge of the belief space are updated; and an optimal cuckoo harmony in the situational knowledge, namely, the parameter of an IIR (infinite impulse response) digital filter, is outputted cyclically and iteratively. The method has the advantages of fast convergence speed and good performance.

Description

technical field [0001] The invention relates to a method for generating an IIR digital filter. Background technique [0002] In the field of digital processing, the design of digital filter is an extremely important research direction. A digital filter refers to a device whose input and output are both digital signals, which change the relative proportion of the frequency components contained in the input signal or filter out certain frequency components through a certain operational relationship. Compared with traditional analog filters, digital filters have many advantages such as high precision, strong stability, light weight, small size, and no need for strict impedance matching. Digital filters can be classified into finite impulse response digital filters and infinite impulse response (Infinite Impulse Response, IIR) digital filters from the realized network structure or from the unit impulse response classification. As we all know, the IIR digital filter is very imp...

AI Technical Summary

Problems solved by technology

However, the particle swarm algorithm is easy to fall into the local optimal solution, and the performance fluctuates greatly.

Zhang Gexiang and others published "An Effective IIR Digital Filter Optimal Design Method" in "Signal Processing" (2004, Vol.20, No.2), using quantum genetic algorithm to design IIR digital filter, but this will be discrete The way intelligent computing methods are used to solve real variable problems cannot achieve good results

[0004] Because the above methods are all nonlinear solution methods, it is very easy to fall into local extremum during the solution process, and it is difficult to obtain the global optimal solution

Moreover, the existing IIR digital filter design based on intelligent calculation seldom considers various contradictory factors, such as the maximum fluctuation in the passband and the minimum attenuation in the stopband, so its application range is limited.

Images