Iwate University

Japan Science and Technology Agency

Japan Science and Technology Corporation

Rion Company Ltd.

National University Corporation, Iwate University

Kiyoshi Nishiyama

Masahiro Sunohara

Makoto Tateno

Nobuhiko Hiruma

Chiho Haruta

A system identification device for performing fast real-time identification for a system from input/output data includes a filter robust to disturbance, by setting the maximum energy gain from the disturbance to a filter error, as an evaluation criterion, smaller than a given upper limit. The filter estimates a state estimation value of a state of the system.

System identification device, system identification method, system identification program, and recording medium recording system identification program

A large-scale sound system or communication system is numerically and stably identified. When an input signal is represented by the M(&#x2266;N)-th order AR model, high-speed Hfiltering can be performed with a computational complex 3N+O(M). A processing section determines the initial state of a recursive equation (S), sets Caccording to an input u(S), determines a variable recursively (S), updates a matrix G, calculates an auxiliary gain matrix K(S), divides it (S), calculates a variable Dand a backward prediction error &#x3b7;(S), calculate a gain matrix K(S), and updates a filter equation of a high-speed Hfilter (S). To reduce the computational complexity, K(:, 1)/(1+&ggr;HK(:, 1)) is directly used as the filter gain K.

System identification method and program, storage medium, and system identification device

It is possible to establish an estimation method capable of logically and optimally deciding a forgetting coefficient and develop an estimation algorithm and a high-speed algorithm which are numerically stable. Firstly, a Processing section reads out or receives an upper limit value &#x3b3;from a storage section or an input section (S). The.processing section decides a forgetting coefficient &#x3c1; by equation (15) (S). After this, according to the forgetting coefficient &#x3c1;, the processing section executes a hyper Hfilter of equations (10-13) (S). The processing section () calculates the existence condition of equation (17) (or equation (18) which will be given later) (S). When the existence condition is satisfied at all the times (S), &#x3b3;is decreased by &#x394;&#x3b3; and the same processing is repeated (S). On the other hand, when the existence condition is not satisfied by a certain &#x3b3;(S), the &#x394;&#x3b3; is added to the &#x3b3;and the sum is output to an output section and/or stored in the storage section as an optimal value &#x3b3;of the &#x3b3;(S).

System estimation method and program, recording medium, and system estimation device

Quick real-time identification and estimation of a time-non-varying or time-varying system. A new Hevaluation criterion is determined, a fast algorithm for a modified Hfilter based on the criterion is developed, and a quick time-varying system identifying method according to the fast Hfiltering algorithm is provided. By the fast Hfiltering algorithm, a time-varying system sharply varying can be traced with an amount of calculation O(N) per unit time step. The algorithm completely agrees with a fast Kalman filtering algorithm at the extreme of the upper limit value. If the estimate of impulse response is determined, a pseudo-echo is sequentially determined from the estimate and subtracted from the real echo to cancel the echo. Thus an echo chancellor is realized.

Growing community of inventors

Iwate, Japan

Kiyoshi Nishiyama