The Vehicle Audio Blind Signal Separation And Genetic Algorithm

This thesis is focused on the separation vehicle acoustic signal. Because of the complex transportation environment, the propagation of the signal has multipath effect. It is very difficult to describe them with simple mathematical models accurately. Blinding Signal Separation (BSS) method, however, can greatly reduce the errors to the separation results, caused by the signal propagation model and receiving arrays. This thesis reviewed the present research situation of BSS systematically and discussed several traditional BBS algorithms. It is difficult to insure globe convergence for regular BSS algorithms because they are easily trapped into local optimum, which can result in error of separation. This research associates genetic algorithm with traditional BSS and uses global optimize feature of genetic algorithm. This new BSS algorithm is applied to the separation of acoustic signals of lorry, saloon, car, microbus and fanning vehicle, collected by array microphones. The results proved the capability of the algorithms to separate single vehicle signal from multi-vehicle acoustic signals. Using the acoustic noise signal generated by driving motor vehicles to examine the traffic value is a novel and promising method.