Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama

Abstract

Osnovni problem u radu kočnica motornih vozila je pad njihovih performansi na povišenim temperaturama u kontaktu frikcionog para kočnice (kočnog diska i disk pločice). Povećanje temperature u kontaktu frikcionog para kočnice često dovodi do pada vrednosti momenta kočenja u toku ciklusa kočenja, a samim tim i do smanjenja izlaznih performansi kočnice. Da bi se obezbedila stabilnost momenta kočenja u toku ciklusa kočenja, razvijen je optimizacioni model na bazi dinamičkih veštačkih neuronskih mreža. Razvijeni model je iskorišćen za modeliranje složenih sinergijskih uticaja koji dovode do pojave triboloških fenomena koji utiču na izlazne performanse disk kočnice. Dinamički optimizacioni neuronski model performansi disk kočnice je razvijen na bazi rekurentnih neuronskih mreža. Model predviđa dinamičku promenu momenta kočenja u zavisnosti od trenutnih vrednosti pritiska aktiviranja kočnice, brzine i temperature u kontaktu frikcionog para u toku ciklusa kočenja. Genetski algoritmi su integrisani sa neuronskim dinamičkim modelom u cilju optimizacije pritiska aktiviranja kočnice koji u toku ciklusa kočenja treba da obezbedi željenu vrednost momenta kočenja. Ovakav hibridni, neuro-genetski, model je pokazao mogućnost uspešne optimizacije vrednosti hidrauličkog pritiska aktiviranja kočnice, potreban da bi se postigle stabilne i maksimizirane izlazne performanse kočnice u toku ciklusa kočenja.

The basic problem of automotive brakes operation is the decreasing of their performance at elevated temperatures in the contact of friction pair (brake disc and brake pad). Increasing of the brake interface temperature often causes decreasing of braking torque during a braking cycle. In order to provide the stable level of braking torque during a braking cycle, the neural network based optimization model of the disc brake performance has been developed. The dynamic neural networks have been employed for modelling of complex synergy of tribological phenomena that affects the final disc brake performance at elevated temperatures. The dynamic optimization neural network model of disc brake performance at elevated temperatures has been developed using recurrent neural networks. It predicts the braking torque versus the dynamic change of the brake actuation pressure, sliding speed and the brake interface temperature in a braking cycle. Genetic algorithms were integrated with the neural network model for optimization of the brake actuation pressure in order to obtain the desired level of braking torque. This hybrid, neuro-genetic model was successfully used in optimization of the brake hydraulic pressure level needed to achieve the maximum and stable brake performance during a braking cycle.