Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama
Neuro-genetic optimization of disc brake performance at elevated temperatures
Апстракт
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 integri...sani 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 netw...ork 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.
Кључне речи:
optimization / neural networks / genetic algorithms / disc brakes / brake performanceИзвор:
FME Transactions, 2014, 42, 2, 142-149Издавач:
- Univerzitet u Beogradu - Mašinski fakultet, Beograd
Финансирање / пројекти:
- Научно-технолошка подршка унапређењу безбедности специјалних друмских и шинских возила (RS-MESTD-Technological Development (TD or TR)-35045)
- Развој, пројектовање и имплементација савремених стратегија интегрисаног управљања оперативним радом и одржавањем возила и механизације у системима аутотранспорта, рударства и енергетике (RS-MESTD-Technological Development (TD or TR)-35030)
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Ćirović, Velimir AU - Smiljanić, Dušan AU - Aleksendrić, Dragan AU - Simović, V. PY - 2014 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2053 AB - 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. AB - 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. PB - Univerzitet u Beogradu - Mašinski fakultet, Beograd T2 - FME Transactions T1 - Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama T1 - Neuro-genetic optimization of disc brake performance at elevated temperatures EP - 149 IS - 2 SP - 142 VL - 42 DO - 10.5937/fmet1402142C ER -
@article{ author = "Ćirović, Velimir and Smiljanić, Dušan and Aleksendrić, Dragan and Simović, V.", year = "2014", 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.", publisher = "Univerzitet u Beogradu - Mašinski fakultet, Beograd", journal = "FME Transactions", title = "Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama, Neuro-genetic optimization of disc brake performance at elevated temperatures", pages = "149-142", number = "2", volume = "42", doi = "10.5937/fmet1402142C" }
Ćirović, V., Smiljanić, D., Aleksendrić, D.,& Simović, V.. (2014). Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama. in FME Transactions Univerzitet u Beogradu - Mašinski fakultet, Beograd., 42(2), 142-149. https://doi.org/10.5937/fmet1402142C
Ćirović V, Smiljanić D, Aleksendrić D, Simović V. Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama. in FME Transactions. 2014;42(2):142-149. doi:10.5937/fmet1402142C .
Ćirović, Velimir, Smiljanić, Dušan, Aleksendrić, Dragan, Simović, V., "Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama" in FME Transactions, 42, no. 2 (2014):142-149, https://doi.org/10.5937/fmet1402142C . .