عنوان مقاله [English]
Driving cycles are data in terms of the speed and the time that are used in the vehicle design, the transportation and the fuel management, the explanation and the improvement of standard indicators. In this study, four combined driving cycles were extracted based on real data. To achieve this goal, the data collection was performed using a passenger car with a gasoline engine by the car chasing method, on the way from Tehran to Amol, under real driving conditions. Then, in MATLAB software, using support vector machine and K-means algorithms, by considering mid-range and mean values as group centers, a code was generated to create the desired cycle and calculate its characteristic parameters, such as the average speed and the percentage of the car travel time in idle, cruise, accelerating and decelerating conditions. Then, these cycles were compared based on the mean relative error, the root mean square error and the Chi-square test. The results showed that although the cycles extracted by the support vector machine were closer to the allowable time interval (less than 1800 seconds), the cycle extracted by the K-means algorithm, and the mean as the centers of the generated categories, recorded the least errors. This cycle, in addition to spending most of its time in the accelerated motion, reported a greater amplitude of acceleration and velocity fluctuations than other compared cycles.