پیوندهای مفید
آمار
| تعداد نشریات | 8 |
| تعداد شماره‌ها | 419 |
| تعداد مقالات | 5,514 |
| تعداد مشاهده مقاله | 6,241,125 |
| تعداد دریافت فایل اصل مقاله | 5,416,794 |
مقایسه عملکرد الگوریتم‌های ماشین بردار پشتیبان و میانگین کی در استخراج چرخه واقعی رانندگی ترکیبی تهران- آمل | ||
| نشریه مهندسی مکانیک امیرکبیر | ||
| مقاله 15، دوره 53، شماره 9، آذر 1400، صفحه 5017-5036 اصل مقاله (2.26 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22060/mej.2021.19222.6980 | ||
| نویسندگان | ||
| تابان مهر قرائتی1؛ علی مومنی موحد1؛ محمد آزادی* 2؛ سید اشکان موسویان3 | ||
| 1دپارتمان مهندسی مکانیک، دانشکده فنی و مهندسی، دانشگاه بین‌المللی امام خمینی، قزوین، ایران | ||
| 2سمنان-مهندسی مکانیک | ||
| 3دانشکده فنی کشاورزی شهریار، دانشگاه فنی و حرفه‌ای | ||
| چکیده | ||
| چرخه‌‌های رانندگی داده‌‌هایی بر حسب سرعت و زمان هستند که از آن‌ها در طراحی خودروها، مدیریت حمل و نقل و سوخت، تبیین و بهسازی شاخص‌های استاندارد استفاده می‌شود. در این پژوهش، چهار چرخه رانندگی ترکیبی بر اساس داده‌‌های واقعی استخراج گردید. برای رسیدن به این هدف، داده‌برداری با استفاده از یک خودروی سواری با موتور بنزین‌سوز به روش تعقیب خودرو، در مسیری از تهران به آمل، تحت شرایط رانندگی واقعی انجام شد. پس از آن در نرم‌افزار متلب، با استفاده از الگوریتم‌های ماشین بردار پشتیبان و میانگین کی و با در نظر گرفتن مقادیر میان‌برد و میانگین به عنوان مراکز دسته‌ها، یک کد برای تولید چرخه‌‌های مورد نظر، و محاسبه پارامترهای مشخصه‌ی آن‌ها، نظیر سرعت متوسط، درصد زمان پیمایش خودرو در حالت‌های درجا، بدون شتاب، شتابگیری مثبت و منفی ایجاد شد. سپس این چرخه‌‌ها بر اساس میانگین خطای نسبی، خطای ریشه میانگین مربع و آزمون مربع چی با یکدیگر مورد مقایسه قرار گرفتند. نتایج نشان داد اگرچه، چرخه‌‌های استخراج شده توسط ماشین بردار پشتیبان به بازه زمانی مجاز (کمتر از 1800 ثانیه) نزدیک‌ترند، اما چرخه استخراج شده توسط الگوریتم میانگین کی و میانگین به عنوان مراکز دسته‌های ایجاد شده، کمترین خطاها را ثبت نموده است. این چرخه علاوه بر آن‌که بیشتر زمان خود را در حال حرکت شتابدار بوده است، دامنه نوسانات شتابی وسرعتی بیشتری را نسبت به دیگر چرخه‌‌های مورد مقایسه گزارش نمود. | ||
| کلیدواژه‌ها | ||
| چرخه رانندگی؛ ماشین بردار پشتیبان؛ الگوریتم میانگین کی؛ چرخه ترکیبی؛ دسته‌بندی و طبقه‌بندی | ||
| عنوان مقاله [English] | ||
| Comparison of Support Vector Machine and K-Means Algorithms Performance in Extracting the Real Driving Cycle of Combined Tehran-Amol | ||
| نویسندگان [English] | ||
| Tabanmehr Qaraati1؛ Ali Momeni Movahed1؛ Mohammad Azadi2؛ Seyed Ashkan Moosavian3 | ||
| 1Department of Mechanical Engineering, Faculty of Technical and Engineering, Imam Khomeini International University, Qazvin, Iran | ||
| 2سمنان-مهندسی مکانیک | ||
| 3Shahriyar Faculty, Technical and Vocational University | ||
| چکیده [English] | ||
| Driving cycles represent the vehicle speed as a function of time and are used in vehicle design, fuel management, and the improvement of standard indicators. In this study, four combined driving cycles were extracted using real data. The data was collected from a passenger car with a gasoline engine under real driving conditions while driven from Tehran to Amol based on the car chasing method. A code was generated in MATLAB software to create the desired cycle using support vector machine and K-means algorithms considering mid-range and mean values as group centers. The characteristic parameters of the cycles such as the average speed and the percentage of the car travel time at idle, cruise, accelerating, and decelerating conditions were also calculated. These cycles were compared based on the mean relative error, the root-mean-square error, and the Chi-square test. The results showed that the cycles extracted by the support vector machine were closer to the allowable time interval (less than 1800 seconds); however, the cycle extracted by the K-means algorithm with the mean value as the centers of the generated categories, recorded the least errors. This cycle, in addition to spending most of its time in accelerated motion, represented a greater amplitude of acceleration and velocity fluctuations than other cycles. | ||
| کلیدواژه‌ها [English] | ||
| Driving cycle, Support vector machine, K-means algorithm, Combined cycle, Classification, and clustering | ||
| مراجع | ||
|
[1] X. Zhao, Q. Yu , J. Ma, Y. Wu, M. Yu, Y. Ye, Development of a representative EV urban driving cycle based on a K-means and SVM hybrid clustering algorithm, Journal of Advanced Transportation, 2018 (2018) 1890753. [2] X. Zhao, J. Ma, S. Wang, Y. Ye, Y. Wu, M. Yu, Developing an electric vehicle urban driving cycle to study differences in energy consumption, Environmental Science and Pollution Research, 26 (2019) 13839-13853. [3] N.H. Arun, S. Mahesh, G. Ramadurai, S.M.S. Nagendra, Development of driving cycles for passenger cars and motorcycles in Chennai, India, Sustainable Cities and Society, 32 (2017) 508-512. [4] S.H. Kamble, T.V. Mathew, G.K. Sharma, Development of real-world driving cycle: Case study of Pune, India, Transportation Research Part D, 14 (2009) 132-140. [5] A. Esteves-Booth, T. Muneer, H. Kirby, J. Kubie, J. Hunter, The measurement of vehicular driving cycle within the city of Edinburgh, Transportation Research Part D, 6 (2001) 209-220. [6] Z. Jing, G. Wang, S. Zhang, C. Qiu, Building Tianjin driving cycle based on linear discriminant analysis, Transportation Research Part D, 53 (2017) 78-87. [7] U. Galgamuwa, L. Perera, S. Bandar, A representative driving cycle for the southern expressway compared to existing driving cycles, Springer International Publishing Switzerland, 2 (2016) 22. [8] B. Liu, Q. Shi, L. He, D. Qiu, A study on the construction of Hefei urban driving cycle for passenger vehicle, IFAC-PapersOnLine, 51 (2018) 854-858. [9] W. Saleh, R. Kumar, H. Kirby, P. Kumar, Real world driving cycle for motorcycles in Edinburgh, Transportation Research, 14 (2009) 326-333. [10] A. Fotouhi, M. Montazeri-Gh, Tehran driving cycle development using the K-means clustering method, Scientia Iranica, 20 (2013) 286-293. [11] W. Zhou, K. Xu, Y. Yang, J. Lu, Driving cycle development for electric vehicle application using principal component analysis and K-means cluster: With the case of Shenyang, China, in: 8th International Conference on Applied Energy, Energy Procedia, Beijing, China, 2017, pp. 2831-2836. [12] A.R. Mahayadin, I. Ibrahim, I. Zunaidi, A.B. Shahriman, M.K. Faizi, M. Sahari, M.S.M. Hashim, M.A.M. Saad, M.S. Sarip, Z.M. Razlan, M.F.H. Rani, Z.M. Isa, N.S. Kamarrudin, A. Harun, Y. Nagaya, Development of driving cycle construction methodology in Malaysia's urban road system, in: International Conference on Computational Approach in Smart Systems Design and Applications, Institute of Electrical and Electronics Engineers, Kuching, Malaysia, 2018, pp. 18132704. [13] H.Y. Tong, W.T. Hung, C.S. Cheung, Development of a driving cycle for Hong Kong, Atmospheric Environment, 33 (1999) 2323-2335. [14] H. Razavi, The driving cycle to Monte Carlo method in order to explore the suitability of the vehicle with its application, Journal of Transport Engineering, 2(3) (2011) 238-249. [15] J. Brady, M. O'Mahony, Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas, Applied Energy, 177 (2016) 165-178. [16] P. Chauhan Boski, G.J. Joshi, P. Purnima, Driving cycle analysis to identify intersection influence zone for urban intersections under heterogeneous traffic condition, Sustainable Cities and Society, 41 (2018) 180-185. [17] S. Tamsanya, S. Chungpaibulpattana, S. Atthajariyakul, Development of automobile Bangkok driving cycle for emissions and fuel consumption assessment, in: The Second Joint International Conference, Sustainable Energy and Environment, Bangkok, Thailand, 2006, pp. 1-6. [18] I.N. Anida, A.R. Salisa Driving cycle development for Kuala Terengganu city using K-means method, International Journal of Electrical and Computer Engineering, 9 (2019) 1780-1787. [19] Y. Nguyen, N.D. Bui, T.D. Nghiem, A. Le, GPS data processing for driving cycle development in Hanoi, Vietnam, Journal of Engineering Science and Technology, 15 (2020) 1429-1440. [20] M.A. Pouresmaeili, I. Aghayan, A. Taghizadeh, Development of a Mashhad driving cycle for passenger car to model vehicle exhaust emissions calibrated using on-board measurements, Sustainable Cities and Society, 36 (2018) 12-20. [21] T. Qaraati, A.M. Movahed, M. Azadi, A. Moosavian, M. Nikkhah, Comparing characteristic parameters of driving cycle using real data collected in Iran and global standard cycles, in: 11th International Conference on Internal Combustion Engines and Oil, Tehran, 2020 (in Persian). [22] X. Zhao, Q. Yu, J. Ma, Y. Wu, M. Yu, Y. Ye, Development of a representative EV urban driving cycle based on a K-means and SVM hybrid clustering algorithm, Journal of Advanced Transportation, 2018 (2018) 1890753. [23] T.J. Barlow, S. Latham, I.S. McCrae, P.G. Boulter, A reference book of driving cycles for use in the measurement of road vehicle emissions, TRL Published Project Report, 2009. [24] Q. Shi, R. Wang, Y. Zheng, Y. Li, The study of a new method of driving cycles construction, Procedia Engineering, 16 (2011) 79-87. [25] M. Montazeri-Gh, M. Naghizadeh, Development of car drive cycle for simulation of emissions and fuel economy, in: Proceedings of 15th European Simulation Symposium, Delft, Netherland, 2003. [26] M. Tutuianu, A. Marotta, H. Steven, E. Ericsson, T. Haniu, N. Ichikawa, H. Ishii, Development of a world-wide harmonized light duty driving test cycle (WLTC), DHC Subgroup, 2013. [27] J.C. Platt, Sequential minimal optimization: A fast algorithm for training support vector machines, Microsoft Technical Report, 1998. [28] C.R. Souza, Kernel functions for machine learning applications, Edge Impulse, 2010, http://www.crsouza.com/. [29] Median vs. average to describe normal, in: Natural Resources Conservation Service, United States Department of Agriculture, 2019, https://www.wcc.nrcs.usda.gov/. [30] Y. Dodge, D. Cox, D. Commenges, P.J. Solomon, S. Wilson, The Oxford dictionary of statistical terms, Oxford University Press, 2003. [31] E. Volchok, Clear-sighted statistics - Module 17: Chi-Square tests, Cuny Academic Works, New York, USA, 2020. [32] C. Yiakopoulos, K.C. Gryllias, I.A. Antoniadis, Rolling element bearing fault detection in industrial environments based on a K-means clustering approach, Expert Systems with Applications, 38 (2011) 2888-2911. [33] A. Al-Samari, Real-world driving cycle: Case study of Baqubah, Iraq, Diyala, Journal of Engineering Sciences, 10 (2017) 39-47. [34] R. Tharvin, N. Kamarrudin, A. Shahriman, I. Zunaidi, Z. Razlan, W. Wan, A. Harun, M. Hashim, I. Ibrahim, M. Faizi, Development of driving cycle for passenger car under real world driving conditions in Kuala Lumpur, Malaysia, in: IOP Conference Series: Materials Science and Engineering, Sarawak, Malaysia, 2018. [35] W.T. Hung, H. Tong, C. Lee, K. Ha, L. Pao, Development of a practical driving cycle construction methodology: A case study in Hong Kong, Transportation Research Part D: Transport and Environment, 12 (2007) 115-128. [36] P. Outapa, S. Thepanondh, A. Kondo, N. Pala-En, Development of air pollutant emission factors under real-world truck driving cycle, International Journal of Sustainable Transportation, 12 (2018) 432-440. | ||
|
آمار تعداد مشاهده مقاله: 843 تعداد دریافت فایل اصل مقاله: 981 |
||