LSTM for Modeling of Cylinder Pressure in HCCI Engines at Different Intake Temperatures via Time-Series Prediction
نویسندگان
چکیده
Modeling engines using physics-based approaches is a traditional and widely-accepted method for predicting in-cylinder pressure the start of combustion (SOC). However, developing such intricate models typically demands significant effort, time, knowledge about underlying physical processes. In contrast, machine learning techniques have demonstrated their potential building that are not only rapidly developed but also efficient. this study, we employ approach to predict cylinder homogeneous charge compression ignition (HCCI) engine. We utilize long short-term memory (LSTM) based model compare its performance against fully connected neural network model, which has been employed in previous research. The LSTM model’s results evaluated experimental data, yielding mean absolute error 0.37 squared 0.20. prediction presented as time series, expanding upon prior work focused on at discrete points time. Our findings indicate can accurately HCCI up 256 steps ahead.
منابع مشابه
Modeling Low-Pressure Injections in Diesel HCCI Engines
Homogeneous Charge Compression Ignition (HCCI) combustion is being considered as an alternative to conventional engine combustion systems due to its high efficiency and low engine-out emissions. To prepare a homogeneous mixture for diesel HCCI combustion, two types of low pressure (5MPa~20MPa) injectors were considered: a swirl injector and a multi-hole injector. A modified version of the KIVA-...
متن کاملprediction of ignition delay period in d.i diesel engines
a semi-empirical mathematical model for predicting physical part of ignition delay period in the combustion of direct - injection diesel engines with swirl is developed . this model based on a single droplet evaporation model . the governing equations , namely , equations of droplet motion , heat and mass transfer were solved simultaneously using a rung-kutta step by step unmerical method . the...
Cylinder Pressure and Ionization Current Modeling for Spark Ignited Engines
Engine management systems (EMS) need feedback on combustion performance to optimally control internal combustion engines. Ion sensing is one of the cheapest and most simple methods for monitoring the combustion event in a spark ignited engine, but still the physical processes behind the formation of the ionization current are not fully understood. The goal here is to investigate models for ioni...
متن کاملa time-series analysis of the demand for life insurance in iran
با توجه به تجزیه و تحلیل داده ها ما دریافتیم که سطح درامد و تعداد نمایندگیها باتقاضای بیمه عمر رابطه مستقیم دارند و نرخ بهره و بار تکفل با تقاضای بیمه عمر رابطه عکس دارند
ذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machines
سال: 2023
ISSN: ['2075-1702']
DOI: https://doi.org/10.3390/machines11100924