Detecting the Flame Front Evolution in Spark-Ignition Engine under Lean Condition Using the Mask R-CNN Approach

Abstract

In the wake of previous works, the authors propose a new approach for the identification and evolution of the flame front in an optical SI engine. Currently, it is an essential prerogative to characterize the capability of innovative igniters to guarantee earlier flame development in critical operating conditions, such as ultra-lean mixture, towards which automotive research is moving to deal with the ever more stringent regulations on pollutant emissions. The core of the new approach lies in the R-CNN Mask method. The latter consists of a conceptually simple and general framework for object instance segmentation. It can efficiently detect objects contained in an image while simultaneously generating a high-quality segmentation mask for each instance. In particular, the aim this work is to develop an automatized algorithm for detecting, as objectively as possible, the flame front evolution of lean/ultra-lean mixtures ignited by low-temperature plasma-based ignition systems. The capability of the Mask R-CNN algorithm to automatically estimate the binarized area, without setting a defined binarized threshold, allows us to perform an analysis of the flame front evolution completely independent from the user interpretation. Mask R-CNN can detect the kernel in advance and can identify events as regular combustions instead of misfires or anomalies if compared to other traditional approaches. These features make the proposed method the most suitable option to analysis the real behavior of the innovative ignition systems at critical operating conditions.

NARX Technique to Predict Torque in Internal Combustion Engines

“…Following the considerations reported in the section Artificial Neural Network Setup and Methods, a new neural structure optimization was required. Even in this case, a maximum of 2 hidden layers composed of different numbers of neurons (7,9,12,15,17) was selected following the architecture depicted in Figure 5, for a total of 25 combinations, for the corresponding evaluation of the performance during the training phase. The structure showing the best RMSE in training was chosen for the test session.…”

“…Machine learning (ML) approaches are increasingly proposed in many automotive applications such as virtual sensors [10,11], fault diagnosis systems [12], and performance optimizations [13] for real-time and low-cost hardware implementation and compact configuration [14]. Their capability to forecast parameters employing interpolation-based algorithms of known intermediate values can reduce the number of analyzed operating points, thus leading to notable advantages in terms of memory and computational speed [15][16][17].…”

Thermal Energy and Luminosity Characterization of an Advanced Ignition System Using a Non-Intrusive Methodology in an Optically Accessible Calorimeter

“…The recognition of the flame evolution is carried out by PA, regardless of any user's decision, which could make the proposed method potentially suitable for any type of application requiring a high degree of objectivity. The new algorithm, applied to simplified but realistic images, shows promising results [65,66].…”

Advanced Flame front Detection in Combustion Processes Using Autoencoder Approach

“…In previous works of the same research group [15], ML algorithms with CNN structures were employed to detect the flame front evolving in a single-cylinder optical access engine and the corresponding performance compared with the ones obtained through the utilization of a semi-automatic algorithm proposed by Shawal et al [16] and used as a base reference. The results show that the proposed methods identify some combustions, initially marked as misfires or anomalies by the base reference method as valid.…”