A methodology for increasing the signal to noise ratio for the misfire detection at high speed in a high performance engine

Abstract

The paper presents a methodology for pre-processing the combustion time intervals, that is the basic signal used in misfire detection strategies, with the aim of increasing the signal-to-noise ratio to enable a more efficient misfire diagnosis, especially when the engine is running at high speeds and low loads. The performance of the basic misfire detection algorithm shows that in those engine operating conditions the background noise amplitude has approximately the same value of the information related to the misfire presence, thus hiding the misfire event that may not be detected. The proposed methodology is based on the correction of the combustion time signal cycle-by-cycle, using a vector of data that take into account the specific behavior of every cylinder. The vector of data for the combustion time correction is stored in a map inside the control unit and could be continuously updated with an auto-adaptive learning technique. r

Torsional vibration responses of the engine crankshaft-gearbox coupled system with misfire and breathing slant crack based on instantaneous angular speed

“…Chen and Randall [34] used artificial neural networks to diagnose accurately the location and severity of misfire of an internal combustion engine. Cavina et al [35] came up with a methodology by pre-processing the combustion time intervals to increase the signal-to-noise ratio. By monitoring the responses of each cylinder, the methodology would correct the combustion time signal time every cycle.…”

Misfire detection of diesel engine based on convolutional neural networks

“…Therefore, other misfire feature indicators besides modifying the engine roughness method have been introduced. 36 In the study by Cavina and Ponti, 37 a misfire detection parameter, that evaluates the torque nonuniformity between the various cylinders, was defined and applied to both V6 and an L4 engines with good results. Hu et al 38 proposed a multivariate statistical analysis approach for locating multiple misfire events.…”

Multivariate statistical analysis strategy for multiple misfire detection in internal combustion engines

“…Although this method provides sufficient information about the engine combustion conditions, it is time-consuming and requires an accurate dynamic model. It would be more efficient to evaluate the crankshaft kinetic energy variation caused by the combustions with the time periods, which are spent on the rotation of predefined angular sectors [16][17][18]. To distinguish misfire events from compression faults, two energy indices were extracted from an energy model of crankshaft [19].…”