Engine Knock Detection Based on Time-Frequency Images and Support Vector Machine

Ning Li; Rui Zhou

doi:10.4028/www.scientific.net/AMR.694-697.1387

Paper Titles

Study on Oil Pipeline Leakage Detection Based on Stress Wave Detection Technique and Wavelet Analysis
p.1368

An Analytical Method of Time Character of Electron Beam Current Density on Transmission Electron Microscope Imaging
p.1372

Research of Rolling Bearing Fault Feature Extraction Based on EMD and Choi-Williams
p.1377

Design and Research on the Cigarette Paper Smoldering Rate of PRS-2 Tester
p.1382

Engine Knock Detection Based on Time-Frequency Images and Support Vector Machine
p.1387

Research on the Construction Tower Cranes Group State Real-Time Monitoring System
p.1391

40-GHz Pulse Generation Based on Two Cascaded Electro-Absorption Modulators Driven by 20GHz-Sine-Wave Signal
p.1399

A Novel Genetic-Algorithm-Based AMC Structure
p.1403

An Efficient Detail-Preserving Random-Valued Impulse Noise Filter
p.1407

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 694-697Engine Knock Detection Based on Time-Frequency...

Engine Knock Detection Based on Time-Frequency Images and Support Vector Machine

Abstract:

Knock is a major cause of pollution, parts damage and metallic noise in an engine. But slight knock can improve the power and economic performance of an engine. Therefore, existence and intensity of the knock are preconditions for the automatic knock control system to work. This paper describes an advanced approach solving the knock detection task. It is based on a time-frequency image generation solution followed by a support vector machine detection step trained in a constructive supervised way. The proposed method is applied to analyze the pressure signals measured from an engine cylinder to detect the knock based on the popular cycle-by-cycle classification. It is shown that this approach can qualify well for knock detection.