排気温度波形を用いた内燃機関失火検出法に関する研究
スポンサーリンク
概要
- 論文の詳細を見る
A novel misfire detection method for stationary internal combustion gas engines is presented. The main aim of the proposed method is focused on statistical detection of misfire as a precursor of malfunctions of ignition systems. Use of conventional exhaust temperature sensor installed in each cylinder is proposed. Characteristic waveforms which appear in the measured sensor output are analyzed and classified if they are signs of misfire or normal fluctuations. The key factor of the proposed method is an algorithm for discrimination of waveforms. Empirical if/then rules and dynamic time warping are compared as waveform recognition methods. The former has a merit of low computational cost, whereas the latter can be designed and employed rapidly using an appropriate template wave. Data collected for three years from an actual engine in operation is used for validation and evaluation of effectiveness of the proposed method.