Abstract:Engine vibration signals are easy to be interfered by other noise, causing feature signals that represent its operating status get submerged and further leading to difficulty in engine fault diagnosis. In addition, most of the signals utilized to verify the extraction method are derived from numerical simulation, which are far away from the real engine signals. To address these problems, this paper combines the priority of signal sparse decomposition and engine finite element model to research a novel feature … Show more
“…There is a long history of works focused on misfire fault detection in internal combustion engines. Many approaches utilize vibration analysis [ 23 , 24 , 25 , 26 , 27 , 28 , 29 ] and physics-based estimations such as with acceleration, torque, and speed [ 30 , 31 , 32 , 33 ].…”
In a world dependent on road-based transportation, it is essential to understand automobiles. We propose an acoustic road vehicle characterization system as an integrated approach for using sound captured by mobile devices to enhance transparency and understanding of vehicles and their condition for non-expert users. We develop and implement novel deep learning cascading architectures, which we define as conditional, multi-level networks that process raw audio to extract highly granular insights for vehicle understanding. To showcase the viability of cascading architectures, we build a multi-task convolutional neural network that predicts and cascades vehicle attributes to enhance misfire fault detection. We train and test these models on a synthesized dataset reflecting more than 40 hours of augmented audio. Through cascading fuel type, engine configuration, cylinder count and aspiration type attributes, our cascading CNN achieves 87.0% test set accuracy on misfire fault detection which demonstrates margins of 8.0% and 1.7% over naïve and parallel CNN baselines. We explore experimental studies focused on acoustic features, data augmentation, and data reliability. Finally, we conclude with a discussion of broader implications, future directions, and application areas for this work.
“…There is a long history of works focused on misfire fault detection in internal combustion engines. Many approaches utilize vibration analysis [ 23 , 24 , 25 , 26 , 27 , 28 , 29 ] and physics-based estimations such as with acceleration, torque, and speed [ 30 , 31 , 32 , 33 ].…”
In a world dependent on road-based transportation, it is essential to understand automobiles. We propose an acoustic road vehicle characterization system as an integrated approach for using sound captured by mobile devices to enhance transparency and understanding of vehicles and their condition for non-expert users. We develop and implement novel deep learning cascading architectures, which we define as conditional, multi-level networks that process raw audio to extract highly granular insights for vehicle understanding. To showcase the viability of cascading architectures, we build a multi-task convolutional neural network that predicts and cascades vehicle attributes to enhance misfire fault detection. We train and test these models on a synthesized dataset reflecting more than 40 hours of augmented audio. Through cascading fuel type, engine configuration, cylinder count and aspiration type attributes, our cascading CNN achieves 87.0% test set accuracy on misfire fault detection which demonstrates margins of 8.0% and 1.7% over naïve and parallel CNN baselines. We explore experimental studies focused on acoustic features, data augmentation, and data reliability. Finally, we conclude with a discussion of broader implications, future directions, and application areas for this work.
“…Singular value reflects the energy distribution of useful signals and noise in the signal. Singular value decomposition (SVD) can remove the noise, extract the features of the signal and analyze the components of the signal [5,6]. However, the SVD denoising method is difficult to separate and extract the feature components at a low signal-to-noise ratio (SNR).…”
Signal de-noising process is the process of signal characteristic components extraction. In view of the singular value decomposition de-noising method is difficult to separate under low SNR, through observing the singular value distribution under different decomposition order, select the appropriate number of decomposition, and combining the wavelet packet de-noising ability and good frequency resolution, put forward a kind of effective signal de-noising method. Firstly, based on different SNR to choose the appropriate number of singular value decomposition, select bigger singular value reconstructing the signal, preliminary to remove noise, and then make three layer wavelet packet decomposition, compare the energy distribution of all nodes, and make selection of energy concentration of several nodes, reconstruct the signal. Simulation results verify the validity of this method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.