Air filter particulate loading detection using smartphone audio and optimized ensemble classification

Abstract Automotive engine intake filters ensure clean air delivery to the engine, though over time these filters load with contaminants hindering free airflow. Today’s open-loop approach to air filter maintenance has drivers replace elements at predetermined service intervals, causing costly and potentially harmful over- and under-replacement. The result is that many vehicles consistently operate with reduced power, increased fuel consumption, or excessive particulate-related wear which may harm the catalyst or damage machined engine surfaces. We present a method of detecting filter contaminant loading from audio data collected by a smartphone and a stand microphone. Our machine learning approach to filter supervision uses Mel-Cepstrum, Fourier and Wavelet features as input into a classification model and applies feature ranking to select the best-differentiating features. We demonstrate the robustness of our technique by showing its efficacy for two vehicle types and different microphones, finding a best result of 79.7% accuracy when classifying a filter into three loading states. Refinements to this technique will help drivers supervise their filters and aid in optimally timing their replacement. This will result in an improvement in vehicle performance, efficiency, and reliability, while reducing the cost of maintenance to vehicle owners.

[1]  Peyman KABIRI,et al.  Using PCA in Acoustic Emission Condition Monitoring to Detect Faults in an Automobile Engine , 2010 .

[2]  Stephen C. H. Leung,et al.  Vertical bagging decision trees model for credit scoring , 2010, Expert Syst. Appl..

[3]  S. N. Dandare.  Multiple Fault Detection in typical Automobile Engines: a Soft computing approach , 2013 .

[4]  Ajay A. Deshpande,et al.  Smartphone-Based Wheel Imbalance Detection , 2015, HRI 2015.

[5]  Daniel Curiac,et al.  Ensemble based sensing anomaly detection in wireless sensor networks , 2012, Expert Syst. Appl..

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Khaled Rasheed,et al.  Decision tree and ensemble learning algorithms with their applications in bioinformatics. , 2011, Advances in experimental medicine and biology.

[8]  John F. Thomas,et al.  Effect of Intake Air Filter Condition on Light-Duty Gasoline Vehicles , 2012 .

[9]  Brian H. West,et al.  Effect of Intake Air Filter Condition on Vehicle Fuel Economy , 2009 .

[10]  Marius Toma,et al.  Research on Drivers’ Perception on the Maintenance of Air Filters for Internal Combustion Engines☆ , 2016 .

[11]  Tadeusz Jaroszczyk,et al.  Factors Affecting the Performance of Engine Air Filters , 1993 .

[12]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[13]  Ajay A. Deshpande,et al.  Smartphone-Based Vehicular Tire Pressure and Condition Monitoring , 2016, IntelliSys.

[14]  Sanjay E. Sarma,et al.  Engine Misfire Detection with Pervasive Mobile Audio , 2016, ECML/PKDD.

[15]  Marius Toma.  Investigating Maintenance Procedures for Engine Air Filters , 2016 .

[16]  A. Deshpande,et al.  Vehicular engine oil service life characterization using On-Board Diagnostic (OBD) sensor data , 2014, IEEE SENSORS 2014 Proceedings.

[17]  Daegon Cho,et al.  Characterizing the technological evolution of smartphones: insights from performance benchmarks , 2016, ICEC.

[18]  Cha Zhang,et al.  Ensemble Machine Learning , 2012 .

[19]  Xu Zheng,et al.  Comparison of different techniques for time-frequency analysis of internal combustion engine vibration signals , 2011 .

[20]  Hamid GHADERI,et al.  Automobile Independent Fault Detection based on Acoustic Emission Using Wavelet , 2011 .

[21]  Vinayak K. Bairagi,et al.  Engine fault diagnosis using sound analysis , 2016, 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT).

[22]  P.O.A.L. Davies,et al.  I.C. ENGINE INTAKE AND EXHAUST NOISE ASSESSMENT , 1999 .

[23]  Peter Bühlmann,et al.  Bagging, Boosting and Ensemble Methods , 2012 .

[24]  Marthinus J. Booysen,et al.  Survey of smartphone-based sensing in vehicles for intelligent transportation system applications , 2015 .

[25]  Jian-Da Wu,et al.  Investigation of engine fault diagnosis using discrete wavelet transform and neural network , 2008, Expert Syst. Appl..

[26]  Prem Kumar Kalra,et al.  Audio Signature-Based Condition Monitoring of Internal Combustion Engine Using FFT and Correlation Approach , 2011, IEEE Transactions on Instrumentation and Measurement.

[27]  A. Sujono.  Utilization of Microphone Sensors and an Active Filter for the Detection and Identification of Detonation (Knock) in a Petrol Engine , 2014 .

[28]  Andrew Stranieri,et al.  Empirical Study of Decision Trees and Ensemble Classifiers for Monitoring of Diabetes Patients in Pervasive Healthcare , 2012, 2012 15th International Conference on Network-Based Information Systems.