An improved method of detecting engine misfire by sound quality metrics of radiated sound

Singh, Sneha; Potala, Sagar; Mohanty, Amiya Ranjan

doi:10.1177/0954407018818693

Cited by 14 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This experiment demonstrated that any of the methods mentioned may be efficiently applied to diagnose a misfire fault of an internal combustion engine. In another approach, Singh et al [11] used sound quality metrics (roughness, loudness, and fluctuation strength) into the SVM classifier to analyze and classify the engine block and tailpipe sounds. Using this technique, Sing and his co-workers reached an accuracy of 94% in the misfire diagnosis process.…”

Section: Introductionmentioning

confidence: 99%

Misfire detection of an internal combustion engine based on vibration and acoustic analysis

Firmino

Neto

Oliveira

et al. 2021

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

A Misfire event is an unwanted phenomenon that compromises the regular operation of the engine, increasing the pollution of emission gases and decreasing its efficiency. Therefore, smart systems that detect misfire ensure better engine operation and compliance with government environmental regulations. This paper presents a comparative study of two smart systems that use two different methodologies for misfire detection in a 2006 Ford Zetec-Rocam engine, which is a 4-stroke sparkignition engine. The first methodology tested was vibration analysis, which consists of collecting vibration data from the engine block using a vibration acquisition system. After the acquisition stage, we extracted and selected the signal features using the fast Fourier transform (FFT) in order to recognize the fault patterns through the use of an artificial neural network (ANN), which presented an accuracy of 99.30%. The second methodology was the acoustic analysis of the engine sound. The data were collected by a sound acquisition system, and then the feature extraction and selection were done by using the same technique as we did in the vibration analysis. For this technique, the ANN developed presented an accuracy of 98.70%. Although the vibration analysis is slightly more accurate than the acoustic analysis for misfire diagnosis, the acoustic system has the advantage of not being necessary the physical contact between the data acquisition system and the engine. Therefore, both techniques may be applied with great accuracy, and the decision of using one approach or another will depend on the equipment availability and the user's specialty.

show abstract

Section: Introductionmentioning

confidence: 99%

Misfire detection of an internal combustion engine based on vibration and acoustic analysis

Firmino

Neto

Oliveira

et al. 2021

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Misfires have been detected in a contact-less acoustic method with 94% accuracy, relative to 82% accuracy attained from vibration signals. Without opening the hood and recording at the exhaust, the authors reached 85% classification accuracy from audio (which again outperformed vibration) [39]. While some algorithms have been developed without physical process knowledge, others make use of system models to improve diagnostic performance.…”

Section: Engine and Transmissionmentioning

confidence: 98%

Surveying Off-Board and Extravehicular Monitoring and Progress Towards Pervasive Diagnostics

Siegel¹,

Coda²,

Terwilliger³

2021

SAE Intl. J CAV

View full text Add to dashboard Cite

We survey the state-of-the-art in offboard diagnostics for vehicles, their occupants, and environments, with particular focus on vibroacoustic approaches. We identify promising application areas including data-driven management for shared mobility and automated fleets, usage-based insurance, and vehicle, occupant, and environmental state and condition monitoring. We close by exploring the particular application of vibroacoustic monitoring to vehicle diagnostics and prognostics and propose the introduction of automated vehicle-and context-specific model selection as a means of improving algorithm performance, e.g. to enable smartphone-resident diagnostics. The described approach may serve as the first step in developing "universal diagnostics," with applicability extending beyond the automotive domain. Motivating the Need for Vehicle DiagnosticsThe automotive world is changing, and there is increasing concern about vehicles' environmental impact, particularly those with internal combustion engines. As a result, there is a growing prevalence of efficiency-improving systems within vehicles. One of the biggest contributors to lifetime efficiency is the availability of in-vehicle diagnostic systems, as these may report faults early and precisely to motivate owners and operators to seek out preventative or restorative maintenance, enhancing safety and reducing operating costs.At the same time, mobility culture is evolving, transitioning from the need to own a car towards the concept of mobilityas-a-service. Today, vehicle sales are slowing despite continued high mobility demand: The average vehicle age and lifetime miles travelled are increasing, particularly in developing countries [1,2], and shared mobility services, car rentals, and "robotaxis" are emerging. Increased utilization and novel use cases require enhanced fleet data generation and management capabilities. Key to enhanced fleet management is the concept of automotive diagnostics, i.e. the inference of a vehicle's condition based on observed symptoms indicating a technical state [3]. Diagnostics are important for monitoring vehicle, environment, and occupant status (e.g. component wear, road conditions, or driver alertness).Historically, these diagnostics draw upon in-situ sensors and computation to develop "On Board Diagnostics." On-Board Diagnostics (OBD)On-Board Diagnostic (OBD-II) systems present on vehicles sold since 1996 [4] are an automated control system utilizing distributed sensing across a vehicle's embedded systems as a technical solution for measuring vehicle operational parameters and detecting, reporting, and responding to faults.

show abstract

“…8,9 This property has made SVM as an effective supervised learning algorithm in recent years. 10–12 For example, Jegadeeshwaran and Sugumaran 13 developed a fault diagnosis scheme for hydraulic brakes using SVM. It has been reported that SVM has advantages (in terms of good prediction accuracy, less model training time, and ability to handle unstructured and semi-structured data) in classification problems with small samples, high dimensions, and nonlinear data that make it widely popular for fault diagnosis and predictive health monitoring.…”

Section: Introductionmentioning

confidence: 99%

Learning-based fault diagnosis of air brake system using wheel speed data

Raveendran

Devika

Subramanian

2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Faults in the air brake system used in Heavy Commercial Road Vehicles (HCRVs) would adversely affect the vehicle’s dynamic performance, and hence their prompt detection is critical for vehicle safety. This paper first investigates the effect of air brake system faults through extensive hardware-in-loop experiments. These faults were observed to degrade the braking response, yaw stability, and vehicle braking distance. In many countries, an antilock brake system is mandatory in HCRVs, and wheel speed data are readily available. Inspired by this, the feasibility of using wheel speed data to detect faults is investigated in this study. As an initial step of predictive maintenance, a fault diagnostic scheme based on a supervised learning algorithm, Support Vector Machine (SVM) that uses only wheel speed data has been developed. The SVM algorithm’s efficacy was tested for 1937 test cases that encompassed a wide range of operating conditions. It was found that a Gaussian kernel SVM (G-SVM) provided a good classification accuracy of 96.54%, demonstrating its ability to predict a faulty condition accurately. The standard deviation of G-SVM’s prediction accuracy for five groups of data sets with 100 instances was found to be 1.57%, which shows that the model is more precise to predict the fault/no-fault condition of the air brake system.

show abstract

An improved method of detecting engine misfire by sound quality metrics of radiated sound

Cited by 14 publications

References 27 publications

Misfire detection of an internal combustion engine based on vibration and acoustic analysis

Misfire detection of an internal combustion engine based on vibration and acoustic analysis

Surveying Off-Board and Extravehicular Monitoring and Progress Towards Pervasive Diagnostics

Learning-based fault diagnosis of air brake system using wheel speed data

Contact Info

Product

Resources

About