No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Mobile Based Application for Detecting Fault by Sound Analysis in Car Engines Using Triangular Window and Wavelet Transform
Abstract
Sound energy belies an enormous amount of information which can provide assistance in various applications like navigation, communication, recognition, medical - diagnosis, detection and therapy, analysis & design of structures and many more. This paper presents a method for detecting faults in car engines just by recording their sounds through window based applications in mobile phones and processing it in the mobile phone using our algorithm. The algorithm preprocesses the sound to remove the noise if present, the noise free car engine sound is passed through a triangular window to acquire the Multi resolution coefficients for discrete wavelet transform and compare resulting plots. The Wavelet transform analysis is done and the plots are scrupulously analyzed and the faults can now be detected by referring to plots. With a little know-how non technical persons can now detect the abnormalities in car engines just be using this automation.
... Algorithms for specific engine sound recognition were done by [1] and a mobile-based application, running in Windows, for detecting engine faults was made by [2]. Microcontroller based on-board diagnostic (OBD) system was proposed by [3] to diagnose engines which are not yet equipped with OBD. ...
This study aims to design and implement an acoustic-based car engine fault diagnostic system in the Android platform. The system is in the form of an Android application which can run on any phone with an Android operating system.
A smart phone running in the Android operating system is used in order to analyze the sounds coming from the car engine. The smart phone is simply placed at an approximate distance of 1-foot away from the engine assembly. Fault diagnosis covers engine start problem detection, drive-belt analysis and tune-up detection based on valve clearance. Each fault is analyzed individually and sample engine acoustics are obtained per engine fault mentioned. The system is equipped with signal processing algorithms using Fourier transforms and spectral power densities that process the sounds obtained in order to come up with a diagnostic result and further recommend some possible solutions. The algorithm is based on the correlation coefficient of the spectral power densities (SPD), collected using two distinct clustering techniques (spectral power sum and spectral power hop), of the audio signals (test and reference engine sounds) which are fed into a fuzzy logic inference system for classification.
The design and implementation of the engine fault diagnostic system was made successful in a smart phone running in the Android platform. Fault signatures were made and were used as a reference for fault detection. Results show that the system was able to diagnose the engine faults on the target model as well as with other brands of cars.
An automated image processing method is presented for simulating areal bone mineral density measures using high-resolution peripheral quantitative computed tomography (HR-pQCT) in the ultra-distal radius. The accuracy of the method is validated against clinical dual X-ray absorptiometry (DXA). This technique represents a useful reference to gauge the utility of novel 3D quantification methods applied to HR-pQCT in multi-center clinical studies and potentially negates the need for separate forearm DXA measurements.
Osteoporotic status is primarily assessed by measuring areal bone mineral density (aBMD) using 2D dual X-ray absorptiometry (DXA). However, this technique does not sufficiently explain bone strength and fracture risk. High-resolution peripheral quantitative computed tomography (HR-pQCT) has been introduced as a method to quantify 3D bone microstructure and biomechanics. In this study, an automated method is proposed to simulate aBMD measures from HR-pQCT distal radius images.
A total of 117 subject scans were retrospectively analyzed from two clinical bone quality studies. The distal radius was imaged by HR-pQCT and DXA on one of two devices (Hologic or Lunar). Areal BMD was calculated by simulation from HR-pQCT images (aBMD(sim)) and by standard DXA analysis (aBMD(dxa)).
The reproducibility of the simulation technique was 1.1% (root mean-squared coefficient of variation). HR-pQCT-based aBMD(sim) correlated strongly to aBMD(dxa) (Hologic: R (2) = 0.82, Lunar: R (2) = 0.87), though aBMD(sim) underestimated aBMD(dxa) for both DXA devices (p < 0.0001). Finally, aBMD(sim) predicted aBMD at the proximal femur and lumbar spine with equal power compared to aBMD(dxa).
The results demonstrate that aBMD can be simulated from HR-pQCT images of the distal radius. This approach has the potential to serve as a surrogate forearm aBMD measure for clinical HR-pQCT studies when axial bone mineral density values are not required.
Fractures of the proximal femur are one of the principal causes of mortality among elderly persons. Traditional methods for the determination of femoral fracture risk use methods for measuring bone mineral density. However, BMD alone is not sufficient to predict bone failure load for an individual patient and additional parameters have to be determined for this purpose. In this work an approach that uses statistical models of appearance to identify relevant regions and parameters for the prediction of biomechanical properties of the proximal femur will be presented. By using Support Vector Regression the proposed model based approach is capable of predicting two different biomechanical parameters accurately and fully automatically in two different testing scenarios.
Dual-energy X-ray absorptiometry (DXA) is recognized as the reference method to measure bone mineral density (BMD) with acceptable accuracy errors and good precision and reproducibility. The World Health Organization (WHO) has established DXA as the best densitometric technique for assessing BMD in postmenopausal women and based the definitions of osteopenia and osteoporosis on its results. DXA allows accurate diagnosis of osteoporosis, estimation of fracture risk and monitoring of patients undergoing treatment. However, when DXA studies are performed incorrectly, it can lead to major mistakes in diagnosis and therapy. This article reviews the fundamentals of positioning, scan analysis and interpretation of DXA in clinical practice.
Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was warped to the size and shape of a single 2D radiographic image of a subject. Mean absolute depth errors are comparable with previous approaches utilising multiple 2D input projections.
Several approaches have been adopted to derive volumetric density (g cm(-3)) from a conventional 2D representation of areal bone mineral density (BMD, g cm(-2)). Such approaches have generally aimed at deriving an average depth across the areal projection rather than creating a formal 3D shape of the bone.
Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was subsequently warped to suit the size and shape of a single 2D radiographic image of a subject. CT scans of excised human femora, 18 and 24 scanned at pixel resolutions of 1.08 mm and 0.674 mm, respectively, were equally split into training (created 3D shape template) and test cohorts.
The mean absolute depth errors of 3.4 mm and 1.73 mm, respectively, for the two CT pixel sizes are comparable with previous approaches based upon multiple 2D input projections.
This technique has the potential to derive volumetric density from BMD and to facilitate 3D finite element analysis for prediction of the mechanical integrity of the proximal femur. It may further be applied to other anatomical bone sites such as the distal radius and lumbar spine.
This paper proposes a diagnostic method that deals with obtaining diagnostic information on parts of engine systems. The focus of the research is on momentary state of engine lighting equipment "all ok" and "candle fault". The final diagnostic system should recognize "cable fault" and "transformer fault" in addition. Today's diagnostic systems used in vehicles are based on separate diagnostic subsystems for each electronic or electric device. The basic idea of the project is to develop a centralized diagnostic method to cover all functional systems. The proposed method would expedite the overall testing time and bring other significant advantages such as savings on test equipment. The fundamental idea is that both electronic and electric devices in a vehicle have a relationship to communication control busses. Also each device can be described as an electrical consumer with its typical power consumption characteristics. Hence, the proposed diagnostic method is based on investigating transient profile on power lines of a tested device whilst changing its state from off to on. The short time Fourier transform (STFT) processing is then applied to analyze the gained signal. The analysis results evaluate the condition of the engine lighting equipment.
The authors describe a general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces. The method handles the full six degrees of freedom and is based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point. The ICP algorithm always converges monotonically to the nearest local minimum of a mean-square distance metric, and the rate of convergence is rapid during the first few iterations. Therefore, given an adequate set of initial rotations and translations for a particular class of objects with a certain level of `shape complexity', one can globally minimize the mean-square distance metric over all six degrees of freedom by testing each initial registration. One important application of this method is to register sensed data from unfixtured rigid objects with an ideal geometric model, prior to shape inspection. Experimental results show the capabilities of the registration algorithm on point sets, curves, and surfaces
For vibration signal analysis, the objective is usually to extract frequency data from a signal and study how the signal's frequency content changes with time. Because wavelets are local functions of time, each with a predetermined frequency content, wavelet analysis provides a good means of doing this. As a result, practical wavelet analysis is growing rapidly. There are many different wavelets to use but no accepted procedure for choosing between them. This paper discusses various alternative wavelets for practical calculations and describes two of the key numerical algorithms. Examples of recent applications using these algorithms are reviewed, including vibration monitoring and detection, transient signal analysis and denoising.
As known in the industry, ISO has two specifications for computing Sound Power from sound pressure data measured in a laboratory environment: ISO-3745, a precision method and ISO-3744, an engineering method. The two specifications differ in a variety of ways including the qualification procedures for the test environment. In this paper, the authors provide a quick synopsis of the major differences between these two standards from the standpoint of the room qualification procedures and their impact on compressor data validity and portability. Comparison of room qualification testing strategies will also be provided with recommendation for ways to speed up the test, and analyze and display the data.
The paper describes an unusual approach to diagnose standard ignition subsystem of fuel engines. All the information about real state conditions of the ignition coils and sparks is taken from simple measurement of power consumption transient of the electric control systems of engine. The transient is processed by continuous wavelet transformation (CWT). Result of the CWT is used for a classifier. Classifier is supposed to work in learning and diagnostic modes. The main output of the classifier is two disjoint states meaning correct and incorrect functional work of the engine ignition system. The described method is going to be used as a part of standard information equipment of vehicles. The method could bring saving the costs for automobile manufacturer.
A method to obtain 3D structural measurements of the proximal femur from 2D DXA images and a statistical atlas is presented. A statistical atlas of a proximal femur was created consisting of both 3D shape and volumetric density information and then deformably registered to 2D fan-beam DXA images. After the registration process, a series of 3D structural measurements were taken on QCT-estimates generated by transforming the registered statistical atlas into a voxel volume. These measurements were compared to the equivalent measurements taken on the actual QCT (ground truth) associated with the DXA images for each of 20 human cadaveric femora. The methodology and results are presented to address the potential clinical feasibility of obtaining 3D structural measurements from limited angle DXA scans and a statistical atlas of the proximal femur in-vivo.
Use of the orthogonal wavelet transform to detect abnormal transients generated by early gear damage from the gearbox casing vibration signal is discussed. Orthogonal wavelets, such as Daubechies 4 and harmonic wavelets, are used to transform the time domain synchronous vibration signal into the time-scale domain. The orthogonal wavelet transform uses fast algorithms and decomposes the signal onto the minimum number of wavelet series. However comparison with the non-orthogonal wavelet transform for the same length of discrete data shows that the description of the signal in the 3-dimensional map of the wavelet transform is not sufficiently comprehensive due to limited scales.
It is difficult to generate high-definition time-frequency maps for rapidly changing transient signals. New details of the theory of harmonic wavelet analysis are described which provide the basis for computational algorithms designed to improve map definition. Features of these algorithms include the use of ridge identification and phase gradient as diagnostic features.
Machine sound always carries information about the working of the machine. But in many cases, the sound has a very low SNR. To obtain correct information, the background noise has to be removed or the sound must be purified. A de-noising method is given in this paper and is successfully used in feature sound extraction. We can easily diagnose a machine using the purified sound. This de-noising method is based on the wavelet technique and uses the Morlet wavelet as the mother wavelet, because its time–frequency resolution can be adjusted to adapt to the signal to be analyzed. The method is used for extracting the sound of some vehicle engines with different types of failure. The feature sound is extracted successfully.
This paper will attempt to analyse the effectiveness of the Continuous Wavelet Transform in vibro-acoustical diagnostics of gearboxes operating under non-stationary rotational speed. For this, a simple PC-software program for signal processing and extraction of diagnostic features was developed and tested. The objective of the program test is fault-detection, localisation, and assessment at helical spur gears. This includes improvements of the visual estimation of the WT-plots, especially by the task-specific balance of time- and frequency-resolution and by the display of the wavelet amplitude versus the rotational angle in polar coordinates. The following examples demonstrate the improvements in the detection of gear faults.
The wavelet transform is used to represent all possible types of transients in vibration signals generated by faults in a gearbox. It is shown that the transform provides a powerful tool for condition monitoring and fault diagnosis. The vibration signal from a helicopter gearbox is used to demonstrate the application of the suggested wavelet by a simple computer algorithm. The major advantage of the wavelet transform for analyzing the signal is that it possesses multi-resolutions for localizing shirt-time components so that all possible types of gear faults can be displayed by a single time-scale distribution resulting from the transform.
To determine whether regional characteristics of the proximal femur could discriminate between a group of patients who had just sustained a first low-trauma femoral neck fracture (n=50) from a group of healthy volunteers (n=123).
The application of an integral bone measurement (dual-energy X-ray absorptiometry) in conjunction with a volumetric cancellous bone density measurement (quantitative computed tomography) to the proximal femur in vivo provided an estimate of the contribution of the spatial distribution of bone density to hip fracture risk prediction.
The primary finding of this study was a significant difference between male and female hip fracture risk predictor variables. In men with femoral neck fracture, a significant decrease in bone density throughout the proximal femur was observed. In women with femoral neck fracture, a combination of local bone deficits (significant decrease in cancellous bone at the site of fracture, and a decrease in cortical bone at the site of impact) and significantly larger proximal femur dimensions (femoral neck and head widths) was evident.
These results imply that effective hip fracture prevention strategies may require separate approaches for men and women. Screening programs for diminished bone density at the proximal femur have proved effective in previous studies. An approach which includes examining these local bone characteristics may further improve our ability to accurately determine hip fracture risk in vivo.
In this experimental study, we evaluated the reproducibility error of mechanical strength tests of the proximal femur when simulating a fall on the trochanter. Based on side differences in femoral failure loads in 55 pairs of femora, we estimated the upper limit of the precision error to be 15% for the side impact test, whereas the intersubject variability was >40%.
Mechanical tests are commonly used as the gold standard for determining one of the main functions of bones, that is, to provide mechanical strength. However, it is unknown what magnitude of error is associated with these tests. Here we investigate the precision error and side difference of a side impact test of the proximal femur.
BMC was measured using DXA in 54 pairs of femora from donors 79.0 +/- 10.6 years of age. Bones were tested to failure, simulating a fall on the greater trochanter.
Failure loads were 3951 +/- 1659N (CV% = 42%) on the right and 3900 +/- 1652N (CV% = 42%) on the left (no significant side difference). The average random difference of femoral BMC was 7 +/- 7% and that of femoral failure loads was 17 +/- 12%. The correlation between BMC and failure load was 79% (r2), but the association between side differences in failure load with those in BMC was only 4%. When confining the analysis to pairs with less than 5% differences in BMC (n = 31), side differences in failure loads were 15 +/- 13%. When correcting failure loads for side differences of BMC, the difference was 16 +/- 15%
These results suggest that the upper limit of the precision error for femoral strength tests is approximately 15% in a side impact configuration. Given the large intersubject variability of failure loads, this test provides an efficient tool for determining the structural strength of the proximal femur in a fall.
Three-dimensional accurate evaluation of the geometry of the proximal femur may be helpful for hip fracture risk evaluation. The purpose of this study was to apply and validate a stereo-radiographic 3D reconstruction method of the proximal femur, using contours identification from biplanar DXA images. Twenty-five excised human proximal femurs were investigated using a standard DXA unit. Three-dimensional personalized models were reconstructed using a dedicated non-stereo corresponding contours (NSCC) algorithm. Three-dimensional CT-scan reconstructions obtained on a clinical CT-scan unit were defined as geometric references for the comparison protocol, in order to assess accuracy and reproducibility of the 3D stereo-radiographic reconstructions. The precision of a set of 3D geometric parameters (femoral-neck axis length, mid-neck cross-section area, neck-shaft angle), obtained from stereo-radiographic models was also evaluated. This study shows that the NSCC method may be applied to obtain 3D reconstruction from biplanar DXA acquisitions. Applied to the proximal femur, this method showed good accuracy as compared with high-resolution personalized CT-scan models (mean error = 0.8 mm). Moreover, precision study for the set of 3D parameters yielded coefficients of variation lower than 5%. This is the first study providing 3D geometric parameters from standard 2D DXA images using the NSCC method. It has good accuracy and reproducibility in the present study on cadaveric femurs. In vivo prospective studies are needed to evaluate its discriminating potential on hip fracture risk prediction.
Active contour segmentation and its robust implementation using level set methods are well-established theoretical approaches that have been studied thoroughly in the image analysis literature. Despite the existence of these powerful segmentation methods, the needs of clinical research continue to be fulfilled, to a large extent, using slice-by-slice manual tracing. To bridge the gap between methodological advances and clinical routine, we developed an open source application called ITK-SNAP, which is intended to make level set segmentation easily accessible to a wide range of users, including those with little or no mathematical expertise. This paper describes the methods and software engineering philosophy behind this new tool and provides the results of validation experiments performed in the context of an ongoing child autism neuroimaging study. The validation establishes SNAP intrarater and interrater reliability and overlap error statistics for the caudate nucleus and finds that SNAP is a highly reliable and efficient alternative to manual tracing. Analogous results for lateral ventricle segmentation are provided.
In this paper we propose a diffeomorphic non-rigid registration algorithm based on free-form deformations (FFDs) which are modelled by B-splines. In contrast to existing non-rigid registration methods based on FFDs the proposed diffeomorphic non-rigid registration algorithm based on free-form deformations (FFDs) which are modelled by B-splines. To construct a diffeomorphic transformation we compose a sequence of free-form deformations while ensuring that individual FFDs are one-to-one transformations. We have evaluated the algorithm on 20 normal brain MR images which have been manually segmented into 67 anatomical structures. Using the agreement between manual segmentation and segmentation propagation as a measure of registration quality we have compared the algorithm to an existing FFD registration algorithm and a modified FFD registration algorithm which penalises non-diffeomorphic transformations. The results show that the proposed algorithm generates diffeomorphic transformations while providing similar levels of performance as the existing FFD registration algorithm in terms of registration accuracy.
The International Society for Clinical Densitometry (ISCD) has developed Official Positions for the clinical use of dual-energy X-ray absorptiometry (DXA) and non-DXA technologies. While only DXA can be used for diagnostic classification according to criteria established by the World Health Organization, DXA and some other technologies may predict fracture risk and be used to monitor skeletal changes over time. ISCD task forces reviewed the evidence for clinical applications of non-DXA techniques and presented reports with recommendations at the 2007 ISCD Position Development Conference. Here we present the ISCD Official Positions for quantitative computed tomography (QCT) and peripheral QCT (pQCT), with supporting medical evidence, rationale, controversy, and suggestions for further study. QCT is available for bone mineral density measurements at the spine, hip, forearm, and tibia. The ISCD Official Positions presented here focus on QCT of the spine and pQCT of the forearm. Measurements at the hip may have clinical relevance, as this is an important fracture site; however, due to limited medical evidence, definitive advice on its use in clinical practice cannot be provided until more data emerge.
The decomposition of deformations by principal warps is
demonstrated. The method is extended to deal with curving edges between
landmarks. This formulation is related to other applications of splines
current in computer vision. How they might aid in the extraction of
features for analysis, comparison, and diagnosis of biological and
medical images in indicated
Femur Bone Distribution and Geometry Reconstruction from a Single DXA Image " accepted for SPIE Medical Imaging
- T Whitmarsh
- L Humbert
- M De
T. Whitmarsh, L. Humbert, M. De Craene et al., " Femur Bone Distribution and Geometry Reconstruction from a Single DXA Image " accepted for SPIE Medical Imaging, 2010.
Analýza chování zapalovacihoustroji v automobilu Å koda (in Czech)
- Jakub Král
- Petr Jezdik
Centralised diagnostic of electronic and electric equipment in vehicles - engine lighting equipment testing
- P Ježdik
- J Novák