Engineering Applications of Artificial Intelligence
Case-based expert system using wavelet packet transform and kernel-based feature manipulation for engine ignition system diagnosis
Highlights
► CBR provides multiple possible diagnoses instead of a single most probable diagnosis. ► CBR can overcome the problem of incremental and decremental knowledge update. ► Techniques such as WPT, KPCA and KKM are employed. ► Superior classification results than SVM and MLP diagnosis have been verified in a selected application.
Introduction
Automotive engine ignition systems vary in construction, but are similar in basic operation. All have a primary circuit that causes a spark in the secondary circuit. This spark must then be delivered to the correct spark plug at the proper time. Conditions in the ignition system and in the cylinder affect the ignition pattern (i.e. scope pattern) in the secondary circuit. An automotive oscilloscope, also known as a scope meter, is considered a valuable tool for detecting engine and ignition problems by displaying the scope patterns for analysis of the operation of an ignition system. The scope patterns can reflect the conditions within the ignition system and help pinpoint their causes of failure, such as narrow spark-plug gaps, open spark-plug cables, a shorted ignition coil, etc. In a typical diagnosis, the scope patterns are usually matched against a normal pattern. Fig. 1 shows some examples of scope patterns and their corresponding engine faults.
A pattern pickup-clamp for an automotive scope meter is necessary when an automotive scope meter for engine trouble diagnosis is used. The pickup-clamp is usually connected to the ignition system to capture its spark ignition patterns. Capturing ignition pattern usually requires intervention of the mechanic to indicate the start and end points of the pattern. The captured pattern would then be compared with samples from the handbooks (Liu and Chu, 2005, Crouse and Anglin, 1993) for diagnosis. The diagnosis is always based on domain knowledge and user experience because the samples from the handbooks are for reference only. However, the ignition patterns are time-varying and non-stationary. Different engine models produce various amplitude and duration for the same ignition system trouble. Even on the same engine, different sizes of ignition patterns under different engine operating conditions may be produced, which increases the difficulty for human diagnosis. Moreover, the ignition patterns of many engine faults are very similar, leading to increased difficulty in identifying the patterns correctly. After diagnosis, the corresponding parts in the ignition system will be disassembled for intensive investigation (this is called a trial). In view of the inaccuracy of human diagnosis, identifying a fault based on ignition patterns, several trials for disassembling and assembling of engine parts are necessary, which incurs a large amount of time and effort by the mechanic. A computer-based pattern classification system is proposed to aid an automotive mechanic for this problem.
Currently, there is very little research in the literature (Vong and Wong, 2011) on computer-aided ignition pattern analysis for automotive engine ignition system trouble-diagnosis. The development of an intelligent system for engine ignition system diagnosis is a promising area of research.
Machine learning methods (Xue and Zhu, 2009, Kotsiantis, 2007, Whiteson and Whiteson, 2009) play an important role in the pattern recognition, such as multi-layer perceptions (MLP) and support vector machines (SVM). A major focus of machine learning research is to automatically learn recognition of complex patterns and make intelligent decisions based on sampled data. In this research, if the computer-aided diagnostic system is designed merely based on captured signals, the accuracy will likely be poor due to the excessive similarity between the captured signals. Applying this rationale, machine learning methods combined with domain knowledge are proposed in this research. However, most of the machine learning methods can only provide a user with a single solution. To increase the chance of locating the faults, a case-based reasoning (CBR) expert system is proposed, which can generate multiple diagnoses, instead of the single most probable one generated by traditional network-based classifiers such as MLP and SVM (Fig. 2). This kind of CBR expert system helps a mechanic make a final decision. From this viewpoint, CBR paradigm fits the requirements of the expert system better. In addition, CBR can overcome the problem of incremental and decremental knowledge update as compared to inductive learning (Smyth and Cunningham, 1995) such as MLP and SVM. Moreover, when adding or removing a case, the maintenance of CBR classifier is relatively easy.
One of the main difficulties of building a CBR diagnostic system is to define the clear and effective case representation in the case library. In the current research, it is unwise to directly put the captured signals in the case representation. The ignition patterns captured by the scope meter are very similar and their differences can only be compared under extracted features. Similar work extracting effective representation from sensor signals can be found in (Funk and Xiong, 2008) and hence wavelet packet transform (WPT) is proposed for the purpose of feature extraction. However, the number of the extracted WPT features for an ignition signal is very large (about 18,000 points) so that the computational cost of building and running the diagnostic system will be very high. For this reason, kernel principal component analysis (KPCA) is proposed to perform a dimension reduction while retaining most of the pattern information of the ignition signals. Finally, the set of features processed by WPT and KPCA along with the domain knowledge of the signals constitutes the case representation of the CBR diagnostic system. CBR is effective but mostly inefficient in computational time because every instance in a case library must be compared during its reasoning, i.e., retrieval. To overcome this inefficiency, a clustering method of kernel k-means (KKM) was employed to compress the case library, where similar cases were clustered into a fixed number of representative cases. Using this set of representative cases, retrieval time can be further reduced significantly. In the following section, the employed techniques are briefly discussed.
Section snippets
Employed techniques
Following the above discussion, we employed WPT for feature extraction, and KPCA for dimension reduction for this work. These two techniques were used for preprocessing the raw captured patterns to form a case library. KKM was examined for clustering the case library into a set of representative cases, for which CBR works in diagnosis. The CBR design and reasoning steps were subsequently addressed.
Domain features for engine ignition patterns
When an engine starts firing, its secondary coil produces rapid high voltage causing a spark plug to produce spark. This high voltage is called firing voltage. The spark voltage represents the voltage required to maintain spark for the duration of the spark line. The duration is called burn time. After the burn time, the energy in the ignition coil nearly exhausts, and the residual energy forms slight oscillations in the ignition coil. This entire procedure is shown in Fig. 9. Using the spark
System workflow
The current diagnostic system includes two modules for preprocessing (Fig. 10) and CBR diagnosis. The ignition patterns are passed to the preprocessing module for normalization, feature extraction under WPT to form a feature vector and then dimension reduction under KPCA. The preprocessed patterns are subsequently stored in WPT_KPCA_DATA (Fig. 10). Meanwhile, the three domain features for every pattern are also extracted to form 3F_DATA (Fig. 10). The features in 3F_DATA combine with that in
Experiment and results
Experiments were carried out to verify the effectiveness of the proposed CBR methodology. Besides, typical classification approaches, SVM and MLP, were also used to respectively construct a classification system for making the comparison with CBR approach. Details of the experiments and their results are discussed in the following sections.
Conclusions
CBR classifier enhanced with KKM technique had been successfully applied to construct a reliable computer-aided diagnostic system for the automotive engine ignition system. From the experimental results, the CBR classifier produced higher accuracy than the traditional MLP and SVM classifiers. The most important appeal of CBR over MLP and SVM is that multiple solutions can be recommended to the user for final decision. This is a more practical and reliable procedure for the automotive mechanics.
Acknowledgments
The research is supported by the University of Macau Research Grant, Grant no. RG064/09-10S/VCM/FST.
References (45)
- et al.
Emerging applications of wavelets: a review
Physical Communication
(2010) - et al.
A novel wavelet transform aided neural network based transmission line fault analysis method
International Journal of Electrical Power & Energy Systems
(2009) - et al.
A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine
Neurocomputing
(2003) - et al.
Multiscale texture classification using dual-tree complex wavelet transform
Pattern Recognition Letters
(2009) - et al.
Target recognition in clutter scene based on wavelet transform
Optics Communications
(2009) - et al.
A predictive current control method for shunt active filter with windowing based wavelet transform in harmonic detection
Simulation Modelling Practice and Theory
(2009) - et al.
On using prototype reduction schemes to optimize kernel-based nonlinear subspace methods
Pattern Recognition
(2004) - et al.
CBR methodology application in an expert system for aided design ship's engine room automation
Expert Systems with Applications
(2005) - et al.
A new reactive, distortion and non-active power measurement method for nonstationary waveforms using wavelet packet transform
Electric Power Systems Research
(2009) - et al.
Analysis of a signal during bistable flow events in Laguna Verde Nuclear Power Station with wavelets techniques
Nuclear Engineering and Design
(2009)
Are case-based reasoning and dissimilarity-based classification two sides of the same coin?
Engineering Applications of Artificial Intelligence
Concepts for novelty detection and handling based on a case-based reasoning process scheme
Engineering Applications of Artificial Intelligence
Analysis of two variants of a spatially distributed crop model, using wavelet transforms and geostatistics
Agricultural Systems
Wavelet analysis of the surface temperature field at an air–water interface subject to moderate wind stress
International Journal of Heat and Fluid Flow
KPCA denoising and the pre-image problem revisited
Digital Signal Processing
Fast pruning algorithm for multi-output LS-SVM and its application in chemical pattern classification
Chemometrics and Intelligent Laboratory Systems
An effective wavelet-based feature extraction method for classification of power quality disturbance signals
Electric Power Systems Research
Case-based adaptation for automotive engine electronic control unit calibration
Expert Systems with Applications
Engine ignition signal diagnosis with wavelet packet transform and multi-class least squares support vector machines
Expert Systems with Applications
Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference
Engineering Applications of Artificial Intelligence
Machine learning next term for event selection in high energy physics
Engineering Applications of Artificial Intelligence
A cluster-based wavelet feature extraction method and its application
Engineering Applications of Artificial Intelligence
Cited by (27)
Deep time–frequency learning for interpretable weak signal enhancement of rotating machineries
2023, Engineering Applications of Artificial IntelligenceApplications of machine learning to machine fault diagnosis: A review and roadmap
2020, Mechanical Systems and Signal ProcessingCitation Excerpt :Wu et al. [93] developed an expert system for fault diagnosis of modern commercial aircrafts, which was designed by the case-based reasoning and the fuzzy logic. Vong et al. [94] constructed a computer-aided diagnosis system based on the case-based reasoning and the kernel k-means for the automotive engine ignition system. The expert system-based diagnosis models represent the diagnosis knowledge from experts as the inference algorithm to automatically recognize the health states of machines.
Risk response for urban water supply network using case-based reasoning during a natural disaster
2018, Safety ScienceCitation Excerpt :Based on this, CBR has increasingly attracted more and more attention in emergency response management. For case representation, an original and simple way of case representation is to use problem-solution pairs with the related features (Vong et al., 2011). Then, for better illustration, knowledge representation methods such as frame model (Liao et al., 2012, Liao et al. (2011)) and ontology model (Amailef and Lu, 2013; Delir Haghighi et al., 2013; Malizia et al., 2010) have been employed to express emergency case, which can lay the foundation to support CBR in building case structure and implementing query operation.
Risk upper bound for a NM-type multiresolution classification scheme of random signals by Daubechies wavelets
2017, Engineering Applications of Artificial IntelligenceCitation Excerpt :It can be embedded in classifier, creating a new complex classification method. These methods include modifications of well known algorithms, e.g. wavelet support vector machines (WSVMs) (Ren et al., 2011; Zhang et al., 2004), kernel k-means (KKM) (Vong et al., 2011), kernel Fisher discriminant analysis (KFDA) (Peng et al., 2013), kernel principal component analysis (KPCA) (Hejazi et al., 2016), or hidden Markov tree (HMT) (Tomassi et al., 2010). For complex classification problems, much effort was made to create more accurate combined classifiers.
Simultaneous-fault detection based on qualitative symptom descriptions for automotive engine diagnosis
2014, Applied Soft Computing JournalCitation Excerpt :Data-driven engine diagnosis methods, on the other hand, rely on signal-based diagnosis or engine oil analysis. Signal-based diagnosis is recently the most popular method [8–15] because it is very suitable for laboratories and the development of automotive scan tools, computerized engine analyzers, engine condition monitoring and on-board diagnostic systems. Its main drawback is that many signal patterns are engine type dependent.