Misfire Detection Research Articles

A study on misfire detection by calculating crank angular velocity considering in-cylinder gas properties

Misfire detection using a new crank angular velocity calculation was studied for high efficiency and robust engine ignition performance and combustion stability control. An applying production was achieved by applying in-cylinder gas properties prediction and its correction to the misfire index and verifying it under various conditions. The relationship between the misfire index and torque fluctuation was consistent depending on the combustion control factors EGR, injection timing, pilot injection quantity change, and environmental change factors water temperature and intake gas temperature. On the other hand, it was found that the piston speed changes due to the in-cylinder pressure with respect to the intake pressure, and the crank angular speed needs to be corrected. Commonly used sensors for engine cooling water temperature, intake gas temperature, intake pressure, and engine speed were used as representative values for in-cylinder pressure, and the cooling loss was subtracted from the polytropic index and the reduction in specific heat ratio due to EGR was corrected. By building a new model that calculates the compression end pressure model from the polytropic index and adding corrections to the misfire index, we applied logic that can be calculated for each cycle to the ECU onboard. Conventionally, compression end pressure prediction requires calculations that take combustion conditions into account, which requires the number of sensors and their accuracy, and a long calculation time. However, in this study, Authors focused on the fact that the pressure at TDC during a misfire does not include ignition and combustion phenomena and expressed the necessary physical phenomena using the minimum sensor information. As a result of the above, a control structure at a level that can be applied to products was obtained.

Misfire Detection Index Distinguishing the Difference of the Engine Angular Acceleration Between Two Specified Teeth of the Sensor Wheel

Misfire Detection Index Distinguishing the Difference of the Engine Angular Acceleration Between Two Specified Teeth of the Sensor Wheel

Detection and identification of cylinder misfire in small aircraft engine in different operating conditions by linear and non-linear properties of frequency components

We suggest an approach for detecting and identifying ignition failure on a internal combustion engine used in aviation through the analysis of vibration time series. The research is carried out at the experimental stage, where time series of vibrations are collected from sensors installed in various parts of the facility at various rotational speeds and various operating conditions (no failure/failure of a selected piston). The time series were decomposed into periodic components centered around dominant frequencies. Data with greater dimensionality was statistically described using linear and non-linear indicators in short time windows, and labeled accordingly. Instead of examining the statistical significance of the characteristics of individual groups, machine learning classification methods were used, which allowed to distinguish the operating state of the engine (damaged/undamaged), and also to identify a specific unfired cylinder. The use of non-linear indicators allowed us to obtain 100% classification accuracy with a small number of samples.

MITDCNN: A multi-modal input Transformer-based deep convolutional neural network for misfire signal detection in high-noise diesel engines

The accurate detection of faults in diesel engines is crucial for extending their operational lifespan, ensuring safety, and yielding significant economic and societal benefits. However, existing detection methodologies encounter difficulties in the presence of substantial environmental noise and lack generalizability across various operating conditions. Traditional fault diagnosis models also predominantly rely on single data detection schemes, such as one-dimensional data input for anomaly analysis, which may not account for the inherent correlations and distribution discrepancies within the same data source presented in different formats. To tackle these challenges, we proposed a novel multi-modal input Transformer-based convolutional neural network (MITDCNN) for misfire detection in diesel engines under significant environmental noise and diverse working conditions. We collected vibration signals from engine cylinder heads at different speeds and extracted both one-dimensional amplitude vector features and two-dimensional image properties. These features were input into the multi-modal feature extraction network and subsequently processed and identified by the cross-channel feature fusion detection network. Our fusion module incorporated a dual-dimension spatial and channel attention mechanism to suppress vibration noise interference effectively, so that the network is able to counteract the impact of environmental noise and varying operating conditions on the final detection outcomes. We validated the efficacy of the proposed approach through a curated dataset and benchmark comparisons with the established algorithms. Our results demonstrate that MITDCNN's accuracy and noise robustness are notably superior to other available methods. Across four datasets generated under distinct working conditions, our approach achieves a minimum accuracy of 99.008%, even with a signal-to-noise ratio of −4dB, greatly surpassing other methods.

HCCI technology using hydrogen energy and artificial intelligence

The principle of a HCCI engine is to inject a mixture of fuel and air into the cylinder and allow it to self-ignite under a high compression ratio. Unlike traditional gasoline and diesel engines, the mixture in the HCCI engine is homogeneous and does not require an ignition system to ignite it. The air-fuel mixture in the cylinder is burned completely by compressing. It makes effective use of fuel. The structure is simpler than a conventional internal combustion engine. HCCI engine has a huge application prospect in many fields. Among them, the automobile is one of the biggest parts. However, some applications have not been widely used. Although the HCCI engine has so many advantages, as this study has discussed, many of its drawbacks are still serious, such as the difficulty in controlling the parameters in the combustion and work process, resulting in the theoretical process being difficult to realize fully. The stringent environmental constraints of HCCI engines, the scarcity of suitable fuels and the significantly lower lifetime of HCCI engines than conventional engines pose significant obstacles to their practical use. This study presents the idea of using artificial intelligence system-assisted control system to accurately control HCCI engines in real time, which has shown great potential in HCCI engine misfire detection and HCCI engine initial burn time prediction.

Misfire Detection Technology with Deep Neural Network Based on Ignition Coil Signals

<div>For achieving high efficiency and low exhaust emissions, engines need to be operated near the limits of stable combustion, such as lean or exhaust gas recirculation (EGR) conditions. Sensing technologies of the combustion state by existing engine components are of high interest. And the utilization of voltage and current signals from ignition coils is discussed in this article. The discharge channel of an ignition spark is strongly affected by flow variation and spark plug surface conditions, and the behavior of discharge channel stretching and restrike event can vary greatly from cycle to cycle. As a result, the effects of flow velocity, temperature, pressure, and electrode surface resistance are compounded in the voltage-current response, making it difficult to accurately detect the combustion state for each cycle by a threshold judgment process using a single feature value.</div> <div>In this article, a method for inductively detecting misfires from voltage and current signals of ignition coils by applying deep learning image recognition is introduced. First, post-ignition for misfire detection is performed on the engine bench during the expansion stroke in an engine cycle, when the cylinder pressure is expected to differ between the combustion cycle and the ignition cycle, and the ignition coil voltage and current are measured. Next, a two-dimensional frequency distribution of voltage and current (discharge histogram) is created as an input image for deep learning, and the AlexNet model, which has been trained with more than one million images, is trained with images of the ignition and combustion cycles as a supervised learning. The accuracy of classification is then verified using a validation dataset. In addition, to making the deep learning model more explainable, the activation score distribution on the discharge histogram was visualized when the trained model judges the images, and the discharge characteristics that provided the basis for deep learning classifications were analyzed.</div>

Review of Artificial Intelligent Algorithms for Engine Performance, Control, and Diagnosis

This paper reviews the artificial intelligent algorithms in engine management. This study provides a clear image of the current state of affairs for the past 15 years and provides fresh insights and improvements for future directions in the field of engine management. The scope of this paper comprises three main aspects to be discussed, namely, engine performance, engine control, and engine diagnosis. The first is associated with the need to control the basic characteristics that prove that the engine is working properly, namely, emission control and fuel economy. Engine control refers to the ability to identify and fulfill the requirements derived from performance, emissions, and durability. In this part, hybrid electric vehicle (HEV) application and transient operations are discussed. Lastly, engine diagnosis entails assessment techniques that can be used to identify problems in the engine and solve them accordingly. In this part, misfire detection, knock detection, and intake system leakage will be evaluated. In engine performance, neural network algorithms provide efficient results in terms of emission control and fuel economy as the requirements are easily achievable. However, when it comes to engine control and diagnosis, the fuzzy logic rule with its strong robustness and neural networks algorithms are limited in efficiency due to the complex nature of the processes and the presence of big data, for instance, in HEVs in engine control. That has brought forward the usage of reinforcement learning and novel machine learning algorithms in recent years to maximize efficiency in engine control and engine diagnosis, as highlighted in the following part. The PRISMA methodology was used to justify the reference selection in this review.

A Transformer-Based Framework for Misfire Detection From Blasting-Induced Ground Vibration Signal

The growing popularity of electronic detonators in tunnel construction facilitates the application of short-delay millisecond blasting. However, the occurrence of misfire endangers personnel safety, which the current blasting initiation system cannot identify. This article proposes a transformer-based framework for misfire detection from blasting-induced ground vibration signals and compares its capability with the signal processing method variational mode decomposition (VMD). The framework is established on a transformer structure cutting with locality self-attention vision transformer (CtL-ViT), which includes a cut embedding process and a locality self-attention calculation mechanism. Field experiments were conducted at a shallow tunnel construction site, and ground vibration signals were recorded. The proposed framework surpasses the VMD method in terms of higher misfire detection accuracy, precision, recall, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}_{1}$ </tex-math></inline-formula> score, which are 97.5%, 91.9%, 99.7%, and 95.8%, respectively. The current results demonstrate the feasibility of CtL-ViT and the inapplicability of VMD in handling a short-delay hole-by-hole vibration signal and reveal the potential of the CtL-ViT framework as a second layer of protection.

Misfire Detection in Spark Ignition Engine Using Transfer Learning.

Misfire detection in an internal combustion engine is an important activity. Any undetected misfire can lead to loss of fuel and power in the automobile. As the fuel cost is more, one cannot afford to waste money because of the misfire. Even if one is ready to spend more money on fuel, the power of the engine comes down; thereby, the vehicle performance falls drastically because of the misfire in IC engines. Hence, researchers paid a lot of attention to detect the misfire in IC engines and rectify it. Drawbacks of conventional diagnostic techniques include the requirement of high level of human intelligence and professional expertise in the field, which made the researchers look for intelligent and automatic diagnostic tools. There are many techniques suggested by researchers to detect the misfire in IC engines. This paper proposes the use of transfer learning technology to detect the misfire in the IC engine. First, the vibration signals were collected from the engine head and plots are made which will work as input to the deep learning algorithms. The deep learning algorithms have the capability to learn from the plots of vibration signals and classify the state of the misfire in the IC engines. In the present work, the pretrained networks such as AlexNet, VGG-16, GoogLeNet, and ResNet-50 are employed to identify the misfire state of the engine. In the pretrained networks, the effect of hyperparameters such as back size, solver, learning rate, and train-test split ratio was studied and the best performing network was suggested for misfire detection.

Misfire Detection in Automotive Engines Using a Smartphone through Wavelet and Chaos Analysis.

Besides the failures that cause accidents, there are the ones responsible for preventing the car’s motion capacity. These failures cause inconveniences to the passengers and expose them to the dangers of the road. Although modern vehicles are equipped with a failure detection system, it does not provide an online approach to the drivers. Third-party devices and skilled labor are necessary to manage the data for failure characterization. One of the most common failures in engines is called misfire, and it happens when the spark is weak or inexistent, compromising the whole set. In this work, two algorithms are compared, based on Wavelet Multiresolution Analysis (WMA) and another using an approach performing signal analysis based on Chaos using the density of maxima (SAC-DM) to identify misfare in a combustion engine of a working automotive vehicle. Experimental tests were carried out in a car to validate the techniques for the engine without failure, with failure in one piston, and with two failed pistons. The results made it possible to obtain the failure diagnosis for 100% of the cases for both WMA and SAC-DM methods, but a shorter time window when using the last one.

Numerical Evaluation of the Effect of Fuel Blending with CO2 and H2 on the Very Early Corona-Discharge Behavior in Spark Ignited Engines

Reducing green-house gases emission from light-duty vehicles is compulsory in order to slow down the climate change. The application of High Frequency Ignition systems based on the Corona discharge effect has shown the potential to extend the dilution limit of engine operating conditions promoting lower temperatures and faster combustion events, thus, higher thermal and indicating efficiency. Furthermore, predicting the behavior of Corona ignition devices against new sustainable fuel blends, including renewable hydrogen and biogas, is crucial in order to deal with the short-intermediate term fleet electric transition. The numerical evaluation of Corona-induced discharge radius and radical species under those conditions can be helpful in order to capture local effects that could be reached only with complex and expensive optical investigations. Using an extended version of the Corona one-dimensional code previously published by the present authors, the simulation of pure methane and different methane–hydrogen blends, and biogas–hydrogen blends mixed with air was performed. Each mixture was simulated both for 10% recirculated exhaust gas dilution and for its corresponding dilute upper limit, which was estimated by means of chemical kinetics simulations integrated with a custom misfire detection criterion.

Misfire Detection Using Crank Speed and Long Short-Term Memory Recurrent Neural Network

In this work, a new approach was developed for the detection of engine misfire based on the long short-term memory recurrent neural network (LSTM RNN) using crank speed signal. The datasets are acquired from a six-cylinder-inline, turbo-charged diesel engine. Previous works investigated misfire detection in a limited range of engine running speed, running load or misfire types. In this work, the misfire patterns consist of normal condition, six types of one-cylinder misfire faults and fifteen types of two-cylinder misfire faults. All the misfire patterns are tested under wide range of running conditions of the tested engine. The traditional misfire detection method is tested on the datasets first, and the result show its limitation on high-speed low-load conditions. The LSTM RNN is a type of artificial neural network which has the ability of considering both the current input in-formation and the previous input information; hence it is helpful in extracting features of crank speed in which the misfire-induced speed fluctuation will last one or a few cycles. In order to select the engine operating conditions for network training properly, five data division strategies are attempted. For the sake of acquiring high performance of designed network, four types of network structure are tested. The results show that, utilizing the datasets in this work, the LSTM RNN based algorithm can overcome the limitation at high-speed low-load conditions of traditional misfire detection method. Moreover, the network which takes fixed segment of raw speed signal as input and takes misfire or fault-free labels as output achieves the best performance with the misfire diagnosis accuracy not less than 99.90%.

Real-time abnormality detection and classification in diesel engine operations with convolutional neural network

In this paper, we propose a real-time diagnostic method using a convolutional neural network (CNN) to detect cylinder misfires and engine load conditions in multi-cylinder internal combustion (IC) diesel engines. To enhance engine efficiency and reliability, it is necessary to detect and classify multiple irregularities in engine operation, such as misfires and changes in load conditions. Optimized combustion parameter setting increases engine efficiency, which depends on the engine load conditions. Similarly, misfire detection prevents engine damage and increases fuel efficiency and reliability of the engine. Previous works investigated misfire detection while ignored the change in engine operating conditions that affects the engine efficiency. This work presents a real-time CNN-based method to detect misfires and load changes together in engine operations by analyzing the IC process. First, the sensor signal is pre-processed to extract a primary signal and translate it into a crank angle degree (CAD) signal, which represents a complete cycle of the IC process in the engine. After that, a CNN is designed for multi-class classification and trained using one-dimensional CAD vectors, which combines a feature extraction capability and pattern recognition in a single learner. The proposed CNN-based method detects and classifies multiple abnormalities in engine operations with an accuracy of more than 99% and low generalization error. The designed CNN uses a single convolutional layer for feature extraction resulting in more efficient systems in terms of performance and speed.

Tooth Time-Based Engine Misfire Detection Index for Multicylinder Engines of Vehicles Not Affected by Various Deviations between Cylinders

Tooth Time-Based Engine Misfire Detection Index for Multicylinder Engines of Vehicles Not Affected by Various Deviations between Cylinders

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

DTCNNMI: A deep twin convolutional neural networks with multi-domain inputs for strongly noisy diesel engine misfire detection

Although machine learning-based intelligent detection methods have made many achievements for diesel engine misfire diagnosis, they suffer from a certain degree of performance degradation due to the strong environmental noise and the change of working conditions in the actual application scenarios. To tackle this issue, this study presents a deep twin convolutional neural networks with multi-domain inputs (DTCNNMI) for diesel engine misfire diagnosis under strong environmental noise and different working conditions. Vibration signals of engine cylinder heads at different speeds are collected experimentally and fed into input layers of the proposed model. It constructs three input layers to combine automatically extracted time-domain, time-frequency-domain and hand-craft time-domain statistical features, improving the model performance. Twin convolutional neural networks with large first-layer kernels are presented for extracting multi-domain information of vibration signals and resist influence of environmental noise and the change of operating conditions on the final diagnosis results. The effectiveness of the proposed approach is validated on the datasets collected experimentally and by making comparison with the existing representative algorithms. The results demonstrate that the accuracy and anti-noise performance of the proposed DTCNNMI outperforms the existing algorithms. On the constructed four datasets under different working conditions, the proposed method achieved at least 97.019% accuracy even when signal-to-noise ratio was −4 dB, which is much higher than those of the other methods. Moreover, the accuracy of the proposed DTCNNMI on datasets A, B, C and D is at least 61.177%, 33.334%, 17.646% and 29.961% higher than other methods, respectively.

이산 푸리에 변환 기반의 엔진 실화 진단

이산 푸리에 변환 기반의 엔진 실화 진단

Misfire detection of diesel engine based on convolutional neural networks

With the ever-stringent vehicles exhaust emission standard and higher requirements on on-board diagnostic technology, the importance of misfire detection in vehicle emission control is emerging. The performance of a traditional misfire detection algorithm predominantly depends on the features and classifier selected. Fixed and handcrafted features require either a reliable dynamic model of an engine or a large number of experiment data to define the threshold, and then, form a map. Since convolutional neural networks (CNNs) have an inherent adaptive design and integrate the feature extraction with classification functions into a compact learning framework, the misfire fault-sensitive features can be auto-discovered from raw speed signals. Furthermore, CNNs can detect the fault features of the misfire through network training with fewer engine operating conditions. In this paper, the theory and method of the misfire diagnosis based on CNNs are presented. The experimental data for network training and testing are sampled on a six-cylinder inline diesel engine. The misfire patterns containing every one-cylinder and two-cylinder misfire are tested under the wide speed and load conditions of the engine. The results show that when the engine operates under steady-state conditions, one-cylinder or two-cylinder complete misfires can be detected accurately by CNNs. In addition, one-cylinder partial misfire is employed to examine the adaptability of trained 1-D CNN. It turns out that when the partial misfire reaches the same level as half amount of the normal fuel injection quantity, one-cylinder partial misfire can be detected with accuracy more than 96%. At last, the misfire detection under the non-stationary conditions, such as acceleration or deceleration, is conducted. The results show the 1-D CNN performed well in a limited acceleration range, and network failure occurs when the absolute acceleration of the engine speed is more than 100 r/min/s.

Detection of cylinder misfire in an aircraft engine using linear and non-linear signal analysis

The aim of research was to detect the misfire of individual cylinders of the Rotax 912 ULS aircraft engine based on engine vibration signals. Vibrations were recorded in three direction, and their time series subject to linear frequency analysis and non-linear recurrence analysis. The greatest vibration difference between a fully operational engine and the engine with one piston off was observed along the piston movement axis (Y-axis). With one cylinder off, the dynamic response of the engine changed in both linear and non-linear manner. Based on the spectral value of the power amplitude of two selected frequencies, a linear indicator describing the vibration level was developed. The values of non-linear indicators were calculated on the basis of the periodicity of the engine operation. Both methods proved capable of qualitatively detecting the fact of misfires in various cylinder configurations. Used in combination, they enable user to identify the defective cylinder.

Effects of misfire on the dynamic behavior of gasoline Engine Crankshafts

Misfire faults caused by the malfunction of single cylinder increases the emission level and fuel consumption of internal combustion. So, the detection of misfire is required.In this paper, we studied the effect of misfire on the dynamic response of the crankshaft in order to propose a method based on the torsional vibration signal of crankshaft acceleration for misfire detection. For this, a torsional model of a four cylinder crankshaft excited by the acyclism phenomena is proposed. The external forces are the inertia and gas torque of each engine cylinder. The equations of motion are obtained by using Lagrange method and computed with the help of Newmark algorithm. Three kind of misfire faults of the first cylinder are modeled through the gas pressure variation inside this cylinder and induced in the excitation torques: missing combustion, pre-ignition and delayed ignition. After that, the vibration responses of the crankshaft is computed and processed in order to highlight the effect of misfire defects on the crankshaft vibration signals. In fact, appearance of sidebands around the acyclism frequency in the frequency domain allow detecting the misfire and the time acceleration signal allows identifying the kind of defect.