Engine Fault Research Articles

Estimating Remaining Useful Life of Turbofan Engine Using Data-Level Fusion and Feature-Level Fusion

Degradation of systems is a natural and inevitable process which widely happens in industries. Therefore, prognostics is used to prevent unexpected failures of complex engineering systems by evaluating the health status of the system and estimating the remaining useful life, using multiple sensors that simultaneously monitor the degradation process of the system. Since these sensor signals often have usable and effective information about a degradation process, data fusion methods are used to obtain more precise and reliable prognostic results. In this paper, the problem of prognostic modeling and remaining useful life estimation of the turbofan engine is considered and a methodology is proposed using data-level and feature-level fusion approaches to better characterize the degradation process of the system. A degradation model for the engine fault is developed by combining a physics-based model and a Wiener process with positive drift. The maximum likelihood estimation method is used to estimate the unknown parameters of the model. Eventually, the remaining useful life is estimated for testing data of a case study involving the degradation of a turbofan engine, and the results are evaluated.

Machine learning algorithms in shipping: improving engine fault detection and diagnosis via ensemble methods

Detection and diagnosis of marine engines faults are extremely important functions for the optimized voyage of any sea-going vessel, as well as the safe conduct of navigation. Early detection of these faults is a prerequisite for reliability: incidents of engine breakdowns can be avoided, since the timely resolving of these faults can ensure the non-interrupted tempo of the sail. Avoiding malfunctions could also improve the ship’s overall environmental “footprint” and even ensure reduced fuel consumption. Initial results of the analysis at hand were presented during the 3rd International Symposium on Naval Architecture and Maritime (INT-NAM 2018), in Istanbul-Turkey. Further exploring the use of machine learning algorithms in shipping and by elaborating more on that effort, an evaluation of intelligent diagnostic methods applicable for a two-stroke slow-speed marine diesel engine is taking place, with the aim to facilitate effective detection and classification of occurring faults. This research was carried out via the cost-free Weka data mining tool, which was used to analyze the data of the engine’s operating parameters that were found outside of the prescribed boundaries. The proposed method is based on the construction of an ensemble classification model “AdaBoost”, which further improves the performance of a basic Simple Cart classifier. During the related experimental activities, the overall recorded performance was 96.5%, clearly establishing this method as a very appropriate choice.

Piston Pin Fault Detection Using A-AWH Algorithm

Engine vibration signal contains significant noise. It always is unstable in the time domain. It's difficult to detect the piston pin with improper eccentricity using vibration signal features. For improving the effectiveness of fault detection, a new algorithm using Angle domain synchronous average. Wavelet packet analysis and Hilbert transform (A-AWH) is proposed, which mainly contains: the method of equal angle sampling is adopted to acquire the rotational vibration signal from an engine; To acquire de-noised signal, the algorithm of angle domain synchronous average is then used; and the de-noise signal are processed by wavelet packet analysis; finally, the angle domain fault features are extracted by Hilbert transform. The effectiveness of the A-AWH algorithm is verified by applying it to the signals recorded from the engine with an eccentric piston pin. With this algorithm, some useful features can be extracted from the vibration signal, which demonstrates that the A-AWH algorithm can provide a new approach of engine faults detection.

VMD-KFCM Algorithm for the Fault Diagnosis of Diesel Engine Vibration Signals

Accurate and timely fault diagnosis for the diesel engine is crucial to guarantee it works safely and reliably, and reduces the maintenance costs. A novel diagnosis method based on variational mode decomposition (VMD) and kernel-based fuzzy c-means clustering (KFCM) is proposed in this paper. Firstly, the VMD algorithm is optimized to select the most suitable K value adaptively. Then KFCM is employed to classify the feature parameters of intrinsic mode functions (IMFs). Through the comparison of many different parameters, the singular value is selected finally because of the good classification effect. In this paper, the diesel engine fault simulation experiment was carried out to simulate various faults including valve clearance fault, fuel supply fault and common rail pressure fault. Each kind of machine fault varies in different degrees. To prove the effectiveness of VMD-KFCM, the proposed method is compared with empirical mode decomposition (EMD)-KFCM, ensemble empirical mode decomposition (EEMD)-KFCM, VMD-back propagation neural network (BPNN), and VMD-deep belief network (DBN). Results show that VMD-KFCM has advantages in accuracy, simplicity, and efficiency. Therefore, the method proposed in this paper can be used for diesel engine fault diagnosis, and has good application prospects.

An Improved Grasshopper Optimization Algorithm Based Echo State Network for Predicting Faults in Airplane Engines

In today's age of industrialization, sensor devices installed on equipment generate a vast amount of data. One of the engineers' main jobs is utilizing these data to provide better solutions to industrial problems. This availability of extensive data partly led to the creation of predictive maintenance (PdM). In PdM, existing and previous conditions of devices are used to predict their future behavior for optimal maintenance. Most of these PdM approaches are typical time-series predictions. Machine learning tools like Recurrent Neural Networks (RNNs) are excellent tools for time-series predictions. However, most RNNs suffer from training issues due to the unstable gradient problem. Thus, networks such as the Echo State Network (ESN), were designed to solve them. The ESN solves the gradient problem by training only the output weights using simple linear regression. Despite this ease, the selection of ESN parameters and topology is a considerable design challenge. This problem is often formulated as a typical optimization problem. Metaheuristic algorithms are known to be excellent tools for solving optimization problems. Hence, in this work, we design an improved Grasshopper Optimization Algorithm (GOA) based ESN. The proposed technique uses a new solution representation with a simplified attraction and repulsion mechanisms to enhance performance. Our target application is to predict the Remaining Useful Life (RUL) of turbofan engines. The method outperforms the Cuckoo Search (CS), Differential Evolution (DE), Particle Swarm Optimization (PSO), Binary PSO (BPSO), the original GOA, the classical ESN, deep ESN, and LSTM. We have provided all implemented codes and data at the GitHub repository. https://github.com/bala-221/Airplane-fault-prediction.

A Practical Approach to Detect Faults of Marine Diesel Engine

The existing marine diesel engine fault diagnosis methods mainly have the problems of model complexity, large amount of calculation, and unable to carry out real-time fault diagnosis of diesel engine. In this paper, a simple and practical approach to detect faults of marine diesel engine is studied. According to a set of sensing data, the fitting equation of each parameter changing with the running state of diesel engine was fitted statistically. Then, the threshold range of each parameter changing with the running state of diesel engine was fitted. During fault diagnosis, the real-time parameters of the sensor in the current running state were calculated according to the real-time running data. If the parameters exceed the threshold range, it is abnormal operation. Because the sensor signal corresponds to the operation status of each specific component, the abnormal evaluation directly indicates the specific fault. Experimental results show that the method has a good practical effect.

Diesel Engine Fault Diagnosis with Vibration Signal

When the vibration of diesel engine structure is measured, the signal is composed of a very complex superposition of the contributions of different vibratory sources modified by their respective transmission paths. These sources originate from several internal phenomenon in the engine such as combustion pressure variation, unbalanced reciprocating and rotating parts. In a diesel engine, movement parts work in a specific order. Once the starting point is determined, occurrence of work order in different cycle phases can be determined. This could successfully use to identifying of impulses in complex vibration signal of a diesel engine. From the variation of features of those impulses, it is possible to determine the working condition of the engine. This can use to fault diagnosis of diesel engine, specially faults related to combustion process.

Fault diagnosis in a current sensor and its application to fault-tolerant control for an air supply subsystem of a 50 kW-Grade fuel cell engine.

The safety, reliability and stability of air supply subsystems are still problems for the commercial applications of fuel cells; therefore, engine fault diagnosis and fault-tolerant control are essential to protect the fuel cell stack. In this study, a fault diagnosis and fault-tolerant control method based on artificial neural networks (ANNs) has been proposed. The offline ANN modification model was trained with a Levenberg–Marquardt (LM) algorithm based on other sensors' signals relevant to the current sensor of a 50 kW-grade fuel cell engine test bench. The output current was predicted via the ANN identification model according to other relevant sensors and compared with the sampled current sensor signal. The faults in the current sensor were detected immediately once the difference exceeded the given threshold value, and the invalid signals of the current sensor were substituted with the predictive output value of the ANN identification model. Finally, the reconstructed current sensor signals were sent back to a fuel cell controller unit (FCU) to adjust the air flow and rotate speeds of the air compressor. Experimental results show that the typical faults in the current sensor can be diagnosed and distinguished within 0.5 s when the threshold value is 15 A. The invalid signal of current sensor can be reconstructed within 0.1 s. Which ensures that the air compressor operate normally and avoids oxygen starvation. The proposed method can protect the fuel cell stack and enhance the fault-tolerant performance of air supply subsystem used in the fuel cell engine, and it is promising to be utilized in the fault diagnosis and fault-tolerant control of various fuel cell engines and multiple sensor systems.

Research on Construction of Crude Set Model of Critical Fault Information for Bus Based on CAN-BUS Data

Under the high load, high frequency and high strength operating environment, the frequent occurrence of vehicle fault gradually attracts the attention of the society. The real-time monitoring and data recording function of vehicle-mounted equipment provides data support for vehicle status assessment and fault warning. In this paper, the real-time data collected by CAN-BUS system of Beijing Bus Group are preprocessed and discretized. On the basis of the traditional rough set theory, a new coding method is set up, and the dependency between conditional attributes and decision attributes is set as an adaptive function, which is reduced by genetic algorithm and cellular genetic algorithm respectively. The calculation results show that the key fault information of public transport vehicles is instrumental speed, oil pressure, percentage of torque, timing engine speed, and coolant temperature. By comparing the results of reduction, it is found that the cellular genetic algorithm has higher applicability than the genetic algorithm in terms of algorithm efficiency, stability, and convergence quality. Although the genetic algorithm attribute reduction is slightly better than the cellular genetic algorithm attribute reduction in the rule matching, the cellular genetic algorithm has a better ability to excavate information within the acceptable compatibility range. Finally, the selected key factors will be deployed on the Beijing Bus Group's big data platform and displayed in real time. The conclusion of this paper enriches the theory of bus engine fault warning and establishes an engine failure warning system, which can effectively reduce the failure rate of bus vehicles and reduce the maintenance cost expenditure. It has certain guiding significance for the bus operation work of Beijing Bus Group.

A Survey of Internal Combustion Engine Condition Monitoring and Fault Detection Techniques

The internal combustion engine is the heart of cars, trucks, and many machines. It is the main source of movement and operation, and it consists of different mechanical sectors. Due to usage and aging, different faults can appear which affect engine operation and managing. Any small engine fault can turn into a major malfunction if it is not monitored and maintained at the proper time. Therefore, monitoring the performance of motors can save time and costs, improve their performance, and help them operate safely. Fault diagnosis, fault detection, and condition monitoring terms are used to describe similar concepts detection of any abnormality or deviation from the engines or machines normal condition. This paper describes a summary of the existing condition monitoring and fault detection techniques of the internal combustion engine, which are used for information collection to ensure operational safety, performance, reasonable maintenance, pollution prevention, and cost reduction.

Diesel Engine Fault Diagnosis Based on Stack Autoencoder Optimized by Harmony Search

Diesel Engine Fault Diagnosis Based on Stack Autoencoder Optimized by Harmony Search

СИНТЕЗ ОПТИМАЛЬНОГО НАБЛЮДАТЕЛЯ ПРИ ОТСУТСТВИИ АПРИОРНОЙ ИНФОРМАЦИИ О ХАРАКТЕРИСТИКАХ ШУМА ВОЗМУЩЕНИЯ СИСТЕМЫ АВТОМАТИЧЕСКОГО УПРАВЛЕНИЯ И КОНТРОЛЯ ТУРБОРЕАКТИВНОГО ДВУХКОНТУРНОГО ДВИГАТЕЛЯ

The possibility of obtaining measuring in-formation about the parameters of the automatic control and monitoring system of a turbofan engine during its operation in flight conditions and almost no restrictions on computational costs enable using algo-rithmic methods to improve the engine fault tolerance. In the previous article, the optimal observer, the Kalman filter, was used as a reserve meter. Its functioning essentially depends on the probabilistic characteristics of the system noise, which is known approximately and changes in a complex man-ner over time. Inaccuracies in these characteristics can lead to filter divergence and loss of its stability. To solve this problem, it is proposed to use the Yazvinsky adaptive filter, which allows calculating the covariance matrix of the disturbance noise after the arrival of new measurements from the values of the updated process of the Kaman filter. In this case computational costs increase insignificantly. The use of the Yazvsky adaptive filter eliminates the need for preliminary correlation analysis of system noise and pro-tects the Kalman filter from loss of stability. The results of modeling the Yazvinsky filter, consistent with the mathematical model of the turbofan engine, based on the flight test data of the PS-90A type engine as part of the TU-214 aircraft, both in steady-state and transient modes of engine operation, are presented. The parameters are indicated as percentage of the maximum values. A comparative analysis of the actual errors in the estimation of the output vector of the turbofan engine ACS when Kal-man and Yazvinsky filters are operating is carried out. The results of the comparative analysis are presented in the form of tables and graphs. It is shown that the proposed algorithm ensures fulfillment of the requirements for the accuracy of estimating the output vector of the automatic control and monitoring system of a gas turbine engine and can be recommended for use in the ACS of the turbofan engine.

A Variational Stacked Autoencoder with Harmony Search Optimizer for Valve Train Fault Diagnosis of Diesel Engine.

Diesel engine fault diagnosis is vital due to enhanced reliability and economic efficiency requirements. The extracted features in traditional fault diagnosis are constructed manually, which is very cumbersome because of the requirement for lots of expertise. To handle this issue, this paper proposed a variational stacked autoencoder (VSAE) to adaptively extract features from angular domain signals. As an unsupervised algorithm, VSAE can extract high-level features with the help of multiple encoding layers. Layer-wise pre-training and fine-tuning are introduced to get a better network initialization value. Moreover, the dropout technique and the batch normalization technique are carried out to prevent over-fitting and implement fast convergence. Finally, the harmony search optimizer (HSO) algorithm is introduced to get an appropriate hyper-parameter setting in the VSAE model, as well as make adaptive adjustment of the network structure. In order to verify the proposed method, the valve train fault data is collected on the diesel engine test rig under twelve operating conditions. The results indicate that the proposed scheme can effectively diagnose different degrees of intake valve fault, exhaust valve fault, and coupling fault under various operating conditions. Furthermore, the classification accuracy improved from 94.10% to 98.85%VSAE compared with stacked autoencoder (SAE) and some other traditional fault diagnosis algorithms.

Feature extraction of non-linearity and low noise-signal ratio signals and its application to engine fault diagnosis

Since the vibration signals of engine cylinder head come from different interference sources, it is difficult to detect weak but useful signals in the background of noise. Aiming at nonlinear and low noise characteristics of engine vibration signals, a method based on integrated empirical mode decomposition (EMD) and fractal dimension is proposed. Firstly, the integrated EMD method is used to decompose the nonlinear low noise signal into a set of intrinsic mode functions from high to low. Then the morphological fractal dimension is applied to the intrinsic mode function (IMFs). The fractal dimension of the characteristic IMF is calculated. The vibration signals of a diesel engine exhaust valve under normal and leakage conditions are analysed. The results show that this method can extract fault features of diesel engine exhaust valve.

Design of liquid rocket engine fault diagnosis device and its HIL verification

Design of liquid rocket engine fault diagnosis device and its HIL verification

Diagnosis of Liner Scuffing Fault of a Diesel Engine via Vibration and Acoustic Emission Analysis

Cylinder liner, piston rings, and piston are the key components which contribute to the overall performance and efficiency of the IC engines. Excessive temperature and pressure inside the combustion chamber, abrasive wear on the surfaces of liner and piston are major factors which degrade the performance and efficiency of the IC engines. The abnormal function of IC engine components causes an increase in sound and vibration levels of the engine structure and degrades the overall performance. The purpose of this work is to use signal processing techniques to extract fault-related information from sound and vibration signals of the IC engine. This work considers Fast Fourier transform and statistical feature extraction methods for monitoring the liner scuffing fault developed in the diesel engine. The performance, emissions, and cylinder pressure were also monitored to analyze the effect of liner scuffing fault. The results demonstrated that the aforementioned vibration signal analysis methods can be employed for the detection of liner scuffing fault in a diesel engine. The vibration and acoustic emission levels of the diesel engine were increased due to liner scuffing fault at all the loading conditions. The statistical feature parameters were increased at all the loading conditions due to the spurious effect of high-frequency amplitudes of vibration and acoustic signals. Furthermore, the performance parameters of the diesel engine were affected due to frictional losses caused due to liner scuffing fault.

Fault Diagnosis Method for Engine Control System Based on Probabilistic Neural Network and Support Vector Machine

Due to the poor working conditions of an engine, its control system is prone to failure. If these faults cannot be treated in time, it will cause great loss of life and property. In order to improve the safety and reliability of an aero-engine, fault diagnosis, and optimization method of engine control system based on probabilistic neural network (PNN) and support vector machine (SVM) is proposed. Firstly, using the German 3 W piston engine as a control object, the fault diagnosis scheme is designed and introduced briefly. Then, the fault injection is performed to produce faults, and the data sample for engine fault diagnosis is established. Finally, the important parameters of PNN and SVM are optimized by particle swarm optimization (PSO), and the results are analyzed and compared. It shows that the engine fault diagnosis method based on PNN and SVM can effectively diagnose the common faults. Under the optimization of PSO, the accuracy of PNN and SVM results are significantly improved, the classification accuracy of PNN is up to 96.4%, and the accuracy of SVM is up to 98.8%, which improves the application of them in fault diagnosis technology of aero-piston engine control system.

An H-shaped two-dimensional piezoelectric vibration energy harvester

An H-shaped piezoelectric vibration energy harvester (VEH) with two dimensional receiving direction is designed to provide power for engine fault monitoring in this work. The VEH consist of one main-beam which receives the vibrational excitation of horizontal direction, and two sub-beams which receive the vibrational excitation of vertical direction. The main-beam and the sub-beam of this H-shaped VEH are almost independent. So this H-shaped VEH could be modelled as a lumped-mass model. The models of the output voltage and the output power are given. The H-shaped VEH is fabricated using computer numerical control technology. The measured results show that the main-beam’s output voltage is 1011 mV with the resonant frequency of 110 Hz, and the sub-beam’s output voltage is 1021 mV with the resonant frequency of 118 Hz. The measured maximum output power of main-beam is 24.5 μW when the sliding rheostat is at 12.9 kΩ. And the measured maximum output power of sub-beam is 12.3 μW when the sliding rheostat is at 29.0 kΩ. The power density of the main-beam is about 0.286 μW mm−3, and the power density of the sub-beam is about 0.149 μW mm−3. Therefore, this H-shaped VEH can provide an effective solution of energy harvesting for engine fault monitoring system. In the future, the size of the structure will be reduced by MEMS technology and this H-shaped VEH can be integrated with other electronic devices.

Sensor fault diagnosis of gas turbine engines using an integrated scheme based on improved least squares support vector regression

As the flight envelope is widening continuously and operational capability is improving sequentially, gas turbine engines are faced with new challenges of increased operation and maintenance requirements for efficiency, reliability, and safety. The measures for security and safety and the need for reducing the life cycle cost make it necessary to develop more accurate and efficient monitoring and diagnostic schemes for the health management of gas turbine components. Sensors along the gas path are one of the components in gas turbines that play a crucial role in turbofan engines owing to their safety criticality. Failures in sensor measurements often result in serious problems affecting flight safety and performance. Therefore, this study aims to develop an online diagnosis system for gas path sensor faults in a turbofan engine. The fault diagnosis system is designed and implemented using a genetic algorithm optimized recursive reduced least squares support vector regression algorithm. This method uses a reduction technique and recursion strategy to obtain a better generalization performance and sparseness, and exploits an improved genetic algorithm to choose the optimal model parameters for improving the training precision. The effectiveness of the sensor fault diagnosis system is then validated through typical fault modes of single and dual sensors.

USAGE OF HIGH-QUALITY ENGINE OILS WITH EXTENDED REPLACEMENT INTERVALS: FEATURES OF THE EQUIPMENT OPERATION

Introduction. The effective operation of cars largely depends on the state of the engines, their downtime in maintenance and repair. Since the maintenance of modern engines is often reduced to the replacement of engine oil, the increase in the duration of its work significantly reduces maintenance costs and downtime in maintenance. Long maintenance-free operation of the internal combustion engines of automotive vehicles is directly related to the state of the engine oil used in this power unit. The aim of the paper is to show the features of the equipment operation with significant intervals of the engine oils’ replacement in order to increase the efficiency of its usage. The paper presents data on the features of the equipment operation when using high-quality motor oils with extended replacement intervals.Materials and methods. The authors conducted performance tests on the basis of MercedesBenzAxor, MercedesBenzActros cars. The manufacturer provided an estimate of the performance of engine oils. The main performance characteristics of motor oils were assessed using standard methods: kinematic viscosity was measured using a Stabinger viscosimeter, the base number was determined by an automatic AT-500 titrator, the content of wear products was obtained using an ASP-coupled emission spectrophotometer.Results. As a result, the authors presented data on the dependence of the changes in the main indicators of engine oil performance while the operating time and also substantiated the requirements for the volumes of fresh engine oil to compensate losses.Discussion and conclusions. The intermediate control allows detecting faults in the internal car engines, as well as providing the most accurate prediction of the resource of the lubricant under consideration. Therefore, the increasing of the engine oil change interval allows getting a significant economic effect.