Fault Diagnosis Technology Research Articles

Carbon deposition fault diagnosis of small piston engine based on optimized VMD

Aiming at the small piston engine carbon deposition fault in the process of running, based on the cylinder pressure and cylinder head vibration signal of the engine, a fault diagnosis method combining variational mode decomposition and support vector machine is used to diagnose the engine carbon deposition fault. Firstly, particle swarm optimization algorithm is used to optimize the parameters of the variational mode decomposition. Then, the intrinsic mode function is obtained by processing the pressure signal and cylinder head vibration signal of the engine. Then, the singular spectrum entropy is calculated by singular value decomposition of the intrinsic mode function. Finally, the singular spectrum entropy is input into the support vector machine classifier as the feature data set for training and testing. The results show that this method can identify the carbon deposition fault of the starting motor well, and the accuracy of fault identification and classification of cylinder pressure and cylinder head vibration signal is 98.33 % and 99.17 % respectively, which verifies the effectiveness of this method.

A novel adaptive fault diagnosis algorithm for multi-machine equipment: application in bearing and diesel engine

This paper proposes an adaptive fault diagnosis algorithm based on vibration signals for fault diagnosis of bearings and diesel engines. First, the improved nonlinear gray wolf optimization algorithm (NGWO) is adopted to optimize the key parameter for variational mode decomposition (VMD) with the power spectral entropy as the fitness value. Meanwhile, adaptive noise reduction of the signal is realized. Then, sensitive fault features of bearings and diesel engines are selected through a feature sensitivity analysis on the vibration signals. Also, a single-layer sparse autoencoder is used to align the feature dimensions of each type of data to construct feature matrix samples. Subsequently, a deep neural network (DNN) consisting of a two-layer stacked sparse autoencoder (SSAE) and a Softmax classification layer is constructed to realize failure mode recognition. During the training process of DNN, a surrogate model formed by NGWO and a back propagation neural network is employed to optimize the hyperparameters of SSAE. Finally, to verify the effectiveness of the proposed fault diagnosis algorithm, fault diagnosis experiments are conducted on the fault data set of bearings and diesel engines. The diagnosis results show that the proposed method achieves high-precision fault diagnosis for bearings and diesel engines and performs stably for small samples.

Fault diagnosis technologies for power transformers during the on‐site inductive oscillating switching impulse voltage withstand test

Although oscillating switching impulse (OSI) voltage is recommended for the transformer field test, the lack of corresponding fault diagnosis technologies limits its application in the field. In this study, the inductive OSI test technology and diagnostic methods are investigated. The front time and the oscillation frequency of the OSI are altered by changing the additional inductance, whereas the tail time is affected by both the front and tail resistance. The OSI voltage withstand test is carried out on a 110 kV three-phase double-winding transformer on site. Furthermore, transfer function (TF) analysis is used for the diagnosis of transformer insulation with high sensitivity during the OSI test. The fault winding is distinguished by comparing the change in the voltage TF and current TF at different voltage levels. The partial discharge (PD) detection method has the highest sensitivity, which realizes the early diagnosis of insulation faults. The insulation status of the windings is ascertained based on the number and amplitude of PDs. The test results prove that the inductive OSI voltage withstand test is easy to perform on site and can successfully diagnose the insulation faults of the transformer in more detail compared with other routine insulation tests.

Identification of Typical Fault States of Marine Diesel Engines Based on Optimized BP Neural Network

Ship diesel engine is the core equipment of the ship, and its working condition is directly related to the safety and reliability of ship navigation. Once the ship diesel engine fails, it may cause different degrees of sea damage accidents, bringing economic losses and even endangering the life safety of crew members. The fault diagnosis can monitor the state of diesel engine during the operation of the ship and capture the fault signal to ensure that the fault can be found and eliminated in time. Therefore, the fault diagnosis research of ship diesel engine is an important research direction at present. This paper verifies that BP neural network has disadvantages such as inability to escape from local optimal solution and long convergence time, and the BP neural network optimized by genetic algorithm is based on intelligent fault state recognition. The optimized BP neural network has significantly improved in the fitting performance and classification performance. The research results have certain reference value and provide a basis for the research of intelligent fault diagnosis of marine diesel engines.

Fault diagnosis and location of hydraulic system of domestic civil aircraft based on logic data

To study the typical fault diagnosis and fault location technology of the hydraulic system of the domestic civil aircraft, the logic data of the typical fault is constructed according to the formation conditions of the fault. The operation data of the typical fault is collected, and the Bayesian network is used to realize the fault diagnosis and fault components position. First, according to the fault formation conditions in the unit operation manual of a certain type of domestic civil aircraft, referring to the construction method of the logic data, taking the typical fault of the hydraulic system as an example, the fault logic data of the domestic civil aircraft is established to intuitively reflect the logical relationship of the fault formation; secondly, based on the constructed logic data, considering the formation conditions of the fault, a Bayesian network corresponding to the logic data is established, and the logical relationship formed by the fault is represented by the value of the conditional probability distribution; obtain quick access recorder (QAR) data and its parameter information according to the input information of the logic data; finally, according to the established Bayesian network and the obtained QAR data, apply forward reasoning to realize the diagnosis of typical faults of the hydraulic system. Under the condition of partial information, reverse reasoning is applied to locate the faulty components of hydraulic system. The research shows that the proposed method can accurately diagnose faults, and can accurately locate faulty components in complete information, and give the probability of occurrence of potentially faulty components under partial information, which can effectively assist in the location of faulty components. The research work has certain reference significance for improving the fault diagnosis function of the airborne health management system and the ground health management system of domestic civil aircraft.

Research on condition monitoring and fault diagnosis technology of dynamometer in aero-engine test bed

In the process of engine development, production, improvement and renewal, engine bench test is an indispensable and important link, dynamometer is the main component of the test bed, in the test process the dynamometer will bear a large load, so it will produce violent vibration, easy to produce mechanical failure. The implementation of engine test bed condition monitoring and fault diagnosis can evaluate the health status of mechanical transmission components of the bend and the dynamic performance of the engine under test. This paper implements monitoring and diagnosis of key mechanical parts, through comprehensive analysis of time domain, amplitude domain, frequency domain characteristic information under no-load, low load, high load and other operating conditions to determine the health / unhealthy condition, fault type and fault severity, validity and accuracy of diagnostic conclusions such as rotor imbalance, bearing outer ring failure were verified by the equipment open and maintenance. This case provides practical guidance for the status monitoring and accurate fault location of aero-engine test bed.

A Novel Open-Circuit Fault Detection and Location for Open-End Winding PMSM Based on Differential-Mode Components

Detecting and locating the open-circuit (OC) fault of an insulated-gate bipolar transistor (IGBT) rapidly and accurately is very important to improve the security and reliability of the drive system. However, due to the symmetry of the dual-inverter topology, it is difficult to achieve fault detection for open-end winding permanent magnet synchronous motor (PMSM). Thus, this article proposes a fault diagnosis technology for open-end winding PMSM fed by a dual inverter with a common dc bus. In this method, the faulty phase and the faulty case are identified by the average value of the output of the closed-loop controller, which is used to eliminate the differential-mode current in the system. Then, the faulty phase is isolated by removing the gate signals. Finally, the faulty IGBT is located by restructuring the faulty phase and analyzing the current of the faulty phase. In this method, the OC fault can be detected and the faulty IGBT can be located accurately. Experimental results are shown to validate the proposed detection method.

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

Due to the relative insufficiencies of conventional time-domain waveform and spectrum analysis in fault diagnosis research, a diesel engine fault diagnosis method based on the Stacked Sparse Autoencoder and the Support Vector Machine is proposed in this study. The method consists of two main steps. The first step is to utilize the Stacked Sparse Autoencoder (SSAE) to reduce the feature dimension of the multi-sensor vibration information; when compared with other dimension reduction methods, this approach can better capture nonlinear features, so as to better cope with dimension reduction. The second step consists of diagnosing faults, implementing the grid search, and K-fold cross-validation to optimize the hyperparameters of the SVM method, which effectively improves the fault classification effect. By conducting a preset failure experiment for the diesel engine, the proposed method achieves an accuracy rate of more than 98%, better engineering application, and promising outcomes.

Gas path fault diagnosis of aircraft engine using HELM and transfer learning

Gas-path fault diagnosis of an aero-engine is a key challenge for flight safety. However, there are two problems: 1) Large collections of healthy condition samples and few fault samples; 2) The diagnosis accuracy cannot meet the practical demands. Therefore this paper proposes a new integrative diagnostic approach for gas-path fault of an aircraft engine to overcome the limitations. A novel model (HELM-TL) is presented to improve fault diagnosis performance, which ensembles the advantages of HELM and transfer learning by fusing target domain data and source domain data effectively. The attention mechanism is adopted to construct global dependency of gas-path monitoring data. Furthermore, this paper develops a novel algorithm for fault diagnosis which dynamically updates learning rate according to loss function. The proposed approach not only obtains more accurate fault distribution, but also avoids over-fitting problem, which greatly improves diagnosis performance and generalization. Finally, experimental data from China Eastern Airlines is adopted to validate. The experimental results show that proposed method has excellent robust according to sensitivity analysis. Moreover, it achieves a good tradeoff between diagnosis accuracy, transfer performance, and runtime cost. The proposed method also improves training accuracy by 5%–15%, reduces RMSE of fault diagnosis by 11%, and improves prediction accuracy by 12.1% compared with the average value of state-of-the-art methods.

Fault diagnosis of ship power equipment based on adaptive neural network

Abstract In recent decades, international shipping trade has been developing continuously. The ship is the main transportation carrier of international shipping, and the power equipment on the ship is in an absolutely critical position, and its working condition is also directly related to the safe running of the ship. Therefore, the research on the ship’s power plant and fault diagnosis system is particularly important. Due to the actual operation of the ship power plant, the characteristics of the components are inevitably changed. Therefore, the corresponding equipment fault diagnosis technology also has a certain importance for the health management system of power equipment. As for the problem that the current ship equipment fault identification method is not widely applicable and the accuracy is not high enough, this paper aims to make the ship fault diagnosis faster and more accurately. It effectively solves the problem of timeliness and accuracy of fault diagnosis. This paper takes ship power equipment as the research object, firstly, introduces and proposes a diagnosis method of adaptive neural network structure, and applies it to fault detection and estimation. Next, this paper uses the adaptive neural network model for ship fault diagnosis. The accuracy of the adaptive neural network designed in this paper is better than that of the conventional neural network, and when the number of training samples is small. It can still obtain an ideal network through training to ensure that the fault detection of power equipment health parameters has high accuracy. The simulation results show that, compared with the common methods, the network model can effectively reduce the fault diagnosis error. The correct rate of fault diagnosis is over 93%, which improves the speed, accuracy, and applicability of fault diagnosis.

Modeling of Satellite Constellation in Modelica and a PHM System Framework Driven by Model Data Hybrid

The new generation of low-earth-orbit (LEO) satellite constellation systems has the characteristics of low delay, strong signal and global coverage, and it is an important direction for the development of next-generation communication technology. A major disadvantage is that the constellation system is huge, often composed of hundreds or thousands of satellites, which puts forward high requirements for the design and health management of the constellation system, and the existing telemetry data monitoring system cannot meet the actual needs. CPS is a multidimensional complex system that integrates computation, communication and control (3C). Through the deep integration and cooperation of 3C, the real-time monitoring and dynamic control of large-scale engineering systems are realized, which is completely suitable for the operation and maintenance requirements of the satellite constellation system. This paper firstly establishes the entire satellite constellation system model, which is integrated from the satellite multidomain system, the constellation orbit environment system and the communication link system. Then, according to the technical concept of cyber-physical systems (CPS), an implementation framework of a prognostics and health (PHM) system driven by a model–data hybrid for satellite constellation systems is proposed. The framework is based on model simulation data and telemetry data and combines virtual and real data fusion, fault diagnosis, simulation prediction and other technologies to generate enhanced data to drive the effective operation of the PHM system. Finally, a verification case is designed to prove that the satellite constellation health management system implemented under this framework has a positive effect on the reliable operation and maintenance of the satellite constellation system.

Research on Fault Diagnosis Technology of Industrial Robot Operation Based on Deep Belief Network

Fault diagnosis technology is the science of identifying the operating state of a machine or unit, and it studies the response of the change in the operating state of the machine or unit in the diagnostic information. It can give an early warning to the failure state of the machine and stop the machine before a major failure occurs so as to protect the life safety of the on-site staff and avoid huge economic losses to the enterprise. For mechanical equipment, fault diagnosis consists of three main links: fault detection; fault identification; and fault classification. Aiming at the problems that need to be solved in the fault diagnosis of industrial robots, this paper adopts a data-driven intelligent diagnosis method to establish a fault diagnosis model of industrial robots based on Deep Belief Network (DBN) and DSmT theory. Firstly, based on wavelet transform and information energy entropy correlation theory, the vibration signal of industrial robot is extracted, and the energy entropy normalized eigenvector is established. Then, the energy entropy normalized feature vector is divided into training set and test set to complete the creation of DBN network model. Finally, using DSmT theory to carry out decision-making fusion, a fault diagnosis model for industrial robots is established, and experiments are carried out on the K-R-R540 robot to verify the applicability of the established fault diagnosis model. It is proved by experiments that the industrial robot fault diagnosis model based on the deep belief network can meet the requirements of the recognition accuracy of robot faults, and the model will perform poorly when the faults coexist with multiple faults.

Research on anti-interference and training set updating ability of fault diagnosis model of high voltage common rail system

In the fault diagnosis of high-pressure common rail diesel engine, the problem of low accuracy of fault diagnosis is caused by the inability to classify untrained state problems and training sets. To solve the above problems, an anti-interference classification model for fault diagnosis of high-voltage common rail system based on alpha shapes algorithm and K-means algorithm is proposed in this paper. This model can improve the anti-interference ability and training set updating ability of the fault diagnosis model. Using the anti-interference classification model composed of anti-jamming device and classifier, the samples for fault diagnosis are screened in advance, and the singular values of untrained state and trained state are classified. By constructing an anti-interference classification model composed of anti-interference device and classifier, the fault is diagnosed, and then the dependency of singular values is obtained through cluster analysis, which improve the anti-interference ability and training set updating ability of the fault diagnosis model. By comparing the diagnosis results of the fault diagnosis model with and without anti-interference classifier, we can found that the addition of anti-interference classifier makes the fault diagnosis model of high-voltage common rail system obtain the anti-interference ability to the untrained state and the ability to update the training set of the singular value of the trained state, and can slightly improve the accuracy of fault diagnosis.

Robust nonlinear adaptive pressure control of polymer electrolyte membrane fuel cells considering sensor failures based on perturbation compensation

The large deviations between the partial pressure of oxygen and hydrogen can lead to severe membrane damage, which reduces the life of the polymer electrolyte membrane fuel cell (PEMFC). The deviation of pressure can be restrained by effective control of partial pressure. Considering the actual operating environment of PEMFC, its control system is not only affected by load changes, but also affected by some unknown disturbances, such as system parameter variations, failures, etc. Considering the above factors, this paper has proposed a robust nonlinear adaptive pressure control (RNAPC) employing the perturbation estimation technique to suppress the deviations. The proposed controller does not need to identify or estimate the system parameters in real time like the conventional controller based on parameter estimation technology, nor does it need to rely on the fault diagnosis and isolation technology to detect and estimate the failures in real time. It only uses the variations of system state variables caused by failures to provide the required failure information for the controller. In the design of RNAPC, an observer is designed to estimate a perturbation term containing system uncertainties, nonlinearities, and disturbances. The estimation of perturbation is used for the compensation of actual perturbation. Then, an adaptive FLC of PEMFC system can be realized. Therefore, the RNAPC requires only a few state measurements and is independent of an accurate system model. Simulation results show that the RNAPC method has smaller deviations of partial pressure of oxygen and hydrogen and better dynamic performance than traditional PI control under load disturbance, and obtains higher robustness against uncertainties and sensor failures than traditional PI control and FLC. The maximum error of partial pressure can be limited within 0.5% under four different simulation scenarios under the RNAPC.

DC Motor Control Technology Based on Multisensor Information Fusion.

To solve these uncertain problems by studying the motor fault diagnosis technology, so as to ensure the normal operation of the motor equipment is the primary problem to be solved in the field of motor fault diagnosis. The traditional DC motor is one of the most widely used motors at present. It has excellent speed regulation performance and is easy to control. It is widely used in applications that require high motor startup and speed regulation characteristics. This research mainly discusses DC motor control technology. Evidence theory can combine various fault information at different levels to enhance mutual support between pieces of evidence, thereby improving the accuracy of motor fault detection. Based on the steps of signal processing, feature extraction, feature dimensionality reduction, and state recognition, the research on the state recognition method of belt conveyor drive motor based on multisource information fusion is carried out. By studying the multisource information fusion, this paper proposes a two-stage belt conveyor drive motor information fusion model based on the optimal D-S evidence theory. The correct identification rate of broken rotor bars during fault monitoring is 99.8%. This method divides the specific motor fault feature set into multiple fault subspaces and uses different diagnostic neural networks and different fault feature parameters for local diagnosis, respectively. The scheme designed in this study significantly improves the recognition accuracy of the motor in the same working condition and under variable working conditions. The drive motor state recognition and intelligent decision-making system designed by combining the results of multisource information fusion can effectively describe the fault type and has strong operability.

Rolling bearing fault diagnosis based on quantum LS-SVM

Rolling bearing is an indispensable part of the contemporary industrial system, and its working conditions affect the state of the entire industrial system. Therefore, there is great engineering value to researching and improving the fault diagnosis technology of rolling bearings. However, with the involvement of the whole mechanical equipment, we need to have a large quantity of data to support the accuracy of fault diagnosis, while the efficiency of classical machine learning algorithms is poor in processing big data, and huge amount of computing resources is required. To solve this problem, this paper combines the HHL algorithm in quantum computing with the LS-SVM algorithm in machine learning and proposes a fault diagnosis model based on a quantum least square support vector machine (QSVM). Based on experiments simulated on analog quantum computers, we demonstrate that our fault diagnosis based on QSVM is feasible, and it can play a far superior advantage over the classical algorithm in the context of big data.

Online Monitoring of Automotive Engine Lubricating Oil Based on Internet of Things Technology

In order to realize the online monitoring of automotive engine lubricating oil, a method based on Internet of Things technology is proposed. This method uses the self-organizing neural network of the Internet of Things to fuse the original multidimensional feature data to obtain the fusion value. The Parzen window method is used to formulate the limit value of fusion value, and the samples are divided into three states: normal, warning, and abnormal. Weka software is used to extract rules from oil data. This method can identify different wear state information from oil spectral data, extract knowledge rules, and use them to build the knowledge base of automobile engine wear diagnosis system, so as to realize the automation and intelligence of automobile engine fault diagnosis based on lubricating oil spectral wear data. The measurement method of the lubricating oil sensor is mainly to comprehensively reflect the relationship between oil quality and electrical signal, so as to effectively provide users with reliable information. After many studies, it is concluded that the conductivity of lubricating oil has a good linear relationship with its acid value, metal particles, moisture content, and the change of additive content. Measuring the change of conductivity is an effective means to detect the change of lubricating oil quality. The experimental results show that using the extracted knowledge rules to verify the state of samples, the recognition rate is 97.47%. In order to more fully explain the difference between important element fusion and all feature fusion, all features are extracted. At the same time, the fault diagnosis and recognition rate of all features is not high, only 62.39%. It is proved that the Internet of Things technology can effectively realize online monitoring of the automotive engine lubricating oil.

Out-of-distribution detection-assisted trustworthy machinery fault diagnosis approach with uncertainty-aware deep ensembles

Recent intelligent fault diagnosis technologies can effectively identify the machinery health condition, while they are learnt based on a closed-world assumption, i.e., the training and testing data follow independently identically distribution (IID). However, in real-world diagnosis, the monitored samples are often from unknown distributions, such as unseen machine faults, leading to an out-of-distribution (OOD) problem. This is a challenging issue that may induce the model to produce unreliable and unsafe decision for unforeseen machine data. To tackle this problem, a novel OOD detection-assisted trustworthy machinery fault diagnosis approach is developed to enhance the reliability and safety of intelligent models. First, multiple deep neural networks are integrated to establish an ensemble diagnosis system, called deep ensembles. Then, the trustworthy analysis with uncertainty-aware deep ensembles is conducted to detect the OOD samples and issue the warnings for the potential untrustworthy diagnosis. A selection criterion of uncertainty threshold is given. Finally, the trustworthy decisions are achieved by comprehensively considering the deep ensembles’ prediction and uncertainty. The proposed trustworthy fault diagnosis approach is validated in two case studies, exhibiting significant advantages for diagnosing OOD samples.

Petrochemical Gearbox Fault Location and Diagnosis Method Based on Distributed Bayesian Model and Neural Network

<p>Increasing attention has been paid to the economic losses and personnel injuries caused by petrochemical gearbox faults. As a result, petrochemical enterprises started to pay huge attention on fault diagnosis technology to solve the fault diagnosis problem. Petrochemical gearboxes are characterized by many fault types, feature variables, and many-to-many relationships between the various fault parameters, which pose huge challenges in the fault diagnosis of petrochemical units. This paper proposes a petrochemical gearbox fault location and diagnosis method based on a distributed Bayesian model and neural network. The proposed approach is based on sample feature information and Bayesian network prior probability to construct a basic framework for petrochemical gearbox fault location. Neural network technology is used to to diagnose fault types. It is helpful to build a long-term fault diagnosis and monitoring system for rotating machinery of petrochemical units.</p> <p> </p>

Research on fault diagnosis of drive motor based on MATLAB / Simulink simulation

Drive motor, as the “heart” of electric vehicles, is the only power source of the vehicle. Its healthy state directly affects the driver’s driving experience and even threatens personal safety. In this paper, the fault diagnosis of drive motor is studied, including the introduction of fault diagnosis and drive motor, and the fault classification and simulation analysis of drive motor. Taking the permanent magnet synchronous motor as an example, the model of the drive motor is built based on MATLAB / Simulink simulation software, and the current and speed changes of the drive motor under normal and fault conditions are compared and analyzed. Finally, the future development trend of drive motor in electric vehicles and the development of fault diagnosis technology are prospected.