Fault Diagnosis Technology Research Articles

Fault diagnosis of a marine power-generation diesel engine based on the Gramian angular field and a convolutional neural network

Fault diagnosis of a marine power-generation diesel engine based on the Gramian angular field and a convolutional neural network

Research on Ferrographic Image Fault Diagnosis Based on Channel Overlapping Technique and Information Fusion Mechanism

Abstract Utilizing computer technology to realize the application of ferrographic intelligent fault diagnosis technology is a foundational investigation to oversee the operations of mechanical equipment. To continuously improve the accuracy of artificial intelligence recognition, the complexity and computation of the model will be increased. The proposal of the transformer model (the core technology of chatgpt) has fundamentally changed the intelligence level of artificial intelligence, but it has also greatly increased the demand for computer computing power. What's more, it is difficult to equip industrial quality inspection sites with high computing power computers. The channel overlapping technique developed in this paper is a technology to segment the three channels of image information and reserve overlapping areas for an information communication mechanism. With this mechanism, the model location channel overlapping convolutional neural network can obtain high recognition accuracy by using only one-half of the original training computing power. When channel overlapping combines with no position information, information fusion is formed. The model channel overlapping technique fusion convolutional neural network established by the information fusion mechanism will get a higher prediction accuracy through joint training with the original image. However, the computation consumption is nearly one-third of the pure traditional convolutional neural network algorithm.

Unknown fault detection of rolling bearings guided by global–local feature coupling

Fault diagnosis technology can effectively prevent the occurrence of faults and reduce safety hazards, which is of great significance in nuclear power, aerospace, manufacturing, and other fields. Given the stringent demands of safe and reliable equipment operation in practical production environments, acquiring a comprehensive set of fault samples becomes challenging. At present, many deep learning-based methods have been researched on this problem. However, these methods do not account for the identification of novel faults that may emerge. In this paper, we propose a novel global and local feature joint learning method for unknown fault detection, which addresses this problem by applying the knowledge learned by the supervised feature extraction process to the unsupervised clustering process. In particular, we propose a dual-branch framework for detecting unknown faults, which is based on multi-scale coupled feature extraction. This framework establishes correlations between features at different scales and employs the coupling of global and local features to facilitate the detection of unknown faults. Additionally, we propose a causal modeling method for global and local features, aiming to uncover the true causal relationship among global and local features and fault categories. Moreover, we propose a consistent prediction method to ensure the coherence of prediction results between the global and local branches. We evaluate the performance of our model using the CWRU, PU, and RB datasets, and the results demonstrate its superiority over state-of-the-art methods in terms of clustering accuracy and normalized mutual information.

LPF/OGS: A Low-Pass Filtering and Overlapping Group Shrinkage Denoising Method for Diesel Engine Fault Diagnosis

LPF/OGS: A Low-Pass Filtering and Overlapping Group Shrinkage Denoising Method for Diesel Engine Fault Diagnosis

Improved deep residual shrinkage network for a multi-cylinder heavy-duty engine fault detection with single channel surface vibration

The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted from the overall system vibration. Faulty characteristics emanating from one single cylinder are also mixed with those from other cylinders. Besides, the change of working condition brings strong nonlinearities in surface vibration. To solve these problems, an improved deep residual shrinkage network (IDRSN) is developed for detecting diverse engine faults at various degrees using single channel surface vibration signal. Within IDRSN, a wide convolution kernel is utilized in first convolution layer to capture the long-term fault-related impacts and eliminate the short-time random impact. The residual network module is adopted to enhance the focus the relevant components of vibration signals. Mini-batch training strategy is used to improve the model stability. Meanwhile, Gradient-weighted class activation map is adopted to assess the consistency between the learned knowledge and the fault-related information. The IDRSN is implemented to diagnosing a diesel engine under various faults, faulty degrees and operating speeds. Comparisons with existing models are analyzed in terms of hyper-parameters, training samples, noise resistance, and visualization. Results demonstrate the proposed IDRSN's superior performance on fault diagnosis accuracy, stability, anti-noise performance, and anti-interference performance. An average accuracy rate of 98.38 % was achieved by the proposed IDRSN, in comparison to 96.64 % and 93.56 % achieved by the DRSN and the wide-kernel deep convolutional neural network respectively. These results highlight the proposed IDRSN's superiority in diagnosing multiple faults under various working conditions, offering a low-cost, highly effective, and applicable approach for complex fault diagnosis tasks.

An online wear metal particles monitoring warning sensor based on electromagnetic induction in lubricating oil

The online monitoring of metal particles in lubricating oil plays an important role in equipment fault diagnosis technology. This paper designs an online wear monitoring warning sensor based on the electromagnetic induction of metal particles in lubricating oil. First, different from the traditional three-coil sensing and detection method, the sensor consists of two excitation coils and one detection coil. In addition, the parallel capacitance and detection capacitance parameters are obtained by COMSOL’s scanning frequency, and the best detection capacitance is 7.53 nF. Second, according to the obtained optimal detection parallel capacitance value, the amplitude data of the particle signal, as well as the ferromagnetic particles above 60 µm and the non-ferromagnetic particles above 80 µm, are obtained. Third, according to the principle of three-coil induction, a mapping relationship model was established between the size range of metal wear particles in lubricating oil. Finally, we set up an oil wear particle platform to verify the sensor performance. The ferromagnetic and non-ferromagnetic particles are divided into multiple size ranges, and the peak-to-peak values of the output signal of different-sized wear particles are measured. We developed a prototype sensor and verified the signal consistency and repeatability of the sensor to wear metal particles. In addition, we used the sensor to test a large number of metal particles of different sizes (14 ferromagnetic particle standard samples with particle sizes ranging from 20.64 to 457.59 µm and ten non-ferromagnetic particle standard samples with particle sizes ranging from 40.52 to 348.07 µm). The experimental results show that the sensor can directly achieve monitoring sensitivity for ferromagnetic particles greater than 64.57 µm and non-ferromagnetic (copper) particles greater than 82.83 µm under the 4.2 mm aperture flow channel. The sensor can effectively realize the sensitivity on monitoring of small ferromagnetic particles and non-ferromagnetic particles, and it is particularly sensitive to small non-ferromagnetic particles.

Research on Experimental Bench Testing of Wear Metal Particles in Lubricating Oil Based on Self-Excitation and Self-Induction of Coil

The on-line monitoring of wear metal particles in lubricating oil plays an important role in equipment fault diagnosis technology. According to the principle of electromagnetic induction and the Biot-Savart law, model structure design, coil production, etc., different from traditional multi-coil excitation detection methods and compared to traditional methods that are only sensitive to large particles, this paper designed a self-excitation and self-induction metal particle monitoring sensor in lubricating oil based on LC resonance. At the same time, a sensor experimental bench is built by combining the production of ferromagnetic and non-ferromagnetic metal particle standards. In addition, through experimental verification, the sensor can achieve monitoring sensitivity for ferromagnetic particles greater than 41.28 μm and non-ferromagnetic (copper) particles greater than 61.53 μm under the 4.2 mm aperture flow channel, realizing the sensitivity on monitoring of small wear ferromagnetic particles and wear metal non-ferromagnetic particles, the experiment showed that it is particularly sensitive to small non-ferromagnetic particles. Based on a wide pipeline radius, the accuracy and sensitivity of the designed single-coil sensing system have been demonstrated.

Research on bearing fault diagnosis technology based on machine learning

As industrial equipment complexity continues to rise, the importance of bearings within these systems has become more critical, given their pivotal role in equipment functionality. Bearing faults can result in severe production accidents and safety issues. Hence, there is an urgent need for advanced bearing fault diagnosis technology. This study concentrates on rolling bearings, analyzing their structural characteristics and key parameters to classify fault types—inner race faults, rolling element faults, and outer race faults. Utilizing a dataset of 80 sets of bearing factory data, time and frequency domain analyses are conducted, establishing seven feature parameters (five in the time domain and two in the frequency domain). This data is organized into a 7-dimensional matrix for subsequent analysis and model development. The K-Means algorithm is chosen for its effectiveness in automatically recognizing fault patterns in rolling bearings. Training on the 7-dimensional matrix identifies four clustering centers corresponding to normal conditions, inner race faults, rolling element faults, and outer race faults. The fault diagnosis system is implemented using Python, and algorithm optimization improves efficiency. The study concludes with insights drawn from the analysis and proposes optimization methods, which contributing to advancing bearing fault diagnosis technology, particularly addressing industrial equipment reliability and safety concerns.

Gas Path Fault Diagnosis of Turboshaft Engine Based On Novel Transfer Learning Methods

Abstract Data-driven fault diagnosis method is widely used in the field of engine health management, which uses engine sensor data as input and engine faulty components as output for component-level fault diagnosis of the engine. The application premise of the general data-driven fault diagnosis method is that all data come from the same working conditions, that is, they belong to the same distribution. However, this assumption is not valid in the actual engine fault diagnosis, because the engine state will change with the increase of running time. In the meantime, collecting engine data is usually expensive, time-consuming, and laborious. To solve these problems, extreme learning machine (ELM) based two transfer learning methods for fault diagnosis of turboshaft engines are proposed in this paper. One is joint solving ELM (JSELM), which regards the information of the target domain and source domain as similar and different parts respectively, and knowledge is extracted from them at the same time. The other is model transfer-based ELM (MTELM), which uses the idea of pretraining. First, a general ELM classifier is trained with the source domain data and then fine-tuned with the target domain data. Both methods have a good real-time performance as the traditional ELM. When there are a few data in the target domain, they achieve much better classification accuracy than traditional ELM. Finally, experiments are carried out with turboshaft engine simulation data. The results show that both methods are effective, especially MTELM, which has better classification accuracy.

Diesel engine fault diagnosis for multiple industrial scenarios based on transfer learning

Fault diagnosis based on data-driven intelligence has recently attracted extensive interest owing to the rapid development of big data and deep-learning algorithms. However, when the amount of faulty data is limited, deep learning training is prone to overfitting. When the application scenario is changed, the generalization ability of the trained network is affected. In this study, a fault diagnosis architecture based on deep transfer learning is proposed to work with limited data and transfer between multiple scenarios. A wide convolution kernel convolutional long short-term memory neural network (WCL) was used to improve the feature extraction ability of fault data from a diesel engine with a low signal-to-noise ratio. A multiple transfer learning scheme based on WCL was further adopted to transfer the well-trained diagnostic knowledge of large-scale labeled source domain data to the target domain with limited samples. In addition, for diesel engines for various purposes, the knowledge transferability between different scenarios was studied. The algorithm evaluates the transfer performance of four different domains when the sample is insufficient, including the cross-fault type, cross-equipment type, cross-fault degree, and cross-working conditions. The results show the proposed method is proven with high noise immunity improves the accuracy of small sample cross-domain diagnosis and provides an optimal transfer scheme suitable for diesel engine fault signals.

Research on a Small-Sample Fault Diagnosis Method for UAV Engines Based on an MSSST and ACS-BPNN Optimized Deep Convolutional Network

Regarding the difficulty of extracting fault information in the faulty status of UAV (unmanned aerial vehicle) engines and the high time cost and large data requirement of the existing deep learning fault diagnosis algorithms with many training parameters, in this paper, a small-sample transfer learning fault diagnosis algorithm is proposed. First, vibration signals under the engine fault status are converted into a two-dimensional time-frequency map by multiple simultaneous squeezing S-transform (MSSST), which reduces the randomness of manually extracted features. Second, to address the problems of slow network model training and large data sample requirement, a transfer diagnosis strategy using the fine-tuned time-frequency map samples as the pre-training model of the ResNet-18 convolutional neural network is proposed. In addition, in order to improve the training effect of the network model, an agent model is introduced to optimize the hyperparameter network autonomously. Finally, experiments show that the algorithm proposed in this paper can obtain high classification accuracy in fault diagnosis of UAV engines compared to other commonly used methods, with a classification accuracy of faults as high as 97.1751%; in addition, we show that it maintains a very stable small-sample migratory learning capability under this condition.

Hybrid intelligence for enhanced fault detection and diagnosis for industrial gas turbine engine

In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. The fault detection and diagnosis (FDD) of industrial gas turbine (IGT) engine is very crucial in smart manufacturing. With the advancement of machine learning and sensor technology, artificial neural network (ANN) and multi-sensor data fusion have made it possible to solve the above issues. In this work, a hybrid model is proposed for the FDD of an IGT engine. Principal component analysis (PCA) is firstly employed to combine the multi-sensor monitoring data as a pre-processing step. The PCA approach has the capacity to glean insights from raw data and optimize the amalgamation of various condition monitoring datasets, with the aim of enhancing accuracy and maximizing the utility of gas turbine information. Later, ANN based FDD method is applied on the fused multiple sensors monitoring data. The present work also implements a comparative account of supervised and unsupervised ANN learning techniques, like multilayer perceptron and self-organizing map, and their pattern classification evaluations. The proposed model facilitates the attainment of early FDD with minimum error and has been validated and tested using real time data from actual operation environments. The data is collected from twin-shaft (18.7 MW) IGT engine as a case study. Results demonstrate that the proposed hybrid model is able to detect the conditions of industrial gas turbine engine with best diagnosis accuracy and calculated errors of 0.00173 and 1.9498. Comparison of two learning techniques demonstrates the superior performance of supervised learning technique.

Preface

This Proceedings arises from 2023 6th International Conference on Power Electronics and Control Engineering (ICPECE 2023), which was held via virtual form in Nanning, China from November 10th to 12th, 2023. Meetings in the ICPECE series were and will be held every year, and ICPECE 2023 marks the sixth time that this series of conference had been held successfully.The scientific and social program for the Conference ran over three days with more than 50 delegates from about 10 countries gathering on November 10th and departing on November 12th, including keynote speeches, oral presentations, poster presentations, free discussion, academic investigation, etc.In all there were four keynote speeches by renowned professors during the meeting. Professor Xingjian Wang from Beihang University, China addressed his research to us on Health Status Assessment and Fault-tolerance Control for Aircraft Control System. According to the control command of the pilot or the autopilot, the aircraft control system drives the aircraft rudder through the servo actuator to realize the aircraft attitude and flight trajectory control. In order to realize the highly reliable and healthy service of the aircraft control system, the health status assessment and remaining useful life prediction of the key components of the aircraft control system, the key technology of fault diagnosis for the airborne hydraulic system, and the high safety hierarchical active fault-tolerance control strategy were carried out to effectively improve the healthy service capability of the aircraft control system.Topics that were the focus of invited presentations and contributed papers at ICPECE 2023 included: Motor Drive and Frequency Converter, Drive Motor and Control Technology, Power and Fluid Machinery Equipment, Automatic Control Technology, Computer Integrated Manufacturing System, etc. All submissions were gone through a rigorous review process by performing double blind review to check their quality of content, level of innovation, significance, originality and legibility.The Conference could not have occurred without the generous support of the sponsors and the hard work of all Committee members. We are most grateful for the staff of Journal of Physics: Conference Series for their help and kindness in the preparation of this volume. Finally, we would like to thank all the attendees at ICPECE 2023 for their scientific contributions to the Conference, and for their warm spirit of engagement which characterized the scientific discussions and social occasions.The Committee of ICPECE 2023List of Committee Member is available in this pdf.

Aircraft Engine Fault Diagnosis Model Based on 1DCNN-BiLSTM with CBAM

As the operational status of aircraft engines evolves, their fault modes also undergo changes. In response to the operational degradation trend of aircraft engines, this paper proposes an aircraft engine fault diagnosis model based on 1DCNN-BiLSTM with CBAM. The model can be directly applied to raw monitoring data without the need for additional algorithms to extract fault degradation features. It fully leverages the advantages of 1DCNN in extracting local features along the spatial dimension and incorporates CBAM, a channel and spatial attention mechanism. CBAM could assign higher weights to features relevant to fault categories and make the model pay more attention to them. Subsequently, it utilizes BiLSTM to handle nonlinear time feature sequences and bidirectional contextual feature information. Finally, experimental validation is conducted on the publicly available CMAPSS dataset from NASA, categorizing fault modes into three types: faultless, HPC fault (the single fault), and HPC&Fan fault (the mixed fault). Comparative analysis with other models reveals that the proposed model has a higher classification accuracy, which is of practical significance in improving the reliability of aircraft engine operations and for Remaining Useful Life (RUL) prediction.

A review of recent advances in fault diagnosis based on deep neural networks

Bearings are essential components in mechanical systems, supporting the rotation of various machine parts in motors, wind turbines, vehicles, and industrial robots, making their health critical for system performance and reliability. Traditional diagnosis methods, such as vibration and acoustic analysis, along with temperature monitoring, often demand expertise and may struggle to detect early faults. However, the introduction of deep learning technology has created new opportunities for more effective bearing fault diagnosis. The application of deep learning-based bearing fault diagnosis in the industrial sector has gained significant attention and multiple types of deep learning networks have already been successfully implemented. This paper aims to provide a clear review of bearing fault diagnosis based on deep learning algorithms. This essay focuses on two of the most popular deep learning networks, Autoencoder and Convolutional Neural Networks. Their mechanism and applications are analyzed based on essays and research paper related to the field of bearing fault diagnosis. Finally, conclusions are presented to summarize the current development and point out faced challenges and future trends of these deep learning networks. It is also expected that this narrative not only serves as a cogent overview of the contemporary fault diagnosis technologies but also provides convenience and inspiration for further study in this field.

Analysis of the Influence of Gas Leakage in The Dipleg of Cyclone Separators on Particle Properties

The FCC unit uses a cyclone separator for gas-solid separation of catalysts from flue gas or oil and gas. When the cyclone separator experiences a gas leakage fault, it directly affects its separation performance, causing excessive catalyst emissions and leading to the occurrence of catalyst running faults. However, there is currently a lack of diagnostic technology for cyclone separator equipment malfunction and gas leakage. Therefore, the influence of the dipleg of the cyclone separator on the particle loss rate under different gas leakage velocities was investigated experimentally. Experiments show that under normal conditions, particles are subject to multiple cycle separation, and fewer particles randomly enter the riser with the upward rotating flow to escape, which is mainly determined by the structure size and inlet velocity of the cyclone separator. When gas leakage occurs in the dipleg, the higher the gas leakage velocity, the higher the particle loss rate. As the number of particle cycles increases, the loss rate gradually decreases. For this purpose, the cyclone separator inside the FCC unit in the industrial site is taken as the object. In response to multiple cyclone separator loss faults, the changes in process parameters and collected catalyst particle properties of the cyclone separator are analyzed, and the changes in the running dose inside the device during operation are analyzed. Based on the analysis results, the operation of the unit is optimized and adjusted to avoid unplanned shutdown and maintenance. Therefore, based on this, a fault diagnosis technology for catalyst loss in FCC unit cyclone separators based on particle property parameters has been created, which has the characteristics of accuracy and reliability and can be applied to the analysis and diagnosis of catalyst loss faults in FCC unit.

An integrated grey-box model for accurate ship engine performance prediction under varying speed and environmental conditions

The development of ship engine fault diagnosis has led to an increased interest in predicting marine engine performance under various environmental and operating conditions. However, predicting engine performance using a single model is limited due to the various characteristics of ship engines depending on speed and environmental conditions. To address this issue, we propose a grey box model (GBM)-based ship engine performance prediction framework that combines the white box model and black box model (BBM) appropriately for both low- and high-speed operating conditions. The application of data preprocessing techniques, such as clustering and cleaning, under specific engine and environmental conditions, combined with dimensionality reduction techniques (partial least square and principal component) and the use of WBM/BBM models under classified speed conditions, makes the proposed framework accessible to real-world operators through data-driven approaches and domain knowledge. We demonstrate that the proposed framework improves the robustness, accuracy, and efficiency of engine performance predictions by considering the characteristics of each speed in real-world navigation data, compared to using single models.

Methodology and application of digital twin-driven diesel engine fault diagnosis and virtual fault model acquisition

Digital real-time fault diagnosis is an effective way to ensure the reliable long-term operation of the diesel engine, but there is still a lack of systematic methods with high integrity and practicability. Therefore, a digital twin-driven diesel engine fault diagnosis method based on the combination of the classification algorithm and the optimization algorithm is proposed and a case study of fuel injection system fault diagnosis is used to illustrate and verify the proposed method. This method closely links the physical system, virtual model, database, and diagnosis system through data transmission and the diagnostic process consists of three parts: classification, diagnosis, and decision. The fault classification part can preliminarily lock the possible types and degrees of faults, and point out the key classification features for each fault type by using classification algorithms such as Random Forest. The fault diagnosis part can diagnose and reproduce the diesel engine faults by using an optimization-simulation joint calculation model, where the virtual model variables and optimization algorithm are determined according to the possible fault types, and the optimization target depends on the importance of classification features. Then the maintenance decision can be made according to the fault detailed information. The proposed method reduces the requirement of covering the fault degree of the database, and the obtained fault model provides the possibility for subsequent online optimization and also facilitates the development of intelligent engine management.

A fault diagnosis method for nuclear power plants rotating machinery based on deep learning under imbalanced samples

Rotating machinery is a critical equipment widely used in nuclear power plants (NPPs). Effective fault diagnosis technology can provide reliable operation and maintenance support for rotating machinery. Data-driven intelligent fault diagnosis technology has attracted much attention in recent years. However, in practical situations, the available fault data is limited, and the imbalanced samples will make the intelligent fault diagnosis model prone to problems such as poor generalization performance and low diagnostic accuracy. Therefore, a fault diagnosis method based on deep learning is proposed to alleviate the impact of imbalanced samples on fault diagnosis of rotating machinery. First, the adaptive synthetic sampling (ADASYN) approach is used to synthesize the multi-channel vibration data to expand the unbalanced samples. Subsequently, ensemble empirical mode decomposition (EEMD) and continuous wavelet transform (CWT) are used to convert the vibration data into time–frequency images to highlight the fault features of the samples. Then, the deep residual neural network is constructed to extract the features of mixed samples and implement fault diagnosis. Fault simulation experiments are carried out based on motors and bearings, and various imbalance degree datasets are formed to provide data support for verifying the effectiveness of the proposed method. The proposed method can achieve good diagnostic performance under various degrees of imbalanced samples. In addition, the comparison results with other methods show that the proposed method has the best comprehensive performance, demonstrating the potential application value in the fault diagnosis of NPPs rotating machinery.

Application of Data Visualization Technology in Fault Diagnosis and Maintenance of Intelligent Electromechanical Systems

There are problems of low efficiency and low accuracy in the fault location and maintenance process of electromechanical systems. In order to solve this problem, this article adopts a comprehensive literature analysis and case study method to conduct in-depth research on the application of data visualization technology in intelligent electromechanical systems. By collecting and analyzing relevant literature, and combining with practical cases, this article explores the specific application methods and effects of data visualization technology in fault diagnosis and maintenance. Research has shown that the diagnostic accuracy of this method is between 94% -99%, and it has good fault diagnosis ability. Data visualization technology plays an important role in the fault diagnosis and maintenance of intelligent electromechanical systems. By visualizing the real-time data and fault information of the system, maintenance personnel can intuitively understand the system status and quickly locate the root cause of the fault.