Appearance Fault Diagnosis of a Transformer Based on Data Set Optimization and Heterogeneous Model Ensemble

This paper proposes a new method for fault diagnosis of new energy transmission system based on combined BiLSTM-1DCNN model. The EV dataset is preprocessed and converted into a format acceptable to the model. The BiLSTM neural network is used to extract temporal features, and the 1DCNN network is used to capture the spatial features of the data. The combination of the two networks can effectively improve the accuracy and efficiency of fault diagnosis. Comparing the proposed method with traditional machine learning methods, it is found that the proposed method has higher accuracy and faster convergence speed. Sensitivity analysis is used to study the impact of different hyperparameters on model performance. The results show that the performance of the model is affected by the number of layers, learning rate and window size in the 1DCNN network. In addition, the experiments and datasets of this study are from ADVISOR of the US Department of Energy (DOE). The proposed combined BiLSTM-1DCNN model provides a promising method for fault diagnosis of new energy drive systems, which can improve the efficiency and accuracy of fault diagnosis.

The complexity and diversity of equipments presented in the development of modern industrial technology brings the wide application of deep learning in fault diagnosis. However, the multi-source heterogeneous data collected from different sensors applied in industrial production cannot be used by traditional neural networks directly, which registers a difficulty to fault diagnosis based on deep learning. In addition, with only one of the data used, traditional deep learning fault diagnosis methods ignores the correlation between heterogeneous data, which may result in the loss of useful information and the accuracy of fault diagnosis. To solve the above problems, a fault diagnosis framework based on deep learning for multi-source heterogeneous data fusion is proposed. In the feature learning stage, stack self-encoder (SAE) and convolution neural network (CNN) are used to extract deep features from one-dimensional vibration data and two-dimensional image data respectively, and then feature fusion fault diagnosis is carried out. It solves the problem that traditional neural network can't make full use of multi-source heterogeneous data, and improves the accuracy of fault diagnosis. What's more, the bearing data of Case Western Reserve University are used to verify the validity of the diagnosis method proposed in this paper.

This paper introduces a novel metaheuristic model-based scheme for fault monitoring in squirrel cage induction motors (SCIMs). This method relies on the combination of the ant lion optimizer (ALO) and the unscented Kalman filter (UKF) to detect and quantify the number of broken bars. Contrary to the UKF-based fault diagnosis, the improved ALO-UKF algorithm tunes optimally and automatically the noise covariance matrices Q and R, which reduces the estimation errors, and then obtains an effective and accurate fault diagnosis. Firstly, a mathematical model of the fault under study has been developed based on rotor parameter value as signature. Secondly, a sixth order ALO-UKF algorithm has been synthesized for simultaneous estimation of rotor resistance and speed. Several broken bar fault conditions have been simulated. Simulation results show the effectiveness and robustness of the proposed ALO-UKF scheme in broken bar detection and identification, and exhibit a more superior performance than the simple-UKF and EKF algorithms in term of stability, accuracy and response time.

PurposePower transformers are vital components of an electrical network. A defective transformer can cause instability and blackouts in parts of the network. An accurate classification of different transformer faults results in a relatively accurate fault diagnosis and timely corrective actions. It is possible to increase productivity and reduce costs by using fault detection of power transformers through the analysis of gases dissolved in oil. The proposed technique is a suitable tool to help the utilities and engineers in charge of preventive maintenance by reducing the costs of different fault diagnosis tests for power transformers.Design/methodology/approachIn this paper, the IEC 60599 standard along with clustering and classification methods are used to classify power transformer’s fault types. K-means and Fuzzy C-means clustering methods are used for clustering, and the support vector machine (SVM) method is used for classification of different types of faults in ‎power ‎transformers. The performance of K-means and SVM methods is improved by using the Grasshopper Optimization Algorithm (GOA). The efficiency of the proposed methods is evaluated using real field data of power transformers. The purpose of this study is to propose hybrid methods including K-means-GOA clustering and SVM-GOA classification for accurate fault diagnosis. These methods have been used for the first time in fault diagnosis determination of power transformers through gas analysis. The Silhouette criteria is used in this paper to compare the efficiency of different clustering methods.FindingsSimulation results of the paper are based on the gas chromatography data related to 266 different real power transformers. They show the high accuracy and high-performance speed of intelligent clustering and classification methods compared to conventional ones. This analysis would be helpful in performing the required maintenance check and plan for repairs.Originality/valueThe applicability and efficiency of the proposed hybrid K-means-GOA and SVM-GOA models are verified for transformer fault detection using the experimental diverse data set including 266 set of real field test parameters of power transformers.

Comparative study on deep transfer learning strategies for cross-system and cross-operation-condition building energy systems fault diagnosis

Adaptive fusion based on physics-constrained dictionary learning for fault diagnosis of rotating machinery

Aiming at the problem of low accuracy of robot joint fault diagnosis, a fault diagnosis method of robot joint based on BP neural network is designed. In this paper, the UR10 robot is taken as the research object, and the end pose data of the robot are collected in real time. By injecting different joint errors and changing the sampling frequency, the joint fault database is collected and established, and the BP neural network is used for training to obtain the robot neural network fault diagnosis model. The fault diagnosis model can output the joint fault of the input end pose data. And we analyzed the influence of different joint angle errors and different training sets on the accuracy of joint fault diagnosis of the robot. The results show that when the sampling frequency is 250 Hz, the simulation result of joint fault diagnosis accuracy with the fault degree of 0.5° is 99.17%, and the experimental result is 97.87%. Compared with traditional data-driven methods, it has higher accuracy and diagnostic efficiency, and compared with existing machine learning methods, it also achieves a high accuracy while reducing the network complexity. The effectiveness of the BP neural network robot joint fault diagnosis method is verified by experiments.

Accurate faults diagnosis in power transformers is important for utilities to schedule maintenance and minimises the operation cost. Dissolved gas analysis (DGA) is one of the proven and widely accepted tools for incipient fault diagnosis in power transformers. To improve the accuracy and solve the cases that cannot be classified using Rogers’ Ratios, IEC ratios and Duval triangles methods, a novel DGA technique based on Parzen window estimation have been presented in this study. The model uses the concentrations of five combustible hydrocarbon gases: methane, ethane, ethylene, acetylene and hydrogen to compute the probability of transformers fault categories. Performance of the proposed method has been evaluated against different conventional techniques and artificial intelligence‐based approaches such as support vector machines, artificial neural networks, rough sets analysis and extreme learning machines for the same set of transformers. A comparison with other soft computing approaches shows that the proposed method is reliable and effective for incipient fault diagnosis in power transformers.

In an intelligent manufacturing context, the smooth operations of mechanical equipment in the production process of enterprises and timely fault diagnosis during operations have become increasingly important. However, the effect of traditional fault diagnosis depends on the feature extraction quality and experts’ empirical knowledge, which is inefficient and costly, and cannot match the needs of mechanical equipment fault diagnosis in intelligent manufacturing. The TSK fuzzy system has a strong approximation capability and the ability to interpret expert knowledge. The broad learning system (BLS) has strong feature extraction and fast computation capabilities. In this paper, we present a new model—the TSK fuzzy broad learning system (TSK-BLS). The model integrates the advantages of the BLS and the fuzzy system at the same time, which can be calculated quickly and accurately by pseudo-inverse and symmetry methods. On the other hand, the model is an embedded model-building mechanism, which extends the application scope of BLS theory. The model was tested on a bearing fault data set, provided by Case Western Reserve University, and the model’s fault diagnosis accuracy was as high as 0.9967. The results were compared with those of the convolutional neural network (CNN) and the BLS models, whose fault diagnosis accuracies are 0.6833 and 0.9133, respectively. Comparison showed that the proposed fault diagnosis model—TSK-BLS, achieved significant improvements.

Due to the fault vibration signal of the rolling bearing is greatly interfered by the background noise, the fault features are easily submerged and result in a low fault diagnosis accuracy. A novel fault diagnosis method of rolling bearing is proposed based on improved VMD-adaptive wavelet threshold combined with noise reduction in this paper. Firstly, the modal components are obtained based on VMD decomposition; Secondly, the dual determination criteria of sample entropy and correlation coefficient are constructed to filter the components; Subsequently, an adaptive wavelet thresholding function is proposed, and quadratic noise reduction is applied to mixed IMFs, which in turn reconstructs each component to achieve joint noise reduction. Finally, based on traditional machine learning and deep learning diagnosis methods, the features of noise reduction signals are extracted to realize fault diagnosis. By verifying and analyzing the simulated signal with the measured signal, noise components, the expression of fault characteristics, and the accuracy of fault diagnosis are eliminated, enhanced, and improved.

Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.

The battery system, as the core energy storage device of new energy vehicles, faces increasing safety issues and threats. An accurate and robust fault diagnosis technique is crucial to guarantee the safe, reliable, and robust operation of lithium-ion batteries. However, in battery systems, various faults are difficult to diagnose and isolate due to their similar features and internal coupling relationships. In this paper, the current research of advanced battery system fault diagnosis technology is reviewed. Firstly, the existing types of battery faults are introduced in detail, where cell faults include progressive and sudden faults, and system faults include a sensor, management system, and connection component faults. Then, the fault mechanisms are described, including overcharge, overdischarge, overheat, overcool, large rate charge and discharge, and inconsistency. The existing fault diagnosis methods are divided into four main types. The current research and development of model-based, data-driven, knowledge-based, and statistical analysis-based methods for fault diagnosis are summarized. Finally, the future development trend of battery fault diagnosis technology is prospected. This paper provides a comprehensive insight into the fault and defect diagnosis of lithium-ion batteries for electric vehicles, aiming to promote the further development of new energy vehicles.

The door system is the core part of the elevator. An accurate diagnosis of the door system can aid engineers in troubleshooting and reduce maintenance costs. However, the research of fault diagnosis based on elevator operation and maintenance data is still in its infancy. With the development of the industrial Internet-of-things, real-time monitoring data of elevator can be collected and used for fault diagnosis modeling. This paper investigates a machine learning-based approach to achieve accurate elevator door fault diagnosis. An experimental study was conducted based on the monitoring data collected from the real-world elevator door system. The experimental results revealed that XGBoost algorithm can accurately identify the fault type of the elevator door.

In order to realize automatic prediction and processing of remote fault diagnosis of oil well pumps distributed in different regions by crude oil production enterprises, a fault diagnosis system for oil well pumps based on machine learning was researched and designed. This fault diagnosis system is composed of three layers (perception layer, network layer and control application layer) Internet of Things structure. The function and characteristics of each layer are analyzed in this paper, and the hardware composition and control principle of sensor nodes and aggregation nodes of the measurement and control system are discussed and gives the node microcontroller program design flow chart and the main module content of the IoT central computer software design. This paper focuses on the principle of machine learning for fault diagnosis and prediction, and deeply explains the algorithm steps of using LSTM for fault diagnosis of oil well pumps. The enterprise application experiment results show that, compared with the traditional manual well patrol fault diagnosis method, this system has the advantages of convenient operation and maintenance, low labor intensity, high timeliness and accuracy of fault diagnosis, which can better reduce equipment maintenance costs for enterprises.

PurposeThe purpose of this paper is to provide a shorter time cost, high-accuracy fault diagnosis method for water pumps. Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention. Considering the time-consuming empirical mode decomposition (EMD) method and the more efficient classification provided by the convolutional neural network (CNN) method, a novel classification method based on incomplete empirical mode decomposition (IEMD) and dual-input dual-channel convolutional neural network (DDCNN) composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approachThis paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient (MFCC) and a neural network model of DDCNN. First, the sound signal is decomposed by IEMD to get numerous intrinsic mode functions (IMFs) and a residual (RES). Several IMFs and one RES are then extracted by MFCC features. Ultimately, the obtained features are split into two channels (IMFs one channel; RES one channel) and input into DDCNN.FindingsThe Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII dataset) is used to verify the practicability of the method. Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis. Compared with EMD, 51.52% of data preprocessing time, 67.25% of network training time and 63.7% of test time are saved and also improve accuracy.Research limitations/implicationsThis method can achieve higher accuracy in fault diagnosis with a shorter time cost. Therefore, the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/valueThis method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.