Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Publication Year
Articles 1 - 30 of 38
Full-Text Articles in Engineering
Rolling Bearing Fault Diagnosis Based On Weighted Domain Adaptive Convolutional Neural Network, Wenfeng Zhang, Zhichao Zhu, Dinghui Wu
Rolling Bearing Fault Diagnosis Based On Weighted Domain Adaptive Convolutional Neural Network, Wenfeng Zhang, Zhichao Zhu, Dinghui Wu
Journal of System Simulation
Abstract: A rolling bearing fault diagnosis method based on a weighted domain adaptive convolutional neural network (WDACNN) is proposed to solve the problem that the data distribution of vibration signals of rolling bearings changes due to workload changes, which leads to poor generalization of fault diagnosis algorithm. In this method, the domain adaptation algorithm is embedded in the convolutional neural network to make the classifier based on the source domain achieve excellent generalization in the target domain, and the weight coefficient is introduced to weight the samples in the source domain to reduce the influence of the class weight deviation. …
Construction And Application Of Digital Twin System For Optical Fiber Secondary Coating Workshop, Biao Yuan, Yourui Huang, Shanyong Xu, Xue Rong
Construction And Application Of Digital Twin System For Optical Fiber Secondary Coating Workshop, Biao Yuan, Yourui Huang, Shanyong Xu, Xue Rong
Journal of System Simulation
Abstract: In order to solve the problem that the current optical fiber secondary coating workshop has inferior intelligence and low digital degree, a three-dimensional (3D) visual monitoring and fault diagnosis method for the optical fiber secondary coating workshop based on digital twin (DT) is proposed. In view of the equipment in the optical fiber secondary coating workshop, combined with the workshop production process and equipment operation mechanism, the digital modeling of all physical properties of the optical fiber secondary coating workshop is carried out, and the virtual twin scene is constructed. Real-time mapping between the virtual workshop and the physical …
A Fault Diagnosis Method Of Rescue Lifting Vehicle Based On Spectral Clustering, Li Lijing, Chang Dashuai, Li Lei, Chai Junfei
A Fault Diagnosis Method Of Rescue Lifting Vehicle Based On Spectral Clustering, Li Lijing, Chang Dashuai, Li Lei, Chai Junfei
Coal Geology & Exploration
In allusion to the characteristics of complex structure of rescue lifting vehicle, the poor independence of working condition and fault data, and the difficulty in fault diagnosis, we proposed a fault diagnosis algorithm of rescue lifting vehicle with the semi-supervised support vector machine in this paper. In the algorithm, the information on hidden features of the original fault data was mined with the idea of spectral clustering, to effectively distinguish the independent structural features of the fault information in the component system with different degrees of coupling. Firstly, a fault map was established based on the original input data. Then, …
Fault Diagnosis Of Hydraulic Power System For Coal Mine Tunnel Drilling Rig Based On T-S Fuzzy Fault Tree, Liu Ruojun, Zhang Youzhen, Yao Ke
Fault Diagnosis Of Hydraulic Power System For Coal Mine Tunnel Drilling Rig Based On T-S Fuzzy Fault Tree, Liu Ruojun, Zhang Youzhen, Yao Ke
Coal Geology & Exploration
In view of the problems of fuzzy logic relation between the elements of the system, the polymorphism of fault mode, and the difficulty in obtaining the fault probability as a result of the complication of the hydraulic power system for coal mine tunnel drilling rig, a fault diagnosis method of hydraulic power system for coal mine tunnel drilling rig based on Takagi-Sugeno (T-S) fuzzy tree was proposed to overcome the limitations of traditional fault tree in fault diagnosis and analysis of the complex electromechanical hydraulic equipment. The method could timely and accurately obtain the fault information of equipment, and to …
A Wind Turbine Fault Diagnosis Method Based On Siamese Deep Neural Network, Jiarui Liu, Guotian Yang, Xiaowei Wang
A Wind Turbine Fault Diagnosis Method Based On Siamese Deep Neural Network, Jiarui Liu, Guotian Yang, Xiaowei Wang
Journal of System Simulation
Abstract: In order to effectively extract the fault features of time series data in supervisory control and data acquisition (SCADA), considering the advantages of one-dimensional convolutional neural network (1-D CNN) for extracting local time series features and the advantages of long-term memory (LSTM) which can extract long-term dependent features, a method for fault diagnosis of wind turbines based on 1-D CNN-LSTM is proposed. To solve the problem of the scarcity of fault samples of wind turbines based on the siamese network architecture, a wind fault diagnosis method based on siamese 1-D CNN-LSTM is proposed. The proposed siamese 1-D CNN-LSTM …
Engine Wear Fault Diagnosis Based On Supervised Kernel Entropy Component Analysis, Zhichao Zhu, Dinghui Wu, Yuanchang Yue
Engine Wear Fault Diagnosis Based On Supervised Kernel Entropy Component Analysis, Zhichao Zhu, Dinghui Wu, Yuanchang Yue
Journal of System Simulation
Abstract: Focus on the influence of environment on engine operation, which leads to a large amount of redundant information and nonlinear structure in oil spectral data that affects the engine fault diagnosis results, the feature extraction method of SKECA (supervised kernel entropy component analysis) is proposed. A supervised learning algorithm is adopted on the basis of Kernel Entropy Component Analysis, which extracts the inherent geometric features of oil spectrum data to make the extracted fault features include the discriminative information. GA (genetic algorithm) is used to find parameters to optimize the results of feature extraction, and SVM (support vector machine) …
Fault Diagnosis Of Industrial Process Based On Lle And K-Means Clustering Algorithm, Li Yuan, Zewei Geng
Fault Diagnosis Of Industrial Process Based On Lle And K-Means Clustering Algorithm, Li Yuan, Zewei Geng
Journal of System Simulation
Abstract: Because of the similarity of various types of data in the industrial process. The fault diagnosis using the K-means algorithm has a large error rate. A K-means clustering algorithm based on Locally Linear Embedding (LLE) is proposed. the normal data is reduced by the LLE algorithm and the projection matrix is obtained. The projection matrix is used to map the original fault data to the low-dimensional space and the K-means algorithm clusters is used to carry out the data to establish a detection and diagnosis model. The method is applied to the fault detection and diagnosis in the TE …
Actuator Fault Status Evaluation Based On Two-Class Nmf Network, Yinsong Wang, Tianshu Sun
Actuator Fault Status Evaluation Based On Two-Class Nmf Network, Yinsong Wang, Tianshu Sun
Journal of System Simulation
Abstract: In the feedback control loop, the adjustment ability of controller covers up the performance degradation of the actuator to some degree. A fault state evaluation algorithm based on a two-class non-negative matrix network is proposed to implement online fault state monitoring of the actuator, including fault classification and degradation assessment. The local static features of the samples are extracted, and a classifier model is established to form a network. The similarity is introduced to describe the dynamic characteristics between samples. To fulfill the actuator fault status assessment, the static distance and dynamic changes of the network output are merged …
Fault Diagnosis Of Mechanical Equipment Based On Ga-Svr With Missing Data In Small Samples, Jingjing Wei, Qinming Liu, Chunming Ye, Guanlin Li
Fault Diagnosis Of Mechanical Equipment Based On Ga-Svr With Missing Data In Small Samples, Jingjing Wei, Qinming Liu, Chunming Ye, Guanlin Li
Journal of System Simulation
Abstract: In view of the equipment fault diagnosis with small and missing sample data, a method of missing data filling based on support vector regression optimized by genetic algorithm is proposed to improve the accuracy of equipment fault diagnosis. The support vector regression optimized by genetic algorithm was trained by other data values of missing data, and univariate prediction results were obtained. The training set was reconstructed through correlation analysis, so as to obtain the multivariate prediction results. Dynamic weights were established to combine univariate prediction results and multivariate prediction results to fill in the missing data. The …
Fault Detection Of Wind Turbine Bearing Based On Bo-Sdae Multi-Source Signal, Dinghui Wu, Zhichao Zhu, Xinhong Han
Fault Detection Of Wind Turbine Bearing Based On Bo-Sdae Multi-Source Signal, Dinghui Wu, Zhichao Zhu, Xinhong Han
Journal of System Simulation
Abstract: Due to the discrepancy within signals from sensors of wind turbines caused by environmental interference, the fault detection results of wind turbine bearing will be affected and the multi-source signal fault diagnosis method is proposed to improve the reliability of fault detection. The time-domain and frequency-domain features of bearing vibration signals, noise signals and temperature signals are used for feature extraction,and then the features are transmitted to the stacked denoising autoencoders, which are optimized the hidden layer node structure by the Bayesian optimization algorithm to achieve multi-source signal feature fusion. Softmax function is used for classification. Experiments show that …
Fault Diagnosis For Bearings Of Unbalanced Data Based On Feature Generation, Minglu Fan, Wang Yan, Zhicheng Ji
Fault Diagnosis For Bearings Of Unbalanced Data Based On Feature Generation, Minglu Fan, Wang Yan, Zhicheng Ji
Journal of System Simulation
Abstract: Focus on the sample imbalance and insufficiency caused by the difficulty to obtain a sufficient number of fault samples in actual production.A model for rolling bearings by combining Convolutional Neural Networks and Synthetic Oversampling is presented.The frequency domain signals is used as the input of the model,and the features are extracted by the Convolutional Neural Network.The new features are generated by Synthetic Oversampling and the data equalization is realized.The model completes the classification by putting all of the features into the Support Vector Machine,and the fault diagnosis of the rolling bearings is carried out.The comparison experiments results …
Energy Entropy And Particle Swarm Optimization Bp Neural Network Of Fault Diagnosis Techniques Of Coal Mine Cable, Zhiling Ren, Yuanyuan Zhang
Energy Entropy And Particle Swarm Optimization Bp Neural Network Of Fault Diagnosis Techniques Of Coal Mine Cable, Zhiling Ren, Yuanyuan Zhang
Journal of System Simulation
Abstract: Aimed at solving the problem of the type of fault difficult to identification when power feeder of coal mine occurred single-phase ground fault, in order to ensure coal mines production safety, a method of fault diagnosis based on wavelet packet energy entropy (WP-EE) and combined with particle swarm optimization neural network was proposed. The type of cable fault was simulated by Matlab, the acquired post-fault voltage signal was performed the three layers wavelet Packet decomposition, the fault characteristic signals was divided into eight segments by frequency, characteristics calculated the entropy energy spectrum according to the information entropy theory, …
Fault Diagnosis Of Reverse Osmosis Water Desalination Based On Optimized Support Vector Machine, Zhang Biao, Jianfeng Xing, Zhicheng Ji
Fault Diagnosis Of Reverse Osmosis Water Desalination Based On Optimized Support Vector Machine, Zhang Biao, Jianfeng Xing, Zhicheng Ji
Journal of System Simulation
Abstract: According to the reverse osmosis membrane fault problems in reverse osmosis water desalination system, a fault diagnosis method based on support vector machine (SVM) was introduced for fault diagnoses. To solve the problem of parameter optimization in SVM, an improved chaos particle swarm algorithm was proposed. The introduction of Chaos theory to particle swarm optimization algorithm may not only enhance the diversity of the population and particle global search ability, but also improve the convergence speed and accuracy of the particle swarm algorithm. The optimized SVM model was applied to the fault diagnosis of reverse osmosis water desalination system. …
Partially Observed System Design Method Realizing Unambiguous Fault Diagnosis, Fang Huan, Lu Yang, Yue Feng, Junming Guan
Partially Observed System Design Method Realizing Unambiguous Fault Diagnosis, Fang Huan, Lu Yang, Yue Feng, Junming Guan
Journal of System Simulation
Abstract: The construction methodology of partially observed system realizing unambiguous fault diagnosis was studied. The observable places determination algorithm OPD was proposed, and the necessary and sufficient condition for solution existence of the algorithm with polynomial time complexity was presented, then it is proved that all transitions in the modeled system could be distinguished by setting SO. The system operating state determination algorithm SOSD was presented based on the OPD algorithm. The proposed SOSD algorithm was realized by 1-step forward marking computation of observable places set $S_O$, it doesn't rely on the initial marking $M_0$ of the controlled …
Fault Diagnosis For Automobile Coating Equipments Based On Extension Neural Network, Yongwei Ye, Shedong Ren, Lianqiang Ye, Shenhao Ge, Zhiqin Qian
Fault Diagnosis For Automobile Coating Equipments Based On Extension Neural Network, Yongwei Ye, Shedong Ren, Lianqiang Ye, Shenhao Ge, Zhiqin Qian
Journal of System Simulation
Abstract: Aiming at the difficulty in discovering and eliminating the system faults of automobile coating equipments in time, a new method of fault diagnosis based on extension neural network was proposed. The feature of extension theory was used in managing the structured information through qualitative and quantitative description, and it was also combined by the characteristic of parallel construct in neural network. So the extension reasoning process was completed by means of the parallel distributed processing construct of the network. Matter-element input and output models were established according to the equipment monitoring parameters and fault types for the heating system. …
Research On Fault Diagnosis For Pitch Sensors Of Wind Turbines, Yanjie Zhai, Dinghui Wu, Yiyang Li, Zhicheng Ji
Research On Fault Diagnosis For Pitch Sensors Of Wind Turbines, Yanjie Zhai, Dinghui Wu, Yiyang Li, Zhicheng Ji
Journal of System Simulation
Abstract: Considering the biased output fault of pitch sensors for wind turbines, a fault diagnosis method based on the multi-innovation kalman filter algorithm was proposed. The corresponding relationship between the change of the pitch angle and the tiny displacement produced by the force acting on the tower was established according to the mechanical structure characteristics of wind turbines. More accurate estimated value for the tiny displacement was achieved by using the multi-innovation kalman filter algorithm which had higher convergence speed and estimation accuracy to reduce the large noise of the output information generated by sensors. The fault could be detected …
Application Of Pso-Bp Algorithm In Hydraulic System Fault Diagnosis, Handong Zhang, Liusong Tao
Application Of Pso-Bp Algorithm In Hydraulic System Fault Diagnosis, Handong Zhang, Liusong Tao
Journal of System Simulation
Abstract: It is of great significance to monitor, forecast and diagnose hydraulic systems’ fault timely and accurately. First, this paper describes the basic fault model theoretical knowledge of BP neural neystem failure neural network modeling has created and simulated. PSO-BP neural network has been raised, this paper has established PSO optimize model of the BP neural system fault diagnosis. BP network has been created and simulated in Plunger pump hydraulic system failure. The correct results indicate that this mixed PSO-BP algorithm is better than the improved BP algorithm, and can meet the requirements of Hydraulic system fault diagnosis.
Fault Diagnosis Algorithm Of Permanent Magnet Synchronous Motor Based On Improved Elm, Wang Xin, Wang Yan, Zhicheng Ji
Fault Diagnosis Algorithm Of Permanent Magnet Synchronous Motor Based On Improved Elm, Wang Xin, Wang Yan, Zhicheng Ji
Journal of System Simulation
Abstract: In order to address the common problems of lacking of phase and interturn short circuit fault, after analyzing the basic and corresponding fault model of permanent magnet synchronous motor(PMSM), an improved extreme learning machine (IELM) algorithm was proposed based on self-adaptive second-order particle swarm optimization (SaSECPSO). SaSECPSO employed adaptive inertia weight and cognitive coefficient with linear variation to improve the convergence rate and accuracy of second-order particle swarm optimization (SECPSO). In addition, the recognition rate of extreme learning machine (ELM) when solving the fault model of PMSM could be significantly improved by using SaSECPSO to simultaneously optimize input weights …
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Journal of System Simulation
Abstract: There are many problems in current detection methods such as conditional limitations and complexity of calculation which make them not easy to be put into practical application. The relationship between the servo motor information and the failure of the control surface was analyzed, and a method of detecting the failure rate of the control surface by using the servo current information in combination with the aerodynamic model was proposed. The result of its hardware-in-the-loop simulation shows that the detection system can quickly and accurately output the failure rate within 1 second which is a conservative estimate. That makes the …
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Quick Diagnosis Of Ucav Control Surface Failure And Its Hardware-In-The-Loop Simulation, Guanhua Lu, Xia Jie
Journal of System Simulation
Abstract: There are many problems in current detection methods such as conditional limitations and complexity of calculation which make them not easy to be put into practical application. The relationship between the servo motor information and the failure of the control surface was analyzed, and a method of detecting the failure rate of the control surface by using the servo current information in combination with the aerodynamic model was proposed. The result of its hardware-in-the-loop simulation shows that the detection system can quickly and accurately output the failure rate within 1 second which is a conservative estimate. That makes the …
Improved Threshold Function Simulation Research In Vibration Signal Denoising, Hongxing Sun, Zhang Yang
Improved Threshold Function Simulation Research In Vibration Signal Denoising, Hongxing Sun, Zhang Yang
Journal of System Simulation
Abstract: Filtering noise component of mechanical vibration signal effectively can observe the characteristics of vibration signal more clearly. So based on the wavelet threshold de-noising method, a new improved threshold function was proposed. The coefficient of wavelet transform mechanical vibration signals were estimated by the threshold selection method based on kurtosis value. Not only new threshold function conforms to the distribution characteristics of the vibration signal, but also new threshold function is continuous in the threshold point. And the new threshold function overcomes the inherent deviation which traditional threshold function brings. The research of noise reduction on the simulation signal …
Fault Diagnosis Method Of Vehicle Power Supply Based On Deep Learning And Sequential Test, Li Wei, Bingxiang Zhou, Dongnian Jiang
Fault Diagnosis Method Of Vehicle Power Supply Based On Deep Learning And Sequential Test, Li Wei, Bingxiang Zhou, Dongnian Jiang
Journal of System Simulation
Abstract: Focus on the health maintenance of vehicle power supply, a fault diagnosis method of vehicle power supply is proposed, which is based on the long and short time memory LSTM(Long Short Time Memory) network and the sequential probability ratio test SPRT(Sequential Probability Ratio Test). Based on the LSTM network, the multivariate time series model of vehicle power supply is established, and the SPRT method is used to perform the adaptive multi-sample fault diagnosis. The experiment on the vehicle power supply simulation system shows that the LSTM diagnosis model has stronger learning and mapping capabilities, and the fault diagnosis method …
Partial Discharge Detection And Localization On The Medium Voltage Xlpe Cableswith Multiclass Support Vector Machines, Fati̇h Serttaş, Fati̇h Onur Hocaoğlu
Partial Discharge Detection And Localization On The Medium Voltage Xlpe Cableswith Multiclass Support Vector Machines, Fati̇h Serttaş, Fati̇h Onur Hocaoğlu
Turkish Journal of Electrical Engineering and Computer Sciences
In medium voltage cables, partial discharges (PD?s) are the major problems that trigger electrical insulation failures. Therefore, classification of PD source type and failure localization in medium voltage cables are significant issues of medium voltage engineering. Therefore, in this study, both detection and localization of PD are studied. As a first step, 4 different kind of defects are artificially generated at the same length of the same kind of medium voltage cross-linked polyethylene (XLPE) cables. Consequently, an experimental setup is built. During the experiments, different medium voltage levels are applied to the cables, then the PD signals are measured and …
Open Circuit Fault Diagnosis Strategy For Switch Of Three Level Inverter, Yanxia Shen, Beibei Miao
Open Circuit Fault Diagnosis Strategy For Switch Of Three Level Inverter, Yanxia Shen, Beibei Miao
Journal of System Simulation
Abstract: Fault diagnosis of switch is the premise of reliable operation of three-level-inverter under the fault of the switch. Taking simple open circuit fault of the diode neutral point clamped (NPC) three level inverter as an example, the open circuit fault diagnosis method based on the combination of online and offline diagnoses is proposed. The fault phase is detected by the mean value of the bridge arm phase voltages. In the time domain, the fault switch tube is diagnosed by the maximum and minimum values of the load phase voltages. In the frequency domain, the amplitude of the fault signal …
Current Sensor Fault Diagnosis For Induction Motor In Vector Control System, Sun Kai, Baina He, Sarah Odofin, Gu Yu
Current Sensor Fault Diagnosis For Induction Motor In Vector Control System, Sun Kai, Baina He, Sarah Odofin, Gu Yu
Journal of System Simulation
Abstract: A current sensor fault diagnosis method of induction motor in vector control system is proposed. A state-space form including sensor faults and environmental disturbances/noises of induction machine is described. An augmented observer is designed to simultaneously estimate system states, and current sensor faults. To attenuate the effects from the environmental disturbances/noises, a genetic algorithm is employed to design observer gain by minimizing the estimation error against environmental disturbances and noises. A simulation model based on Matlab and real-data of the induction motor collected by experiment is utilized to validate the proposed methods, which show the efficiency of the proposed …
Fault Co-Simulation Of Fuel Regulator In A Certain Type Of Turbofan Engine, Wei Xiang, Benwei Li, Xinyi Yang, Xingbo Wang
Fault Co-Simulation Of Fuel Regulator In A Certain Type Of Turbofan Engine, Wei Xiang, Benwei Li, Xinyi Yang, Xingbo Wang
Journal of System Simulation
Abstract: A co-simulation method for fuel regulator fault diagnosis in a certain type of turbofan engine is performed, which consists of AMEsim Model of main fuel control system and Simulink Model of aero-engine. The AMEsim Model of main fuel system and Simulink Model of aero-engine are built and their accuracy is validated by experiments and the engine’s operating data, respectively. The co-simulation model based on the main fuel control system and the aero-engine is proposed through the interface of AMEsim and Simulink software. The typical faults and obviation methods are simulated by the co-simulation model. The research shows that the …
Fault Diagnosis Of High Speed Train Bogie Based On Multi-Domain Fusion Cnn, Yunpu Wu, Weidong Jin, Yingkun Huang
Fault Diagnosis Of High Speed Train Bogie Based On Multi-Domain Fusion Cnn, Yunpu Wu, Weidong Jin, Yingkun Huang
Journal of System Simulation
Abstract: The performance degradation and failures of high-speed train bogie components directly threaten the operation security of train. A fault detection method based on multi-domain fusion convolutional neural network is proposed to address the high complexity, high coupling and strong nonlinearity of vibration signals. Noise injection for time domain signal is used to enhance noise robustness and generalization of the model. Signal time-frequency representation information is obtained through embedded time-frequency transformation layer. Adaptive weight-based fusion is implemented through intrinsic characteristics of the convolutional neural network to handle the multi-domain multi-channel information. The experimental results show that the proposed method improves …
Simulation Of Surge And Stall For Aero Engine Compressor Based On Entropy, Pi Jun, Yongchao Qiu, Zhiwei Hu, Wu Wei
Simulation Of Surge And Stall For Aero Engine Compressor Based On Entropy, Pi Jun, Yongchao Qiu, Zhiwei Hu, Wu Wei
Journal of System Simulation
Abstract: The mature model NASA Rotor37 is used to simulate the transition of the compressor’s operation from the steady state to the non-steady state of stall and surge using the simulation software CFX. The transition is analyzed and researched based on the theory of thermodynamics entropy and sample entropy to provide a basis for the fault diagnosis of stall and surge. The two thermodynamic entropy parameters of average specific entropy value and the isentropic efficiency are found by the analysis changing abnormally in the event of stall. The values of the sample entropy obtained by calculation using the static …
Health Warning And Fault Diagnosisof Pulverizing System Based On Syncretic Similarity, Songming Jiao
Health Warning And Fault Diagnosisof Pulverizing System Based On Syncretic Similarity, Songming Jiao
Journal of System Simulation
Abstract: It is an arduous task to know health statusof a pulverizing system in power plant by monitoring these parameters simultaneously and the fault diagnosing process is complicated.An approach based on syncretic similarity is presented which is suitable for industrial system’s health warning and fault diagnosis.The syncretic similarity couples anew type of weighted mahalanobis distance based on principal component analysiswith an improved weighted sine similarity. The approachhas self-learning ability.Central parameterswhich are used to compute similarity can be modified along with the operation process.Simulation resultsshow that the method is suitable for online application because of its high accuracy, fast …
Transformer Fault Diagnosis Based On Feature Extraction Of Relative Transformation Principal Component Analysis, Yongbo Tang, Yinguo Xiong
Transformer Fault Diagnosis Based On Feature Extraction Of Relative Transformation Principal Component Analysis, Yongbo Tang, Yinguo Xiong
Journal of System Simulation
Abstract: In order to handle the problem that the feature extraction of dissolved gas analysis (DGA) data by principal component analysis (PCA) is not distinct, a new transformer fault diagnosis method based on relative transformation (RT) PCA is proposed. The original data space is converted to the relative data space by relative transformation which makes the transformed data more distinguishable. PCA is employed to reduce the dimension of relative space to make the features more representative in the relative space. Diagnosis model based on least squares support vector machine (LSSVM) is set up according to the fault characteristic of transformer. …