A novel multi-resolution network for the open-circuit faults diagnosis of automatic ramming drive system

The open-circuit fault is one of the most common faults of the automatic ramming drive system(ARDS),and it can be categorized into the open-phase faults of Permanent Magnet Synchronous Motor(PMSM)and the open-circuit faults of Voltage Source Inverter(VSI). The stator current serves as a common indicator for detecting open-circuit faults. Due to the identical changes of the stator current between the open-phase faults in the PMSM and failures of double switches within the same leg of the VSI, this paper utilizes the zero-sequence voltage component as an additional diagnostic criterion to differentiate them.Considering the variable conditions and substantial noise of the ARDS, a novel Multi-resolution Network(Mr Net) is proposed, which can extract multi-resolution perceptual information and enhance robustness to the noise. Meanwhile, a feature weighted layer is introduced to allocate higher weights to characteristics situated near the feature frequency. Both simulation and experiment results validate that the proposed fault diagnosis method can diagnose 25 types of open-circuit faults and achieve more than98.28% diagnostic accuracy. In addition, the experiment results also demonstrate that Mr Net has the capability of diagnosing the fault types accurately under the interference of noise signals(Laplace noise and Gaussian noise).

Intelligent Diagnosis Method for Typical Co-frequency Vibration Faults of Rotating Machinery Based on SAE and Ensembled ResNet-SVM

Intelligent fault diagnosis is an important method in rotating machinery fault diagnosis and equipment health management.To deal with co-frequency vibration faults,a type of typical fault in rotating machinery,this paper proposes a fault diagnosis method based on the stacked autoencoder(SAE)and ensembled ResNet-SVM.Furthermore,the time-and frequency-domain features of several co-frequency vibration faults are summarized based on the mechanism analysis and calculated using actual vibration data.To realize and validate the high-precision diagnosis method of rotating equipment with co-frequency faults proposed in this study,the following three criteria are required:First,to improve the effectiveness and robustness of the ensembled model and the sliding window using data augmentation,adding noise,autoencoder(AE)and SAE methods are analyzed in terms of principle and practical effects.Second,ResNet is used as the feature extractor for the ensembled ResNet-SVM model.Feature extraction is carried out twice,and the extracted co-frequency fault features are more comprehensive.Finally,the data augmentation method and ensemble ResNet-SVM are combined for fault diagnosis and compared with other methods.The experimental results show that the accuracy of the proposed method can exceed 99.9%.

CHARACTERISTICS AND THEIR CORRECT SELECTION IN THE FAULTS DIAGNOSIS OF HYDRAULIC

The condition characteristics of hydraulic systems reflect running condition for the hydraulic equipment directly. It is the key for condition monitoring and early fault diagnosis to select characteristics reasonably. In this paper, the types, properties of characteristics in hydraulic equipment are analysed, and some considerations in their selection are presented.

DIAGNOSIS OF DAMPING FAULTS IN HELICOPTER ROTOR HUB BASED ON FUSELAGE VIBRATIONS

Damping faults in a helicopter rotor hub are diagnosed by using vibration signals from the fuselage. Faults include the defective lag damper and raspings in its flap and feathering hinges. Experiments on the diagnosis of three faults are carried out on a rotor test rig with the chosen fault each time. Fuselage vibration signals from specified locations are measured and analyzed by the fast Fourier transform in the frequency domain. It is demonstrated that fuselage vibration frequency spectra induced by three faults are different from each other. The probabilistic neural network （PNN） is adopted to detect three faults. Results show that it is feasible to diagnose three faults only using fuselage vibration data.

Auditory-model-based Feature Extraction Method for Mechanical Faults Diagnosis

It is well known that the human auditory system possesses remarkable capabilities to analyze and identify signals. Therefore, it would be significant to build an auditory model based on the mechanism of human auditory systems, which may improve the effects of mechanical signal analysis and enrich the methods of mechanical faults features extraction. However the existing methods are all based on explicit senses of mathematics or physics, and have some shortages on distinguishing different faults, stability, and suppressing the disturbance noise, etc. For the purpose of improving the performances of the work of feature extraction, an auditory model, early auditory（EA） model, is introduced for the first time. This auditory model transforms time domain signal into auditory spectrum via bandpass filtering, nonlinear compressing, and lateral inhibiting by simulating the principle of the human auditory system. The EA model is developed with the Gammatone filterbank as the basilar membrane. According to the characteristics of vibration signals, a method is proposed for determining the parameter of inner hair cells model of EA model. The performance of EA model is evaluated through experiments on four rotor faults, including misalignment, rotor-to-stator rubbing, oil film whirl, and pedestal looseness. The results show that the auditory spectrum, output of EA model, can effectively distinguish different faults with satisfactory stability and has the ability to suppress the disturbance noise. Then, it is feasible to apply auditory model, as a new method, to the feature extraction for mechanical faults diagnosis with effect.

A Hybrid Diagnosis Method for Inverter Open-circuit Faults in PMSM Drives

In order to improve the evaluation process of inverter open-circuit faults diagnosis in permanent magnet synchronous motor(PMSM)drives,this paper presents a diagnosis method based on current residuals and machine learning models.The machine learning models are introduced to make a comprehensive evaluation for the current residuals obtained from a state observer,instead of evaluating the residuals by comparing with thresholds.Meanwhile,fault diagnosis and location are conducted simultaneously by the machine learning models,which simplifies the diagnosis process.Besides,a sampling strategy is designed to implement the proposed scheme online.Experiments are carried out on a DSP based PMSM drive,and the effectiveness of the proposed method is verified.

Distributed fault diagnosis observer for multi-agent system against actuator and sensor faults

Component failures can cause multi-agent system(MAS)performance degradation and even disasters,which provokes the demand of the fault diagnosis method.A distributed sliding mode observer-based fault diagnosis method for MAS is developed in presence of actuator and sensor faults.Firstly,the actuator and sensor faults are extended to the system state,and the system is transformed into a descriptor system form.Then,a sliding mode-based distributed unknown input observer is proposed to estimate the extended state.Furthermore,adaptive laws are introduced to adjust the observer parameters.Finally,the effectiveness of the proposed method is demonstrated with numerical simulations.

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.

Overview of the Importance of Intelligent Approaches on Machinery Faults Diagnosis and Prediction Based on Prognostic and Health Management/Condition-Based Maintenance

Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accidents leading to production shrinkage.The potential failure would negatively affect the profitability of the company,including production shut down,cost of spare parts,cost of labor,damage of reputation,risk of injury to people and the environment.In recent years,condition-based maintenance( CBM) and prognostic and health management( PHM) are developed and formed a strong connection among science,engineering,computer,reliability,communication,management,etc.Computerized maintenance management systems( CMMS) store a lot of data regarding the fault diagnosis and life prediction of the machinery equipment.It's too necessary to uncover useful knowledge from the huge amount of data.It's vital to find the ways to obtain useful and concise information from these data.This information can be of great influence in the decision making of managers.This article is a review of intelligent approaches in machinery faults diagnosis and prediction based on PHM and CBM.

Label Recovery and Trajectory Designable Network for Transfer Fault Diagnosis of Machines With Incorrect Annotation

The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotation is difficult and expensive.The incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and2)the distribution of target domain samples becomes misaligned with the false-labeled samples.To overcome these negative effects,this article proposes a solution called the label recovery and trajectory designable network(LRTDN).LRTDN consists of three parts.First,a residual network with dual classifiers is to learn features from cross-domain samples.Second,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source domain.With the training of relabeled samples,the complexity of diagnosis model is reduced via semi-supervised learning.Third,the adaptation trajectories are designed for sample distributions across domains.This ensures that the target domain samples are only adapted with the pure-labeled samples.The LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related machines.The results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.

Expert Experience and Data-Driven Based Hybrid Fault Diagnosis for High-SpeedWire Rod Finishing Mills

The reliable operation of high-speed wire rod finishing mills is crucial in the steel production enterprise.As complex system-level equipment,it is difficult for high-speed wire rod finishing mills to realize fault location and real-time monitoring.To solve the above problems,an expert experience and data-driven-based hybrid fault diagnosis method for high-speed wire rod finishing mills is proposed in this paper.First,based on its mechanical structure,time and frequency domain analysis are improved in fault feature extraction.The approach of combining virtual value,peak value with kurtosis value index,is adopted in time domain analysis.Speed adjustment and side frequency analysis are proposed in frequency domain analysis to obtain accurate component characteristic frequency and its corresponding sideband.Then,according to time and frequency domain characteristics,fault location based on expert experience is proposed to get an accurate fault result.Finally,the proposed method is implemented in the equipment intelligent diagnosis system.By taking an equipment fault on site,for example,the effectiveness of the proposed method is illustrated in the system.

Faults Analysis and Diagnosis of DRJ-460 Dish Centrifugal Separator′s Helical Gear

The main faults of dish centrifugal separator's helical gear are described inthis paper. In order to diagnose the DRJ-460 dish centrifugal separator correctly, the vibration istested with a helical gear under both normal and abnormal conditions. After comparing severalgeneral methods of the gear's fault feature extraction, a new convenient and effective method ispresented on the basis of analyzing the vibration spectrum under different rotary velocities.

Diagnosis of stator faults in induction motor based on zero sequence voltage after switch-off

To improve the accuracy of the stator winding fault diagnosis in induction motor,a new diagnostic method based on the Hilbert-Huang transform(HHT)was proposed.The ratio of fundamental zero sequence voltage to positive sequence voltage after switch-off was selected as the stator fault characteristic,which could effectively avoid the influence of the supply unbalance and the load fluctuation,and directly represent the asymmetry in the stator.Using the empirical mode decomposition(EMD)based on HHT,the zero sequence voltage after switch-off was decomposed and the fundamental component was extracted.Then,the fault characteristic can be acquired.Experimental results on a 4-kW induction motor demonstrate the feasibility and effectiveness of this method.

Petri net model for diagnosis of permanent faults of a hydraulic system

Petri net model is applied to diagnose the permanent fault of hydraulic system within the framework of interpreted Petri net. The permanent fault is described as redundant structure of the model. A definition and a theorem are proposed to determine the diagnosability of the hydraulic system. The relations bwtween the diagnosability and other structure properties are also discussed. An example of actual hydraulic system is presented and its permanent fault can be diagnosed by the proposed method efficiently.

Diagnosis of multiple faults using a double parallel two-hidden-layer extreme learning machine

Multiple faults are easily confused with single faults.In order to identify multiple faults more accurately,a highly efficient learning method is proposed based on a double parallel two-hidden-layer extreme learning machine,called DPTELM.The DPT-ELM method is a variant of an extreme learning machine(ELM).There are some issues with ELM.First,achieving a high accuracy requires too many hidden nodes;second,the direct connection between the input layer and the output layer is ignored.Accordingly,to deal with the above-mentioned problems,DPT-ELM extends the single-hidden-layer ELM to a two-hidden-layer ELM,which can achieve a desired performance with fewer hidden nodes.In addition,a direct connection is built between the input layer and the output layer.Since the input layer weights and the thresholds of the two hidden layers are determined randomly,this simplifies the improved model and shortens the calculation time.Additionally,to improve the signal to noise ratio(SNR),an adaptive waveform decomposition(AWD)algorithm is used to denoise the vibration signal.Then,the denoised signal is used to extract the eigenvalues by the time-domain and frequency-domain methods.Finally,the eigenvalues are input to the DPT-ELM classifier.In this paper,two groups of rolling bearing data at different speeds,which were collected from a real experimental platform,are used to test the method.Each set of data includes three single fault states,two complex fault states and a healthy state.The experimental results demonstrate that the DPT-ELM method achieves fast learning speed and a high accuracy.Moreover,based on 10-fold cross-validation,it proves to be an effective method to improve the accuracy with fewer hidden nodes.

Open-Circuit Faults Diagnosis in Direct-Drive PMSG Wind Turbine Converter

The condition monitoring and fault diagnosis have been identified as the key to achieving higher availabilities of wind turbines.Numerous studies show that the open-circuit fault is a significant contributor to the failures of wind turbine converter.However,the multiple faults combinations and the influence of wind speed changes abruptly,grid voltage sags and noise interference have brought great challenges to fault diagnosis.Accordingly,concerning the open-circuit fault of converters in direct-driven PMSG wind turbine,a diagnostic method for multiple open-circuit faults is proposed in this paper,which is divided into two tasks:The first one is the fault detection and the second one is the fault localization.The detection method is based on the relative current residuals after exponential transformation and on an adaptive threshold,and the localization method is based on the average values of fault phase currents.The scheduled diagnosis method is available to both the generator-side converter and the grid-side converter,allowing to detect and locate single and double open-circuit faults.For validating this,robustness test and multiple open-circuit faults diagnosis are presented in a 2-MW direct-driven PMSG wind turbine system,the results validate the reliability and effectiveness of the proposed method.

Stator Winding Turn Faults Diagnosis for Induction Motor by Immune Memory Dynamic Clonal Strategy Algorithm

Quick detection of a small initial fault is important for an induction motor to prevent a consequent large fault.The mathematical model with basic motor equations among voltages,currents,and fluxes is analyzed and the motor model equations are described.The fault related features are extracted.An immune memory dynamic clonal strategy(IMDCS)system is applied to detecting the stator faults of induction motor.Four features are obtained from the induction motor,and then these features are given to the IMDCS system.After the motor condition has been learned by the IMDCS system,the memory set obtained in the training stage can be used to detect any fault.The proposed method is experimentally implemented on the induction motor,and the experimental results show the applicability and effectiveness of the proposed method to the diagnosis of stator winding turn faults in induction motors.

Causal temporal graph attention network for fault diagnosis of chemical processes

Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical processes.With the development of artificial intelligence(AI)and big data technologies,data-driven approaches with excellent performance are widely used for FDD in chemical processes.However,improved predictive accuracy has often been achieved through increased model complexity,which turns models into black-box methods and causes uncertainty regarding their decisions.In this study,a causal temporal graph attention network(CTGAN)is proposed for fault diagnosis of chemical processes.A chemical causal graph is built by causal inference to represent the propagation path of faults.The attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault fluctuations.Experiments in the Tennessee Eastman(TE)process and the green ammonia(GA)process showed that CTGAN achieved high performance and good explainability.

Hierarchical multihead self-attention for time-series-based fault diagnosis

Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.

Dynamic Vision-Based Machinery Fault Diagnosis With Cross-Modality Feature Alignment

Intelligent machinery fault diagnosis methods have been popularly and successfully developed in the past decades,and the vibration acceleration data collected by contact accelerometers have been widely investigated.In many industrial scenarios,contactless sensors are more preferred.The event camera is an emerging bio-inspired technology for vision sensing,which asynchronously records per-pixel brightness change polarity with high temporal resolution and low latency.It offers a promising tool for contactless machine vibration sensing and fault diagnosis.However,the dynamic vision-based methods suffer from variations of practical factors such as camera position,machine operating condition,etc.Furthermore,as a new sensing technology,the labeled dynamic vision data are limited,which generally cannot cover a wide range of machine fault modes.Aiming at these challenges,a novel dynamic vision-based machinery fault diagnosis method is proposed in this paper.It is motivated to explore the abundant vibration acceleration data for enhancing the dynamic vision-based model performance.A crossmodality feature alignment method is thus proposed with deep adversarial neural networks to achieve fault diagnosis knowledge transfer.An event erasing method is further proposed for improving model robustness against variations.The proposed method can effectively identify unseen fault mode with dynamic vision data.Experiments on two rotating machine monitoring datasets are carried out for validations,and the results suggest the proposed method is promising for generalized contactless machinery fault diagnosis.