Application of Multi-sensor Information Fusion in the Fault Diagnosis of Hydraulic System

Aiming at the problem of incomplete information and uncertainties in the diagnosis of complex system by using single parameter, a new method of multi-sensor information fusion fault diagnosis based on BP neural network and D-S evidence theory is proposed. In order to simplify the structure of BP neural network, two parallel BP neural networks are used to diagnose the fault data at first; and then, using the evidence theory to fuse the local diagnostic results, the accurate inference of the inaccurate information is realized, and the accurate diagnosis resuh is obtained. The method is applied to the fault diagnosis of the hydraulic driven servo system （HDSS） in a certain type of rocket launcher, which realizes the fault location and diagnosis of the main components of the hydraulic driven servo system, and effectively improves the reliability of the system.

Application of Ferrography to Fault Diagnosis of Hydraulic Systems

This paper deals with research on the successful use of ferrography as a wear measurement method for condition monitoring and fault diagnosis of hydraulic systems. The analysis program and progression is discussed, and a case study for condition monitoring and fault diagnosis of hydraulic systems by means of ferrography is also reviewed.

Fault diagnosis method of hydraulic system based on fusion of neural network and D-S evidence theory

According to fault type diversity and fault information uncertainty problem of the hydraulic driven rocket launcher servo system（HDRLSS） , the fault diagnosis method based on the evidence theory and neural network ensemble is proposed. In order to overcome the shortcomings of the single neural network, two improved neural network models are set up at the com-mon nodes to simplify the network structure. The initial fault diagnosis is based on the iron spectrum data and the pressure, flow and temperature（PFT） characteristic parameters as the input vectors of the two improved neural network models, and the diagnosis result is taken as the basic probability distribution of the evidence theory. Then the objectivity of assignment is real-ized. The initial diagnosis results of two improved neural networks are fused by D-S evidence theory. The experimental results show that this method can avoid the misdiagnosis of neural network recognition and improve the accuracy of the fault diagnosis of HDRLSS.

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.

Development of Fault Diagnosis System for Spacecraft Based on Fault Tree and G2

Some ideas in the development of fault diagnosis system for spacecraft are introduced. Firstly, the architecture of spacecraft fault diagnosis is proposed hierarchically with four diagnosis frames, i.e., system level, subsystem level, component level and element level. Secondly, a hierarchical diagnosis model is expressed with four layers, i.e., sensors layer, function layer, behavior layer and structure layer. These layers are used to work together to accomplish the fault alarm, diagnosis and localization. Thirdly, a fault-tree-oriented hybrid knowledge representation based on frame and generalized rule and its relevant reasoning strategy is put forward. Finally, a diagnosis case for spacecraft power system is exemplified combining the above with a powerful expert system development tool G2.

Robust fault diagnosis with disturbance rejection and attenuation for systems with multiple disturbances

The fault diagnosis problem is investigated for a class of nonlinear neutral systems with multiple disturbances.Time-varying faults are considered and multiple disturbances are supposed to include the unknown disturbance modeled by an exo-system and norm bounded uncertain disturbance.A nonlinear disturbance observer is designed to estimate the modeled disturbance.Then,the fault diagnosis observer is constructed by integrating disturbance observer with disturbance attenuation and rejection performances.The augmented Lyapunov functional approach,which involves the tuning parameter and slack variable,is applied to make the solution of inequality more flexible.Finally,applications for a two-link robotic manipulator system are given to show the efficiency of the proposed approach.

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.

STUDY OF A FAULT DIAGNOSIS EXPERT SYSTEM FOR SYNTHETIC MINING SYSTEM HYDRAULIC SUPPORT

Fault diagnosis expert system for hydraulic support is studied.The system is achieved by Turbo prolong Language, it summaries the experience of the domain expert and sets up a fault tree, knowledge base is developed by a productive rule.According to the feature of diagnosis, the system selects forward non determination inferring and limited depth first search strategy.It can accomplish expert diagnosis of more than 50 kinds faults in hydraulic support.

Application of Maximum Probability Approach to the Fault Diagnosis of a Servo System

In an actual control system, it is often difficult to find out where the faults are if only based on the outside fault phenomena, acquired frequently from a fault system. So the fault diagnosis by outside fault phenomena is considered. Based on the theory of fuzzy recognition and fault diagnosis, this method only depends on experience and statistical data to set up fuzzy query relationship between the outside phenomena (fault characters) and the fault sources (fault patterns). From this relationship the most probable fault sources can be obtained, to attain the goal of quick diagnosis. Based on the above approach, the standard fuzzy relationship matrix is stored in the computer as a system database. And experiment data are given to show the fault diagnosis results. The important parameters can be on line sampled and analyzed, and when faults occur, faults can be found, the alarm is given and the controller output is regulated.

Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

Recently,intelligent fault diagnosis based on deep learning has been extensively investigated,exhibiting state-of-the-art performance.However,the deep learning model is often not truly trusted by users due to the lack of interpretability of“black box”,which limits its deployment in safety-critical applications.A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases,and the human in the deci-sion-making loop can be found to deal with the abnormal situa-tion when the models fail.In this paper,we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks,called SAEU.In SAEU,Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks.Based on the SAEU,we propose a unified uncertainty-aware deep learning framework(UU-DLF)to realize the grand vision of trustworthy fault diagnosis.Moreover,our UU-DLF effectively embodies the idea of“humans in the loop”,which not only allows for manual intervention in abnor-mal situations of diagnostic models,but also makes correspond-ing improvements on existing models based on traceability analy-sis.Finally,two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

Fault detection of excavator’s hydraulic system based on dynamic principal component analysis

In order to improve reliability of the excavator's hydraulic system, a fault detection approach based on dynamic principal component analysis(PCA) was proposed. Dynamic PCA is an extension of PCA, which can effectively extract the dynamic relations among process variables. With this approach, normal samples were used as training data to develop a dynamic PCA model in the first step. Secondly, the dynamic PCA model decomposed the testing data into projections to the principal component subspace(PCS) and residual subspace(RS). Thirdly, T2 statistic and Q statistic performed as indexes of fault detection in PCS and RS, respectively. Several simulated faults were introduced to validate the approach. The results show that the dynamic PCA model developed is able to detect overall faults by using T2 statistic and Q statistic. By simulation analysis, the proposed approach achieves an accuracy of 95% for 20 test sample sets, which shows that the fault detection approach can be effectively applied to the excavator's hydraulic system.

Artificial Intelligence-Driven Vehicle Fault Diagnosis to Revolutionize Automotive Maintenance:A Review

Conventional fault diagnosis systems have constrained the automotive industry to damage vehicle maintenance and component longevity critically.Hence,there is a growing demand for advanced fault diagnosis technologies to mitigate the impact of these limitations on unplanned vehicular downtime caused by unanticipated vehicle break-downs.Due to vehicles’increasingly complex and autonomous nature,there is a growing urgency to investigate novel diagnosis methodologies for improving safety,reliability,and maintainability.While Artificial Intelligence(AI)has provided a great opportunity in this area,a systematic review of the feasibility and application of AI for Vehicle Fault Diagnosis(VFD)systems is unavailable.Therefore,this review brings new insights into the potential of AI in VFD methodologies and offers a broad analysis using multiple techniques.We focus on reviewing relevant literature in the field of machine learning as well as deep learning algorithms for fault diagnosis in engines,lifting systems(suspensions and tires),gearboxes,and brakes,among other vehicular subsystems.We then delve into some examples of the use of AI in fault diagnosis and maintenance for electric vehicles and autonomous cars.The review elucidates the transformation of VFD systems that consequently increase accuracy,economization,and prediction in most vehicular sub-systems due to AI applications.Indeed,the limited performance of systems based on only one of these AI techniques is likely to be addressed by combinations:The integration shows that a single technique or method fails its expectations,which can lead to more reliable and versatile diagnostic support.By synthesizing current information and distinguishing forthcoming patterns,this work aims to accelerate advancement in smart automotive innovations,conforming with the requests of Industry 4.0 and adding to the progression of more secure,more dependable vehicles.The findings underscored the necessity for cross-disciplinary cooperation and examined the total potential of AI in vehicle default analysis.

Machine Fault Diagnosis Using Audio Sensors Data and Explainable AI Techniques-LIME and SHAP

Machine fault diagnostics are essential for industrial operations,and advancements in machine learning have significantly advanced these systems by providing accurate predictions and expedited solutions.Machine learning models,especially those utilizing complex algorithms like deep learning,have demonstrated major potential in extracting important information fromlarge operational datasets.Despite their efficiency,machine learningmodels face challenges,making Explainable AI(XAI)crucial for improving their understandability and fine-tuning.The importance of feature contribution and selection using XAI in the diagnosis of machine faults is examined in this study.The technique is applied to evaluate different machine-learning algorithms.Extreme Gradient Boosting,Support Vector Machine,Gaussian Naive Bayes,and Random Forest classifiers are used alongside Logistic Regression(LR)as a baseline model because their efficacy and simplicity are evaluated thoroughly with empirical analysis.The XAI is used as a targeted feature selection technique to select among 29 features of the time and frequency domain.The XAI approach is lightweight,trained with only targeted features,and achieved similar results as the traditional approach.The accuracy without XAI on baseline LR is 79.57%,whereas the approach with XAI on LR is 80.28%.

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

Stochastic resonance of coupled time-delayed system with fluctuation of mass and frequency and its application in bearing fault diagnosis

The stochastic resonance behavior of coupled stochastic resonance(SR)system with time-delay under mass and frequency fluctuations was studied.Firstly,the approximate system model of the time-delay system was obtained by the theory of small time-delay approximation.Then,the random average method and Shapiro-Loginov algorithm were used to calculate the output amplitude ratio of the two subsystems.The simulation analysis shows that increasing the time-delay and the input signal amplitude appropriately can improve the output response of the system.Finally,the system is applied to bearing fault diagnosis and compared with the stochastic resonance system with random mass and random frequency.The experimental results show that the coupled SR system taking into account the actual effect of time-delay and couple can more effectively extract the frequency of the fault signal,and thus realizing the diagnosis of the fault signal,which has important engineering application value.

The Lightweight Edge-Side Fault Diagnosis Approach Based on Spiking Neural Network

Network fault diagnosis methods play a vital role in maintaining network service quality and enhancing user experience as an integral component of intelligent network management.Considering the unique characteristics of edge networks,such as limited resources,complex network faults,and the need for high real-time performance,enhancing and optimizing existing network fault diagnosis methods is necessary.Therefore,this paper proposes the lightweight edge-side fault diagnosis approach based on a spiking neural network(LSNN).Firstly,we use the Izhikevich neurons model to replace the Leaky Integrate and Fire(LIF)neurons model in the LSNN model.Izhikevich neurons inherit the simplicity of LIF neurons but also possess richer behavioral characteristics and flexibility to handle diverse data inputs.Inspired by Fast Spiking Interneurons(FSIs)with a high-frequency firing pattern,we use the parameters of FSIs.Secondly,inspired by the connection mode based on spiking dynamics in the basal ganglia(BG)area of the brain,we propose the pruning approach based on the FSIs of the BG in LSNN to improve computational efficiency and reduce the demand for computing resources and energy consumption.Furthermore,we propose a multiple iterative Dynamic Spike Timing Dependent Plasticity(DSTDP)algorithm to enhance the accuracy of the LSNN model.Experiments on two server fault datasets demonstrate significant precision,recall,and F1 improvements across three diagnosis dimensions.Simultaneously,lightweight indicators such as Params and FLOPs significantly reduced,showcasing the LSNN’s advanced performance and model efficiency.To conclude,experiment results on a pair of datasets indicate that the LSNN model surpasses traditional models and achieves cutting-edge outcomes in network fault diagnosis tasks.

Adaptive fault diagnosis of sucker rod pump systems based on optimal perceptron and simulation data

A highly precise and timely diagnosis technology can help effectively monitor and adjust the sucker rod production system(SRPS)used in oil wells to ensure a safe and efficient production.The current diagnosis method is pattern recognition of a dynamometer card(DC)based on feature extraction and perceptron.The premise of this method is that the training and target data have the same distribution.However,the training data are collected from a field SRPS with different system parameters designed to adapt to production conditions,which may significantly affect the diagnostic accuracy.To address this issue,in this study,an improved model of the sucker rod string(SRS)is derived by adding faultparameter dimensions,with which DCs under 16 working conditions could be generated.Subsequently an adaptive diagnosis method is proposed by taking simulated DCs generated near the working point of the target SRPS as training data.Meanwhile,to further improve the accuracy of the proposed method,the DC features are improved by relative normalization and using additional features of the DC position to increase the distance between different types of samples.The parameters of the perceptron are optimized to promote its discriminability.Finally,the accuracy and real-time performance of the proposed adaptive diagnosis method are validated using field data.

Optical Fibre Communication Feature Analysis and Small Sample Fault Diagnosis Based on VMD-FE and Fuzzy Clustering

To solve the problems of a few optical fibre line fault samples and the inefficiency of manual communication optical fibre fault diagnosis,this paper proposes a communication optical fibre fault diagnosis model based on variational modal decomposition(VMD),fuzzy entropy(FE)and fuzzy clustering(FC).Firstly,based on the OTDR curve data collected in the field,VMD is used to extract the different modal components(IMF)of the original signal and calculate the fuzzy entropy(FE)values of different components to characterize the subtle differences between them.The fuzzy entropy of each curve is used as the feature vector,which in turn constructs the communication optical fibre feature vector matrix,and the fuzzy clustering algorithm is used to achieve fault diagnosis of faulty optical fibre.The VMD-FE combination can extract subtle differences in features,and the fuzzy clustering algorithm does not require sample training.The experimental results show that the model in this paper has high accuracy and is relevant to the maintenance of communication optical fibre when compared with existing feature extraction models and traditional machine learning models.

Bearing fault diagnosis based on a multiple-constraint modal-invariant graph convolutional fusion network

Multisensor data fusionmethod can improve the accuracy of bearing fault diagnosis,in order to address the problems of single-sensor data types and the insufficient exploration of redundancy and complementarity between different modal data in most existing multisensor data fusion methods for bearing fault diagnosis,a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network(MCMI-GCFN)is proposed in this paper.Firstly,a Convolutional Autoencoder(CAE)and Squeeze-and-Excitation Block(SE block)are used to extract features of raw current and vibration signals.Secondly,the model introduces source domain classifiers and domain discriminators to capture modal invariance between different modal data based on domain adversarial training,making use of the redundancy and complementarity between multimodal data.Then,the spatial aggregation property of Graph Convolutional Neural Networks(GCN)is utilized to capture the dependency relationship between current and vibration modes with similar time step features for accurately fusing contextual semantic information.Finally,the validation is conducted on the public bearing damage current and vibration dataset from Paderborn University.The experimental results showed that the delivered fusion method achieved a bearing fault diagnosis accuracy of 99.6%,which was about 9%–11.4%better than that with nonfusion methods.

Temperature fault-tolerant control system of CSTR with coil and jacket heat exchanger based on dual control and fault diagnosis

For the characteristics of the continuous stirred-tank reactor(CSTR) with coil and jacket cooling system,a CSTR temperature dual control solution based on the analysis of the CSTR exothermic reaction control characteristic was proposed for an organic material polymerization production.The control solution has passive fault-tolerant ability for the jacket cooling water cutting off fault and active fault-tolerant potential for the coil cooling water cutting off fault,and it has good control ability,high saving energy and reducing consumption performance.Fault detection and diagnosis and fault-tolerant control strategy are designed for the coil cooling fault to achieve the active fault-tolerant control function.The CSTR temperature dual control,process fault detection and diagnosis and active fault-tolerant control were full integrated into the CSTR temperature fault-tolerant control system,which achieve fault tolerance control of CSTR temperature for any severe malfunction of jacket cooling or coil cooling cutting off,and the security for CSTR exothermic reaction is improved.Finally,the effectiveness of this system was validated by semi-physical simulation experiment.