Valve Fault Research Articles

Anomaly Detection in Spacecraft Propulsion System using Time Series Classification based on K-NN

In this paper, we propose an anomaly detection method developed by the team called “Team Tsubasa” in the PHMAP2023 Data Challenge. This is an anomaly detection competition for spacecraft propulsion systems (PHM Society, 2023). We joined the Data Challenge with the aim of deepening our knowledge of anomaly detection technology through the competition. In spacecraft propulsion systems, solenoid valve faults and bubble anomalies can occur, and it is considered important to detect them. Also, when other unknown anomalies occur, it is necessary to detect them without confusing them with known anomalies. In this paper, we propose time series classification by k-NN algorithm (Cover & Hart, 1967) as one of the methods to detect these anomalies. In this data challenge, we tried to classify anomalies by k-NN and to identify the location of the anomalies. For those classified as solenoid valve faults, we estimated the opening ratio of the solenoid valve from the similarity of the time series waveforms. As a result, the proposed method achieved a score of 99.05% based on the scoring rules given by the PHMAP 2023 Secretariat and our team won third place.

Hierarchical fault diagnosis and severity identification method of building air condition systems

Faults are inevitable of building Heating, Ventilation and Air Conditioning (HVAC) system, which causing either excessive energy consumption, bad thermal comfort, or undesirable indoor air quality. Existing fault diagnosis research generally uses algorithm optimization and data processing to improve performance, but not enough consideration is given to process design and the difference of physical properties of parameters during fault. Thus, this paper proposed a two-level hierarchical fault diagnosis and severity identification method for building Variable Refrigerant Flow (VRF) system. The Extreme Gradient Boosting (XGB) was studied to train fault diagnosis model at first level, and the association rule dug out each fault feature with different severities and XGB was used to identify fault severity at second level. Three faults with ten severities were simulated to verify this method. The results indicated that the fault diagnosis accuracy of abnormal refrigerant charge, four-way valve fault and Electronic Expansion Valve (EXV) fault could reach 99.46%, 100% and 99.65% respectively. The association rule analysis found that the discharge temperature, the sub-cooler gas outlet temperature, and sub-cooler EXV opening had the highest support to three faults respectively. Based on adaptive input features, the average fault severity identification rate of three faults could reach 98.23%, 99.94% and 96.16% respectively.

Improved fault diagnosis method of electric gate valve in nuclear power plant

The vibration signal (VS) analysis and acoustic emission signal (AES) analysis methods are the common effective diagnostic methods in valve fault diagnosis (FD)(Classify fault types). However, these two methods are disadvantaged by the surrounding environment and noise signals produced during acquisition. To obtain an improved FD effect of an electric gate valve (EGV) in nuclear power plant, the two previous methods are ameliorated by a noise reduction processing, then the signal feature extraction is performed. The FD and degree evaluation are carried out for the common fault types of the EGV taken as object. In this paper, three-phase unbalanced faults (Acquisition of VS), packing damage faults (Acquisition of VS) and internal leakage faults (Acquisition of AES) are taken as examples. The Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm composed with Fast Fourier Transform (FFT) and the SAEU3H series digital acoustic emission detection system (SAEU3H SDAEDS) are used to noise reduction and extraction of parameters of the VS and AES, respectively. Then, the extracted feature parameters are brought into the Bi-directional Long Short-Term Memory (Bi-LSTM) deep neural network for FD and fault degree evaluation (Assess the severity of failure occurrences). The experimental results show that the method adopted in this paper has high FD accuracy and low fault evaluation error.

Research on fault diagnosis method of electric gate valve under strong background noise

Electric gate valves are essential equipment in nuclear power plants. The safe and stable operation of an electric gate valve is key in maintaining the safety of nuclear power plant. However, due to the strong surrounding noise during the signal acquisition process that affect nuclear power plant electric gate valves, the early status monitoring and fault diagnosis of the electric gate valve are ineffective. However, the traditional fault diagnosis methods are not suitable for electric gate valves and fail to classify faults classification under the strong background noise. To achieve the noise reduction of electric gate valve acceleration signals based on strong background noise, the work proposes a Variational Mode Decomposition (VMD) method to denoise the strong noise in the collected signal. Seven genetic optimization algorithms are combined with VMD to enhance the model parameter selection of VMD. This selection criterion helps to select the most suitable algorithm combination for processing the acceleration signal of the electric gate valve under the background of strong noise. In order to obtain a better fault classification effect, the weak noise in the acceleration signal is further removed by Singular Value Decomposition (SVD). Moreover, the time-domain feature parameter extraction is performed on the denoised acceleration signal. Consequently, the model training of the Bidirectional Gate Recurrent Unit (BGRU) and the development of the electric gate valve fault diagnosis system under the background of strong noise are completed. The final experimental results show that the system developed in this paper has a good fault classification effect.

Fault Diagnosis in Gas Lift System Using PDF Data

Fault detection and isolation in the gas lift system were implemented assuming the gas lift variables are stochastic. Injection valve coefficient (Civ), production choke coefficient (Cpc), annulus pressure (Pa), and wellhead pressure (Pwh) were observed to show variations with faults presence. By simulating these gas lift variables as stochastic, the probability density function (PDF) data were used to generate decision functions for both the detection and isolation of the gas lift valve faults. The scheme accurately detected and isolated faults in the injection valve coefficient (Civ) and production choke coefficient (Cpc). The result of this diagnosis will aid the proper implementation of fault tolerant control in the gas lift system which will lead to its optimal operation.

Adaptive diagnosis and non-fragile predictive control for HFV engine with non-Gaussian uncertain output

This study presents an adaptive fault estimation and model predictive fault-tolerant control (FTC) for the hypersonic vehicle engine with non-Gaussian uncertain output jet plume. The non-Gaussian probability density function (PDF) describing the plume velocity in a stochastic system is approximated by Type II fuzzy radial basis functions. In the fault observer, the novel prey adaptive estimation method is designed for the valve faults with different amplitudes. Ultimately, this fuzzy-prey fusion adaptive observer shields perturbation and accurately estimates complex faults including incipient and intermittent faults. A predictive tolerant controller compensates for all the faults effects and non-fragile compensation factors of FTC eliminate the perturbation interference, thence the output PDF matches with the expected value. Finally, the more refined internal structure of plume output distribution replaces the local and rough valve position variables, helping this study realizes the hypersonic vehicle engine integrated refine control. Simulation result verifies the effectiveness of the proposed approaches and the superiority compared with the existing method.

Actuation of an electrohydraulic manipulator with a novel feedforward compensation scheme and PID feedback in servo-proportional valves

Achieving good tracking control beyond 0.1Hz by electrohydraulic manipulators still remains challenging due to the coupling of nonlinear actuation dynamics and multiple actuations. A novel order-separated feedforward, or FF, model has been proposed for estimating the major part of the commands of servo-proportional valves for metering their ports to monitor oil flow in the paired cylinders. Motion studies have been executed in serial manipulation mode by using such control to two valves and in serial–parallel mode to eight valves. Oil leakage and cylinder friction have been included as lower-order effects for the narrow radial clearance and near-zero lap in the valves each paired with a low-friction cylinder. Other assumptions of negligible inertia and suspended weight under the pistons have been validated by a numerical exercise. A PID feedback has been added during real-time tracking by an FFPID controller. Reciprocating and circular motion demands in the serial mode and heave tracking in serial–parallel mode, all in a vertical plane, have been executed. More precise and smoother tracking has been achieved up to 1Hz in the serial mode mostly with lower expense of energy than a conventional PID-alone controller. Results indicate FF guidance to mitigate oscillations occasionally apparent in PID-only case due to either hunting among multiple solutions or gain sensitivity of the nonlinear system. Good heave tracking has been obtained up to 0.2Hz. Substantial disturbance rejection capability of the controller has been demonstrated against tension arising from the connecting oil hoses. A potential use of the FF model in diagnosing emerging valve or cylinder fault with their aging has also been explained.

Time-frequency Feature Extraction Method of the Multi-Source Shock Signal Based on Improved VMD and Bilateral Adaptive Laplace Wavelet

Vibration signals have the characteristics of multi-source strong shock coupling and strong noise interference owing to the complex structure of reciprocating machinery. Therefore, it is difficult to extract, analyze, and diagnose mechanical fault features. To accurately extract sensitive features from the strong noise interference and unsteady monitoring signals of reciprocating machinery, a study on the time-frequency feature extraction method of multi-source shock signals is conducted. Combining the characteristics of reciprocating mechanical vibration signals, a targeted optimization method considering the variational modal decomposition (VMD) mode number and second penalty factor is proposed, which completed the adaptive decomposition of coupled signals. Aiming at the bilateral asymmetric attenuation characteristics of reciprocating mechanical shock signals, a new bilateral adaptive Laplace wavelet (BALW) is established. A search strategy for wavelet local parameters of multi-shock signals is proposed using the harmony search (HS) method. A multi-source shock simulation signal is established, and actual data on the valve fault are obtained through diesel engine fault experiments. The fault recognition rate of the intake and exhaust valve clearance is above 90% and the extraction accuracy of the shock start position is improved by 10°.

Pitch control of electrohydraulic semi-rotary-actuated wind turbine with actuator and valve fault using generalized power-based exponential rate reaching law sliding mode controller

Wind power systems comprise complex components and get exposed to harsh environments due to wind speed variations. Researchers in the domain of wind turbine system control are getting more and more attracted to applying sliding mode control, which emerges as an interesting viable option because of its ease of implementation in practice. Design of suitable nonlinear reaching laws in sliding mode control remains an active domain of research which can simultaneously offer fast convergence and improved control performance. This article develops a detailed model of a proportional valve-controlled semi-rotary-actuated wind turbine with valve deadband, valve fault, and actuator fault. Then, the work proposes a generalized power-based exponential rate reaching law-based sliding mode control for pitch control. Detailed derivation of the reaching time for the proposed sliding mode controller with the reaching law has been presented and its stability analysis has been carried out based on Lyapunov theory. Furthermore, the controller performance has been studied as a passive fault-tolerance controller. Extensive performance evaluations have been carried out using benchmark test signals and real wind data, and the superiority of the proposed controller has been demonstrated in comparison to other state-of-the-art sliding mode controls employing a variety of exponential reaching laws and recently proposed wind turbine pitch controller. The proposed generalized power-based exponential rate reaching law-based sliding mode control was able to achieve the lowest integral absolute error value of 0.0014 with real wind data in comparison to the other competing controllers considered here, that is, exponential reaching law-based sliding mode control, exponential rate reaching law-based sliding mode control, constant proportional rate reaching law-based sliding mode control, enhanced exponential reaching law-based sliding mode control, and improved exponential rate reaching law-based sliding mode control, which were able to achieve integral absolute error values of 0.0086, 0.0065, 0.0050, 0.0034, and 0.0015, respectively. Furthermore, the robustness of the proposed generalized power-based exponential rate reaching law-based sliding mode control has been aptly demonstrated with the instantaneous imposition of fault in the actuator.

Multisource electrohydraulic servo valve fault status diagnostic algorithm based on a message propagation mechanism

Fault identification of electrohydraulic servo valves is crucial to maintain the reliability and safety of high-precision electrohydraulic servo systems. Because the nonlinear characteristics and fault characteristics of electrohydraulic servo systems under noise conditions are implicit, it is difficult to obtain a large number of fault data of electrohydraulic servo valves. Therefore, an electrohydraulic servo valve fault diagnosis model based on characteristic distillation is proposed in this paper. First, the original fault data model is obtained based on an electrohydraulic servo valve fault test platform, the data are standardized, and the data of more than one cycle are extracted using a combination of down sampling and a sliding window for data enhancement. Second, a neural network fault diagnosis algorithm based on stack graph convolution is proposed, which is suitable for detecting different types of states (normal state, wear state, stuck state and coil short-circuit state) of electrohydraulic servo valves. The accuracy of the test set fluctuates between 0.7 and 1.0. Then, because there is a certain relationship between the characteristic smoothing phenomenon of a stack graph convolution model and the number of layers, a multilayer stack graph convolution model is bound to have problems such as model degradation. Therefore, a residual model is introduced into the stack model to improve the convergence speed of the model during the optimization process. The results show that the average accuracy of this method is 100%.

Research on Structurally Constrained KELM Fault-Diagnosis Model Based on Frequency-Domain Fuzzy Entropy

As the core equipment of the high-pressure diaphragm pump, the working conditions of the check valve are complicated, and the vibration signal generated during operation displays non-stationary and nonlinear characteristics. In order to accurately describe the non-linear dynamics of the check valve, the smoothing prior analysis (SPA) method is used to decompose the vibration signal of the check valve, obtain the tendency term and fluctuation term components, and calculate the frequency-domain fuzzy entropy (FFE) of the component signals. Using FFE to characterize the operating state of the check valve, the paper proposes a kernel extreme-learning machine (KELM) function norm regularization method, which is used to construct a structurally constrained kernel extreme-learning machine (SC-KELM) fault-diagnosis model. Experiments demonstrate that the frequency-domain fuzzy entropy can accurately characterize the operation state of check valve, and the improvement of the generalization of the SC-KELM check valve fault model improves the recognition accuracy of the check-valve fault-diagnosis model, with an accuracy rate of 96.67%.

Fault diagnosis of the hydraulic valve using a novel semi-supervised learning method based on multi-sensor information fusion

Hydraulic systems are usually applied in large and complex engineering fields. For hydraulic systems or components in operation, it is difficult to obtain fault data with fault labels due to the high engineering cost. Therefore, a semi-supervised learning (SSL) method based on multi-sensor information fusion is proposed to obtain valuable pseudo label data to diagnose faults of the hydraulic directional valve in operation. In this method, the classification model is trained from a small amount of data with fault labels, thus generating pseudo labels for a large amounts of unmarked data. The contribution of this article is that a multi-sensor fusion algorithm is designed to obtain pseudo labels with high confidence, and an adaptive threshold model similar to generative countermeasure network is designed to intelligently generate thresholds for selecting pseudo labels instead of human intervention. Theoretical and experimental results show that the multi-sensor information fusion algorithm can obtain high confidence pseudo tags, the adaptive threshold model can screen effective pseudo tag samples by generating appropriate thresholds for accelerating the convergence of the classification model. In the hydraulic valve fault diagnostic test, after five iterations, the average diagnosis accuracy of this method can reach 99.72% and 99.00% respectively for different types of hydraulic valves in different engineering fields. This provides a new idea for developing intelligent hydraulic directional valve with self fault diagnosis function.

Water Desalination Plant Fault Detection using Artificial Neural Network

<p>Water famine is very cruel. The desalination plant was brought in to alleviate the water shortage. A desalination plant has been set up in many places around the world. In the view of expanding worldwide need of fresh water, the usage of desalination plant becomes more common. There are more than twenty-five thousand desalination plants around the world. Many industries require treated water for production, water treatment, and other functions. Water quality is occasionally insufficient or does not satisfy the quality criteria for manufacturing causes. So, the enterprises utilize desalination systems to purify water for their own usage. It makes the water safe to drink as well as suitable for a variety of industrial applications. The fault occurring in the desalination plant, it slows down the processing the speed and reduce the output rate. In this study, focuses on the faults like not under system control, electrical fault, pump fault, control valve fault, inaccurate signal, old data fault, derived fault and transmitter fault. The proposed artificial neural network with the single and double component fault (ANN S-DCF) is introduced to detect the faults occurring in the desalination plant. The faults are splitted into two catagories and characteristics of each fault are trained in the artificial neural network. The result of this work achieves the best accuracy comparing to the existing techniques of SVR (support vector regression), PCA (principal component analysis) and DPLS (dynamic partial least square) method. This study achieves the accuracy rate of 96%, precision rate of 93% and sensitivity rate of 95% respectively with low complexity and high operational speed.</p>

Fault Detection of UHV Converter Valve Based on Optimized Cost-Sensitive Extreme Random Forest

Aiming at the problem of unbalanced data categories of UHV converter valve fault data, a method for UHV converter valve fault detection based on optimization cost-sensitive extreme random forest is proposed. The misclassification cost gain is integrated into the extreme random forest decision tree as a splitting index, and the inertia weight and learning factor are improved to construct an improved particle swarm optimization algorithm. First, feature extraction and data cleaning are carried out to solve the problems of local data loss, large computational load, and low real-time performance of the model. Then, the classifier training based on the optimization cost-sensitive extreme random forest is used to construct a fault detection model, and the improved particle swarm optimization algorithm is used to output the optimal model parameters, achieving fast response of the model and high classification accuracy, good robustness, and generalization under unbalanced data. Finally, in order to verify its effectiveness, this model is compared with the existing optimization algorithms. The running speed is faster and the fault detection performance is higher, which can meet the actual needs.

Fault diagnosis methods based on a time-series convolution and the comparison of multiple methods

Valves and other actuators may fail and cause economic losses or safety accidents. To ensure the stable operation of a control system, it is necessary to identify the failures of various valves and carry out the corresponding maintenance. Several methods are designed and implemented for valve fault diagnosis in this paper. In particular, a novel fault diagnosis method based on a time-series convolution network (FDM-TSCN) is proposed, which is built on a time-series data feature extracting and convolutional neural network. FDM-TSCN can classify 18 out of 19 types of fault, while many other methods cannot. This algorithm is presented in detail and implemented as a prototype system. Comprehensive simulations are performed on valve fault datasets that are generated by the development and application of methods for actuator fault diagnosis in industrial systems (DAMADICS). The simulation results prove the effectiveness and superiority of the proposed FDM-TSCN method. All of the source codes and related data in the paper are made available, which enables other researchers to verify the work easily and may inspire them to carry out more informed research.

Research on Twin Extreme Learning Fault Diagnosis Method Based on Multi-Scale Weighted Permutation Entropy.

Due to the complicated engineering operation of the check valve in a high−pressure diaphragm pump, its vibration signal tends to show non−stationary and non−linear characteristics. These leads to difficulty extracting fault features and, hence, a low accuracy for fault diagnosis. It is difficult to extract fault features accurately and reliably using the traditional MPE method, and the ELM model has a low accuracy rate in fault classification. Multi−scale weighted permutation entropy (MWPE) is based on extracting multi−scale fault features and arrangement pattern features, and due to the combination of extracting a sequence of amplitude features, fault features are significantly enhanced, which overcomes the deficiency of the single−scale permutation entropy characterizing the complexity of vibration signals. It establishes the check valve fault diagnosis model from the twin extreme learning machine (TELM). The TELM fault diagnosis model established, based on MWPE, aims to find a pair of non−parallel classification hyperplanes in the equipment state space to improve the model’s applicability. Experiments show that the proposed method effectively extracts the characteristics of the vibration signal, and the fault diagnosis model effectively identifies the fault state of the check valve with an accuracy rate of 97.222%.

Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features

This paper describes a comparison of three types of feature sets. The feature sets were intended to classify 13 faults in a centrifugal pump (CP) and 17 valve faults in a reciprocating compressor (RC). The first set comprised 14 non-linear entropy-based features, the second comprised 15 information-based entropy features, and the third comprised 12 statistical features. The classification was performed using random forest (RF) models and support vector machines (SVM). The experimental work showed that the combination of information-based features with non-linear entropy-based features provides a statistically significant accuracy higher than the accuracy provided by the Statistical Features set. Results for classifying the 13 conditions in the CP using non-linear entropy features showed accuracies of up to 99.50%. The same feature set provided a classification accuracy of 97.50% for the classification of the 17 conditions in the RC.

Early warning of reciprocating compressor valve fault based on deep learning network and multi-source information fusion

An early warning method of compressor valve fault based on multi-parameter signals (vibration, pressure, and temperature) is presented in this work. Due to the complexity working condition, the run data of the compressor are of problems like noise and feature aliasing, which makes it difficult to extract useful features and find out the running law from the original signals. In this work, an improved deep learning network Multi-Level Fusion long short-term memory based on Component Evaluating Empirical Mode Decomposition and Fuzzy C-Means (CEEMD-FCM & MLF-LSTM) for parameter prediction of reciprocating compressor and an information fusion strategy is proposed for compressor valve fault warning. The CEEMD-FCM & MLF-LSTM network consists of data processing block, information learning block, and prediction output block, which is mainly responsible for parameter prediction. In the data processing block, the CEEMD-FCM algorithm is used for parameter decomposition, noise removal, and fuzzy mode (FM) reconstruction, which generates the input for the information learning block to ensure the predicting accuracy and reduce model complexity. MLF-LSTM is constructed to predict the parameter in the future by learning the temporal and spatial characteristics of FMs of the run data. Then, an early warning strategy for compressor valve fault based on multi-source information fusion is developed. Experimental results have verified that the proposed CEEMD-FCM & MLF-LSTM model and early warning strategy could realize early warning of compressor valve fault effectively.

Fault Diagnosis of a Solenoid Valve Based on Multi-Feature Fusion

This paper presents a non-intrusive solenoid valve fault diagnosis method, which adopts the eigenvalue extraction scheme and combines the time-frequency analysis and time-domain analysis of the current signal through the solenoid valve fault pattern recognition method. Specifically, the research group selected the solenoid valve driving end current value and its second-order change rate curve as the characteristic curve, and then it extracted the time-domain parameters and the corresponding frequency band energy of the second-order change rate as the characteristic value. Then, the research group conducted time-frequency analysis on the basis of the current signal, created a multi-feature fusion feature vector and then input it into a multi-class support vector machine (SVM) for solenoid valve fault diagnosis. To evaluate the method, the research group developed a working solenoid valve model that integrated a magnetic circuit, circuit and spool motion, and the research group examined four typical solenoid valve states (normal, spring broken, spool stuck and spool slightly stuck), for which the research group collected the current signals during solenoid valve energization and closing. The trials involved analyzing the current characteristics of the drive end, both in simulation and experimental setups, and the research group demonstrated that the proposed drive end current detection diagnosis method can improve the accuracy of recognition by 15.22% compared with traditional neural network recognition methods. The SVM strategy exploiting a multi-feature fusion strategy can improve recognition accuracy by 8.7% and verification accuracy by 42.11% compared with SVM on the basis of the energy feature values.

Early Fault Diagnosis Model Design of Reciprocating Compressor Valve Based on Multiclass Support Vector Machine and Decision Tree

According to the character of frequent fault occurrence, difficult diagnosis of large reciprocating compressor valves, an early fault diagnosis model of reciprocating compressor valve based on multiclass support vector machine and decision tree is designed. A series of simulation experiments of the suction valve and exhaust valve on a large-scale reciprocating compressor experimental bench are made and the valve fault principle is analyzed. Using the advantages of fast and efficient decision tree classification and the prominent characteristics of support vector machine in small sample binary classification, a multivariate classification and recognition model is constructed. The typical characteristic parameters of gearbox vibration signal are extracted as the fault feature vector training model under different fault conditions, and the samples are tested. The experimental results show that the recognition effect of this method is significantly better than that of the neural network method in the case of small samples, and the recognition efficiency is improved more than that of the conventional multivariate support vector machine method which can be effectively applied to reciprocating compressor valve fault diagnosis.