Sensor Fault Identification Research Articles

Current Sensor Fault Detection and Identification for PMSM Drives Using Multichannel Global Maximum Pooling CNN

Current Sensor Fault Detection and Identification for PMSM Drives Using Multichannel Global Maximum Pooling CNN

Identification of combined sensor faults in structural health monitoring systems

Fault diagnosis (FD), comprising fault detection, isolation, identification and accommodation, enables structural health monitoring (SHM) systems to operate reliably by allowing timely rectification of sensor faults that may cause data corruption or loss. Although sensor fault identification is scarce in FD of SHM systems, recent FD methods have included fault identification assuming one sensor fault at a time. However, real-world SHM systems may include combined faults that simultaneously affect individual sensors. This paper presents a methodology for identifying combined sensor faults occurring simultaneously in individual sensors. To improve the quality of FD and comprehend the causes leading to sensor faults, the identification of combined sensor faults (ICSF) methodology is based on a formal classification of the types of combined sensor faults. Specifically, the ICSF methodology builds upon long short-term memory (LSTM) networks, i.e. a type of recurrent neural networks, used for classifying ‘sequences’, such as sets of acceleration measurements. The ICSF methodology is validated using real-world acceleration measurements from an SHM system installed on a bridge, demonstrating the capability of the LSTM networks in identifying combined sensor faults, thus improving the quality of FD in SHM systems. Future research aims to decentralize the ICSF methodology and to reformulate the classification models in a mathematical form with an explanation interface, using explainable artificial intelligence, for increased transparency.

Design of an optimized sensor fault identification within the limited computing, memory, and energy capabilities

The main goal of this work is to design an optimized sensor-fault identification and diagnostic system for the Internet of Things (IoT) and Cyber-Physical Systems (CPS). The challenge is to accomplish this task within the sensors’ limited computing, memory, and energy capabilities. More importantly, identifying errors is time-sensitive, even though the diagnosis does not have to be made quickly. This project aims to provide an enhanced sensor-fault detection and diagnostic system for the IoT and CPS with constrained energy, memory, and computation resources. The system’s goals are to promptly detect defects, lessen the computing burden on sensors, and enhance the recall and accuracy of fault detection. This study used a hybrid approach that combined principal component analysis, autoencoder, and gated recurrent unit to create an optimal sensor-fault detection and diagnostic system. There were 1001 sensor readings in the dataset; 112 were defective, while the remaining 888 were normal. The investigation showed that the suggested method, which detected faults with an accuracy of 95% and recall of 92%, achieved high accuracy and recall in recognizing defects in IoT and CPS. With significantly shorter processing times, the system’s potential to reduce computational strain on sensors was also proved. The findings of this study indicate that the suggested optimized sensor-fault detection and diagnosis system successfully detects faults in IoT and CPS with limited computation, memory, and energy resources. The system’s ability to reduce the computing burden on sensors while improving accuracy and recall makes it an appealing choice for industrial and commercial applications.

Optimizing Detection: Compact MobileNet Models for Precise Hall Sensor Fault Identification in BLDC Motor Drives

Optimizing Detection: Compact MobileNet Models for Precise Hall Sensor Fault Identification in BLDC Motor Drives

Wireless Sensor Networks Fault Detection and Identification

We have developed and experimentally tested a set of models for the detection and identification of sensor faults that commonly occur in wireless sensor networks. Considered faults include outlier, spike, variance, high-frequency noise, offset, gain, and drift faults. These faults affect the system operations and can endanger operators, final users, and the general public. The fault detection models are divided into two classes: data-centric models, which only analyze a single data stream, and system-centric models, which consider the overall system. For data-centric models, we use the magnitude, the gradient, and the variance of raw sensor data to model faults. For system-centric models, we introduce variogram-based techniques that allow faults to be detected by comparing readings from multiple sensors that measure related phenomena. For data-centric and system-centric sensor fault detection, we show how a few model parameters affect the sensitivity of wireless sensor network fault models. We present simulation and experimental results that illustrate the fault detection and identification models. The system is intended for health monitoring applications of the NASA Stennis Space Center (SSC) test stands and widely distributed support systems, including pressurized gas lines, propellant delivery systems, and water coolant lines. The testbed consists of Coremicro® reconfigurable embedded smart sensor nodes [29] capable of wireless communication, a network-capable application processor, a wireless base station, the software that supports sensor and actuator health monitoring, a database server, and a smartphone running a health monitoring Android application.

Sensor Fault Diagnosis, Isolation, and Accommodation for Heating, Ventilating, and Air Conditioning Systems Based on Soft Sensor

Heating, Ventilating, and Air Conditioning (HVAC) systems often suffer from unscheduled maintenance or abnormal shutdown due to the fault of their interior sensor system. Traditional fault diagnosis methods for HVAC sensor systems primarily focus on sensor fault diagnosis and isolation, lacking fault accommodation. Therefore, to realize effective sensor fault detection, identification, and accommodation (SFDIA), a method for HVAC SFDIA based on the soft sensor is proposed. First, a diagnosis soft sensor with multi-variable input is constructed to estimate the output of the physical sensor being diagnosed. The residual between the estimated value of the diagnosis soft sensor and the measurement of the physical sensor is used as an indicator of the sensor’s condition. If the residual exceeds the fault threshold, the sensor is diagnosed to be faulty. In order to maintain valid sensor output, an accommodation soft sensor is constructed using the historical normal value. The erroneous output of the faulty sensor is substituted by the estimated value from the accommodation soft sensor, thereby realizing sensor fault tolerance control. Experimental results demonstrate that the average false alarm rate for sensor fault diagnosis is 1.57% and the average fault diagnosis rate is 96.51%. The predictive mean absolute error (MAE) and root-mean-square error (RMSE) of the recovered soft sensors are 0.0525 and 0.0738, respectively. Thus, the soft sensors developed in this paper exhibit satisfying ability in HVAC SFDIA.

IoT-based expert system for fault detection in Japanese Plum leaf-turgor pressure WSN

Industry 4.0 involves the digital transformation of industrial sectors. Given the current climate change scenario and the scarcity of water in semi-arid regions, this digital transformation has to take into account the sustainable use of water. In agriculture, one of the most water-intensive sectors, to optimise the use of water, precision irrigation techniques are being applied. As a result of the digital transformation of agriculture, a key aspect for the application of these precision irrigation techniques, the crop water stress, can be predicted from a Wireless Sensor Network (WSN) of leaf-turgor pressure sensors. However, these sensors often fail, introducing errors in the data, which could lead to inaccurate application of precision irrigation techniques compromising crops and yields. So, sensor fault identification is a must. Nevertheless, sensor fault identification is a tedious and costly task that requires an expert to manually review all sensors and each of their measurements over the last 24 h. In this work, with the aim of digitally transforming this task, an IoT-based expert system is proposed. By means of a novel learning model, this system is capable of identifying sensor faults with 84.2% f1-score and 0.94 AUC ROC. Note that to train this learning model, only real-world data gathered from an experimental plot has been used. In addition, the real-world application of the IoT-based expert system in this plot is shown and discussed. Furthermore, a novel methodology that summarises the main findings and techniques applied in this study is also illustrated.

Output‐feedback fault‐tolerant tracking control for coupled 2 × 2 hyperbolic PDE systems with multiplicative sensor faults

AbstractThis paper proposes an output‐feedback fault‐tolerant tracking control scheme for coupled hyperbolic PDE systems with multiplicative sensor faults. In order to estimate the system states, an observer is designed by constructing four filters, which impose time delays to their input signals. For sensor fault identification problem, the gradient descent method is utilized based on a parametric model to estimate the fault parameter. With the filter‐based observer and the estimated fault parameters, a novel control strategy is proposed via backstepping design technique to achieve the tracking objective. Finally, the simulation studies are given to verify the tracking performance of the proposed fault‐tolerant tracking control scheme.

Real-Time Sensor Fault Identification and Remediation for Single-Phase Grid-Connected Converters Using Hybrid Observers With Unknown Input Adaptation

Unexpected faults that occur in the sensors of the single-phase grid-connected converter (SGC) may deteriorate the control performance ofthe grid current and dc-link voltage and pose risks to the connected distributed generation system. This article proposes an unknown input sliding mode observer (UI-SMO) based sensor fault identification and remediation strategy. Therein, an UI-SMO is established that integrates the observations of the grid current and dc-link voltage with the reconstruction of the unknown input (i.e., load condition of the SGC). Such an observer-based analytical redundancy generates the residuals that indicate the abnormalities of the sensors for fault identification. An adaptive fault-tolerant control (AFTC) strategy for the SGC is developed, where an automated control system reconfiguration with unknown input adaptation is seamlessly implemented by substituting the data reported by the faulty sensors with their observed values. Extensive simulation and experimental studies validate the effectiveness of the proposed UI-SMO-based sensor fault identification and AFTC strategy of the SGC.

Current Sensor Fault Localization and Identification of PMSM Drives Using Difference Operator

The permanent magnet synchronous motor (PMSM) has received increasing attention in traction applications. For those closed-loop control systems, the current sensor is one of the most sensitive components, which determines the control performance and safety operation. Therefore, the fault diagnosis of current sensors is of great importance to realize fault tolerance and further maintenance. In this work, a novel fault localization and identification method of the current sensor is proposed for PMSM drives. The residual between the measured current and estimated currents based on a modified <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha \beta $ </tex-math></inline-formula> reference frame is employed for the fault sensors’ localization. Besides, a second-order difference operator is adopted to identify the fault types. Moreover, a function is defined for preventing misdiagnosis, thus enhancing the algorithm’s robustness. The algorithm for the fault type identification would not be affected by the variation of motor parameters, granting it high flexibility to combine with not only the fault location algorithm in this article but also with other model-based methods. The effectiveness of the proposed approach is experimentally validated on an 11-kW platform of the PMSM fed by a three-level T-type inverter.

Rapid Sensor Fault Diagnosis for a Class of Nonlinear Systems via Deterministic Learning.

In this article, a rapid sensor fault diagnosis (SFD) method is presented for a class of nonlinear systems. First, by exploiting the linear adaptive observer technology and the deterministic learning method (DLM), an adaptive neural network (NN) observer is constructed to capture the information of the unknown sensor fault function. Second, when the NN input orbit is a period or recurrent one, the partial persistent excitation (PE) condition of the NNs can be guaranteed through the DLM. Based on the partial PE condition and the uniformly completely observable property of a linear time-varying system, the accurate state estimation and the sensor fault identification can be achieved by properly choosing the observer gain. Third, a bank of dynamical observers utilizing the experiential knowledge is constructed to achieve rapid SFD and data recovery. The attractions of the proposed approach are that accurate approximations of sensor faults can be achieved through the DLM, and the data that are destroyed by the sensor faults can be recovered by using the learning results. Simulation studies of a robot system are utilized to show the effectiveness of the proposed method.

Hi/H∞-optimised fault detection for a surface vessel integrated navigation system

AbstractStrapdown inertial navigation systems are widely used in surface ships and warships. Although high-precision optical fibre inertial navigation systems are available, they have high cost and limited practicality. Therefore, they cannot replace the traditional platform inertial navigation systems in all ships. Hence, microelectromechanical system (MEMS)-based inertial sensors are widely used for robust navigation. Accurate and timely identification of sensor faults while ensuring stable navigation is a challenging task. This paper proposes a robust fault detection (FD) approach for a low-cost system that loosely integrates a strapdown inertial navigation system and the global navigation satellite system, where the integrated navigation state estimation provides high-accuracy output. A cubature Hi/H∞-optimised FD filter was designed for a nonlinear discrete time-varying system considering sensitivity to faults and robustness to disturbances. Furthermore, a threshold for FD was derived considering a compromise between the false alarm rate and fault diagnosis accuracy. Finally, the proposed method was validated through simulations using multiple noise distribution sensor data generated by a ship-manoeuvring simulator.

Open-Switch and Current Sensor Fault Diagnosis Strategy for Matrix Converter-Based PMSM Drive System

Reliable fault diagnosis and identification are essential for permanent magnet synchronous motor (PMSM) drive systems with high-reliability requirements. Since open-switch fault and output current sensor fault both affect the residual of output phase current, it is difficult to identify them apart from each other. Thus, this article proposes an open-switch fault and output current sensor fault diagnosis and identification method for the matrix converter (MC)-based PMSM drive system. The finite control set-model predictive control (FCS-MPC) method is applied in the MC-based PMSM drive system. The fault identification method is proposed based on the extracted different faulty features of the open-switch fault and the output current sensor fault. After the open-switch fault is separated from the current sensor fault, an error-voltage-based open-switch fault diagnosis strategy is applied to locate the faulty switch. Hardware-in-the-loop tests are carried out to verify the effectiveness of the proposed method.

Sensor Fault Detection and Identification in an Electro-pump System using Extended Kalman Filter

In this article, the issue of sensor fault detection and identification with sensory information is considered. This is due to the dependence of successful Fult Detection (FD) method on correct sensory measurements that suffer from various soft sensory faults such as bias, drift, scaling factor, and hard faults that can be detected independently. They are not detectable but can be combined with other sensors. To solve this issue, firstly, a state space model for pump subsystem was constructed using the electrical simulation method. Then, the sensory soft faults are modeled and amplified to electro-pump state space model.&nbsp; Both system states and amplified sensory soft faults are then estimated using an Extended Kalman filter (EKF) in which nonlinear model of the induction motor is linearized around the estimated states. Information of current, angular velocity (encoder) and pressure sensors are &nbsp;melted for this goal. The efficiency of the method is firstly evaluated through simulation and then experimental results are provided from our laboratory setup. Measured volume currents, flow, and pressure are compared with simulated signals, and results show that the proposed model is able to successfully describe the laboratory system with good precision. These results show that the model can describe the electro-pump dynamic with good precision.

ESO-KELM-based minor sensor fault identification

ESO-KELM-based minor sensor fault identification

Establishment and optimization of sensor fault identification model based on classification and regression tree and particle swarm optimization

The accuracy of structural state evaluation may be affected by the damaged piezoelectric sensors. Therefore, it is necessary to identify the sensor fault during monitoring. This paper proposes a method based on classification and regression tree (CART) and particle swarm optimization (PSO) to improve the efficiency of potential feature sets selection for sensor fault classification and build an identification model with the best performance. Firstly, the signal features of three structural changes and four sensor faults were extracted with five indexes. Then the decision trees (DT) for sensor fault classification were built based on different index combinations whose performances were then evaluated by the designed fitness function. Finally, PSO was used to optimize the searching for the best index combination. The results show that compared with the exhaustive method, adopting PSO for DT optimization can greatly simplify the search process. When the particle population is 5 and 10, the fitness converges to the optimal solution after only 6 and 4 iterations respectively. Although the DT with the best fitness is trained with only two indexes, its accuracy is higher than those trained with more indexes and the classification accuracy of 64 samples reaches 98.4% which shows the feasibility and practicability of the method.

Sensor Fault Identification in Linear and Nonlinear Dynamic Systems via Sliding Mode Observers

The problem of sensor fault identification in technical sensory systems described by linear and nonlinear dynamic models is considered. To address the problem, sliding mode observers are used and cross-validated. The suggested approach for constructing sliding mode observers is based on the reduced order model of the initial system. This allows to reduce complexity of sliding mode observers and relax the limitations imposed on the initial system.

Active Fault Diagnosis Method for Vehicles in Platoon Formation

This paper presents an active fault diagnosis (AFD) method with reduced excitation for detection and identification of sensor faults of vehicles in a platoon formation. By introducing a probing signal into the platooning, it will allow an active excitation of the system, reveling a residual component, with the same frequency, that can be explored to obtain a fault identification of specific system faults. A supervisor is introduced to monitor the platoon behavior and activate the auxiliary input whenever the system natural excitation is insufficient for a clear fault diagnosis. This solution will allow the fault diagnosis to behave as active or passive through the adaptive signal provided by the supervisor. A dual Youla-Jabr-Bongiorno-Kucera (YJBK) matrix transfer function, also known as fault signature matrix (FSM) is investigated to get a fault diagnosis. In order to obtain an online identification of specific faults in the system, a Taylor approximation of the FSM is pursued. Computational simulations with a high-fidelity full-vehicle model, provided by CarSim , are carried out to demonstrate the effectiveness of the proposed active approach. A direct comparison between an active and a passive behavior in the same scenario shows that the active fault diagnosis method outperforms the passive approach whenever the dynamic behavior does not provide sufficient excitation. Furthermore, the excitation supervisor is able to significantly reduce the amount of artificial excitation introduced into the system ensuring a more energy efficient active fault diagnosis.

Sensor Fault Identification in Nonlinear Dynamic Systems

The problem of sensor fault identification in engineering systems described by nonlinear dynamic models is considered. To solve the problem, sliding mode observers are used. The feature of the suggested solution is using the reduced order model of the initial system to design sliding mode observer. This allows to obtain sliding mode observer of reduced dimension and extend a class of systems for which sliding mode observer can be constructed.

Anomaly Detection in Gas Turbine Time Series by Means of Bayesian Hierarchical Models

AbstractNowadays, gas turbines (GTs) are equipped with an increasing number of sensors, of which the acquired data are used for monitoring and diagnostic purposes. Therefore, anomaly detection in sensor time series is a crucial aspect for raw data cleaning, in order to identify accurate and reliable data. To this purpose, a novel methodology based on Bayesian hierarchical models (BHMs) is proposed in this paper. The final aim is the exploitation of information held by a pool of observations from redundant sensors as knowledge base to generate statistically consistent measurements according to input data. In this manner, it is possible to simulate a “virtual” healthy sensor, also known as digital twin, to be used for sensor fault identification. The capability of the novel methodology based on BHM is assessed by using field data with two types of implanted faults, i.e., spikes and bias faults. The analyses consider different numbers of faulty sensors within the pool and different fault magnitudes. In this manner, different levels of fault severity are investigated. The results demonstrate that the new approach is successful in most fault scenarios for both spike and bias faults and provide guidelines to tune the detection criterion based on the morphology of the available data.