Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers

The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults.In this paper,a deep learning-based observer,which combines the convolutional neural network(CNN)and the long short-term memory network(LSTM),is employed to approximate the nonlinear driving control system.CNN layers are introduced to extract dynamic features of the data,whereas LSTM layers perform time-sequential prediction of the target system.In terms of application,normal samples are fed into the observer to build an offline prediction model for the target system.The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs.Online fault detection can be realized by analyzing the residuals.Finally,an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme.Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.

Fault detection for nonlinear networked control systems based on fuzzy observer

Security and reliability must be focused on control sys- tems firstly, and fault detection and diagnosis （FDD） is the main theory and technology. Now, there are many positive results in FDD for linear networked control systems （LNCSs）, but nonlinear networked control systems （NNCSs） are less involved. Based on the T-S fuzzy-modeling theory, NNCSs are modeled and network random time-delays are changed into the unknown bounded uncertain part without changing its structure. Then a fuzzy state observer is designed and an observer-based fault detection approach for an NNCS is presented. The main results are given and the relative theories are proved in detail. Finally, some simulation results are given and demonstrate the proposed method is effective.

Robust fault detection for a class of nonlinear network control system with communication delay

To investigate a class of nonlinear network control system, a robust fault diagnosis method is presented based on the robust state observer. To access the objective that the designed robust filter is maximally tolerant to disturbances and sensitive to fault, the robustness and stability properties of the fault diagnosis scheme are established rigorously. Using the residual vector, a fault tolerant controller is established in order to guarantee the stability of the closed-loop system, and the controller law can be obtained by solving a set of linear matrix inequalities. Then, some relevant sufficient conditions for the existence of a solution are given by applying Lyapunov stability theory. Finally, a simulation example is performed to show the effectiveness of the proposed approach.

Fault detection and accommodation via neural network and variable structure control

This paper proposes a novel idea that classifies faults into two different kinds： serious faults and small faults, and treats them with different strategies respectively. A kind of artificial neural network （ANN） is proposed for detecting serious faults, and variable structure （VS） model-following control is constructed for accommodating small faults. The proposed framework takes both advantages of qualitative way and quantitative way of fault detection and accommodation. Moreover, the uncertainty case is investigated and the VS controller is modified. Simulation results of a remotely piloted aircraft with control actuator failures illustrate the performance of the developed algorithm.

Fault detection observer design for networked control system with long time-delays and data packet dropout

Focusing on the networked control system with long time-delays and data packet dropout,the problem of observerbased fault detection of the system is studied.According to conditions of data arrival of the controller,the state observers of the system are designed to detect faults when they occur in the system.When the system is normal,the observers system is modeled as an uncertain switched system.Based on the model,stability condition of the whole system is given.When conditions are satisfied,the system is asymptotically stable.When a fault occurs,the observers residual can change rapidly to detect the fault.A numerical example shows the effectiveness of the proposed method.

Fault detection and optimization for networked control systems with uncertain time-varying delay

The observer-based robust fault detection filter design and optimization for networked control systems （NOSs） with uncer- tain time-varying delays are addressed. The NCSs with uncertain time-varying delays are modeled as parameter-uncertain systems by the matrix theory. Based on the model, an observer-based residual generator is constructed and the sufficient condition for the existence of the desired fault detection filter is derived in terms of the linear matrix inequality. Furthermore, a time domain opti- mization approach is proposed to improve the performance of the fault detection system. To prevent the false alarms, a new thresh- old function is established, and the solution of the optimization problem is given by using the singular value decomposition （SVD） of the matrix. A numerical example is provided to illustrate the effectiveness of the proposed approach.

Fault detection based on H_∞ states observer for networked control systems

The influence of random short time-delay to networked control systems （NCS） is changed into an unknown bounded uncertain part. Without changing the structure of the system, an Hoo states observer is designed for NCS with short time-delay. Based on the designed states observer, a robust fault detection approach is proposed for NCS. In addition, an optimization method for the selection of the detection threshold is introduced for better tradeoff between the robustness and the sensitivity. Finally, some simulation results demonstrate that the presented states observer is robust and the fault detection for NCS is effective.

Fault Detection of Networked Control Systems Based on Optimal Robust Fault Detection Filter

有可能比一个采样时期大的随机、未知的导致网络的延期的联网的控制系统(NCS ) 的差错察觉在这份报纸被学习。首先，导致网络的延期引起的影响被转变成为错误建模组织，然后存在连续时间域基于引用，模型被扩大到分离时间领域并且适用指责联网的控制系统的察觉的柔韧的差错察觉方法。建议方法能被 Matlab LMI 工具箱容易实现，并且它的表演被一个模拟例子最后评估。

ASCS Online Fault Detection and Isolation Based on an Improved MPCA

Multi-way principal component analysis（MPCA）has received considerable attention and been widely used in process monitoring.A traditional MPCA algorithm unfolds multiple batches of historical data into a two-dimensional matrix and cut the matrix along the time axis to form subspaces.However,low efficiency of subspaces and difficult fault isolation are the common disadvantages for the principal component model.This paper presents a new subspace construction method based on kernel density estimation function that can effectively reduce the storage amount of the subspace information.The MPCA model and the knowledge base are built based on the new subspace.Then,fault detection and isolation with the squared prediction error（SPE）statistic and the Hotelling（T2）statistic are also realized in process monitoring.When a fault occurs,fault isolation based on the SPE statistic is achieved by residual contribution analysis of different variables.For fault isolation of subspace based on the T2 statistic,the relationship between the statistic indicator and state variables is constructed,and the constraint conditions are presented to check the validity of fault isolation.Then,to improve the robustness of fault isolation to unexpected disturbances,the statistic method is adopted to set the relation between single subspace and multiple subspaces to increase the corrective rate of fault isolation.Finally fault detection and isolation based on the improved MPCA is used to monitor the automatic shift control system（ASCS）to prove the correctness and effectiveness of the algorithm.The research proposes a new subspace construction method to reduce the required storage capacity and to prove the robustness of the principal component model,and sets the relationship between the state variables and fault detection indicators for fault isolation.

Fault detection for networked systems subject to access constraints and packet dropouts

This paper addresses the problem of fault detection（FD） for networked systems with access constraints and packet dropouts.Two independent Markov chains are used to describe the sequences of channels which are available for communication at an instant and the packet dropout process,respectively.Performance indexes H∞ and H_ are introduced to describe the robustness of residual against external disturbances and sensitivity of residual to faults,respectively.By using a mode-dependent fault detection filter（FDF） as residual generator,the addressed FD problem is converted into an auxiliary filter design problem with the above index constraints.A sufficient condition for the existence of the FDF is derived in terms of certain linear matrix inequalities（LMIs）.When these LMIs are feasible,the explicit expression of the desired FDF can also be characterized.A numerical example is exploited to show the usefulness of the proposed results.

H_∞-based fault detection for nonlinear networked systems with random packet dropout and probabilistic interval delay

The fault detection problem for the nonlinear networked control system （NCS） with packet dropout and delay is investigated. A nonlinear stochastic system model is proposed to account for the NCS with random packet dropout and network- induced non-uniformly distributed time-varying delay in both from sensor to controller （S/C） and from controller to actuator （C/A）. Based on the obtained NCS model, employing an observer-based fault detection filter as the residual generator, the addressed fault detection problem is converted into an auxiliary nonlinear H∞ control problem. Then, with the help of Lyapunov functional approach, a sufficient condition for the desired fault detection filter is constructed in terms of certain linear matrix inequalities, which depend on not only the delay interval but also the delay interval occurrence rate and successful packet communication rate. Especially, a trade-off phenomenon between the maximum allowable delay bound and successful data packet transmission rate is found, which is typically resulted from the limited bandwidth of communication networks. The effectiveness of the proposed method is demonstrated by a simulation example.

Coordinated Rotor-Side Control Strategy for Doubly-FedWind Turbine under Symmetrical and Asymmetrical Grid Faults

In order to solve the problems of rotor overvoltage,overcurrent and DC side voltage rise caused by grid voltage drops,a coordinated control strategy based on symmetrical and asymmetrical low voltage ride through of rotor side converter of the doubly-fed generator is proposed.When the power grid voltage drops symmetrically,the generator approximate equation under steady-state conditions is no longer applicable.Considering the dynamic process of stator current excitation,according to the change of stator flux and the depth of voltage drop,the system can dynamically provide reactive power support for parallel nodes and suppress the rise of DC side voltage and rotor over-current.When the grid voltage drops asymmetrically,the positive and negative sequence components are separated in the rotating coordinate system.The doubly fed generator model is established to suppress the rotor positive sequence current and negative sequence current respectively.At the same time,the output voltage limit of the converter is discussed,and the reference value is adjusted within the allowable output voltage range.In order to adapt to the occurrence of different types of power grid faults and complex operating conditions,a fast switching module of fault type detection and rotor control mode is designed to detect the type of power grid faults and voltage drop depth in real time and switch the rotor side control mode dynamically.Finally,the simulation model of the doubly fed wind turbine is constructed in Matlab/Simulink.The simulation results verify that the proposed control strategy can improve the low-voltage ride through performance of the system when dealing with the symmetrical and asymmetric voltage drop of the power grid and identify the power grid fault type and provide the correct control strategy.

An Intelligent Intrusion Detection System in Smart Grid Using PRNN Classifier

Typically,smart grid systems enhance the ability of conventional power system networks as it is vulnerable to several kinds of attacks.These vulnerabil-ities might cause the attackers or intruders to collapse the entire network system thus breaching the confidentiality and integrity of smart grid systems.Thus,for this purpose,Intrusion detection system(IDS)plays a pivotal part in offering a reliable and secured range of services in the smart grid framework.Several exist-ing approaches are there to detect the intrusions in smart grid framework,however they are utilizing an old dataset to detect anomaly thus resulting in reduced rate of detection accuracy in real-time and huge data sources.So as to overcome these limitations,the proposed technique is presented which employs both real-time raw data from the smart grid network and KDD99 dataset thus detecting anoma-lies in the smart grid network.In the grid side data acquisition,the power trans-mitted to the grid is checked and enhanced in terms of power quality by eradicating distortion in transmission lines.In this approach,power quality in the smart grid network is enhanced by rectifying the fault using a FACT device termed UPQC(Unified Power Quality Controller)and thereby storing the data in cloud storage.The data from smart grid cloud storage and KDD99 are pre-pro-cessed and are optimized using Improved Aquila Swarm Optimization(IASO)to extract optimal features.The probabilistic Recurrent Neural Network(PRNN)classifier is then employed for the prediction and classification of intrusions.At last,the performance is estimated and the outcomes are projected in terms of grid voltage,grid current,Total Harmonic Distortion(THD),voltage sag/swell,accu-racy,precision,recall,F-score,false acceptance rate(FAR),and detection rate of the classifier.The analysis is compared with existing techniques to validate the proposed model efficiency.

Event-triggered sampling and fault-tolerant control co-design based on fault diagnosis observer

A co-design scheme of event-triggered sampling mechanism and active fault tolerant control(FTC) is developed. Firstly,a fault diagnosis observer is designed to estimate both the fault and the state simultaneously by using the event-triggered sampled output. Some H∞constraints between the estimation errors and the event-triggered sampling mechanism are established to ensure the estimation accuracy. Then, based on the constraints and the obtained fault information, an event-triggered detector and a static fault tolerant controller are co-designed to guarantee the stability of the faulty system and to reduce the sensor communication cost.Furthermore, the problem of the event detector and dynamic FTC co-design is also investigated. Simulation results of an unstable batch reactor are finally provided to illustrate the effectiveness of the proposed method.

Unified control and detection framework and its applications: a review, some new results, and future perspectives

Initiated three decades ago,integrated design of controllers and fault detectors has continuously attracted research attention.The recent development of the unified control and detection framework with an observer-based residual generator in its core gives a more general form of the previous works.Its applications to residual centred modelling of uncertain control systems,fault detection in feedback control systems with uncertainties,fault-tolerant control(FTC)as well as control performance degradation monitoring,detection and recovery are introduced.In conclusion,some future perspectives are proposed.

Research on fault detection method for heat pump air conditioning system under cold weather

Building energy consumption accounts for nearly 40% of global energy consumption, HVAC(Heating, Ventilating,and Air Conditioning) systems are the major building energy consumers, and as one type of HVAC systems, the heat pump air conditioning system, which is more energy-efficient compared to the traditional air conditioning system, is being more widely used to save energy. However, in northern China, extreme climatic conditions increase the cooling and heating load of the heat pump air conditioning system and accelerate the aging of the equipment, and the sensor may detect drifted parameters owing to climate change. This non-linear drifted parameter increases the false alarm rate of the fault detection and the need for unnecessary troubleshooting.In order to overcome the impact of the device aging and the drifted parameter, a Kalman filter and SPC(statistical process control) fault detection method are introduced in this paper. In this method, the model parameter and its standard variance can be estimated by Kalman filter based on the gray model and the real-time data of the air conditioning system. Further, by using SPC to construct the dynamic control limits, false alarm rate is reduced.And this paper mainly focuses on the cold machine failure in the component failure and its soft fault detection.This approach has been tested on a simulation model of the "Sino-German Energy Conservation Demonstration Center" building heat pump air-conditioning system in Shenyang, China, and the results show that the Kalman filter and SPC fault detection method is simple and highly efficient with a low false alarm rate, and it can deal with the difficulties caused by the extreme environment and the non-linear influence of the parameters, and what's more, it provides a good foundation for dynamic fault diagnosis and fault prediction analysis.

A NEW PROBABILISTIC APPROACH FOR ESTIMATING FAULT DETECTION PROBABILITY

A new approach to calculate fault detection probabilities is presented. Fault-free simulation is used in the approach. The quantities of controllability and observability are defined as probabilities of controlling and observing the nodes in the circuit. The probability distribution of random signals on the circuit nodes is analyzed, and it is proved that controllability is in normal distribution. Thus the unbiasing estimation of the fault detection probability can be obtained. According to the concept of observability, we deal with the fan-out nodes. The fault coverages for actual circuits obtained from this approach agree favorably with the fault simulation results.

ToMFIR-based fault detection approach in frequency domain

This paper is to explore further results for total measurable fault information-based residual（ToMFIR） approach to fault detection in dynamic systems.The ToMFIR contains the essential fault information and remains unaffected by control actions in a closed-loop system.It is composed of controller residual and output residual and some of further results are developed in frequency domain.Besides the ability of detecting actuator and sensor faults,it is able to detect faults/failures resulting from the computer used for control purpose that generates control signals.Currently,all of existing fault detection schemes cannot achieve the same task at all.A practical DC motor example,with a PID controller,is used to demonstrate the effectiveness of the ToMFIR-based fault detection.A comparison with the standard observer-based technique is also provided.

Robust fault detection and diagnosis for uncertain nonlinear systems

This paper considers robust fault detection and diagnosis for input uncertain nonlinear systems. It proposes a multi-objective fault detection criterion so that the fault residual is sensitive to the fault but insensitive to the uncertainty as much as possible. Then the paper solves the proposed criterion by maximizing the smallest singular value of the transformation from faults to fault detection residuals while minimizing the largest singular value of the transformation from input uncertainty to the fault detection residuals. This method is applied to an aircraft which has a fault in the left elevator or rudder. The simulation results show the proposed method can detect the control surface failures rapidly and efficiently.