Identification Scheme Research Articles

Learning mean-field equations from particle data using WSINDy

We develop a weak-form sparse identification method for interacting particle systems (IPS) with the primary goals of reducing computational complexity for large particle number N and offering robustness to either intrinsic or extrinsic noise. In particular, we use concepts from mean-field theory of IPS in combination with the weak-form sparse identification of nonlinear dynamics algorithm (WSINDy) to provide a fast and reliable system identification scheme for recovering the governing stochastic differential equations for an IPS when the number of particles per experiment N is on the order of several thousands and the number of experiments M is less than 100. This is in contrast to existing work showing that system identification for N less than 100 and M on the order of several thousand is feasible using strong-form methods. We prove that under some standard regularity assumptions the scheme converges with rate O(N−1/2) in the ordinary least squares setting and we demonstrate the convergence rate numerically on several systems in one and two spatial dimensions. Our examples include a canonical problem from homogenization theory (as a first step towards learning coarse-grained models), the dynamics of an attractive–repulsive swarm, and the IPS description of the parabolic–elliptic Keller–Segel model for chemotaxis. Code is available at https://github.com/MathBioCU/WSINDy_IPS.

Intelligent Optical Performance Monitoring Based on Intensity and Differential-Phase Features for Digital Coherent Receivers

An intelligent optical performance monitoring scheme for simultaneous modulation format identification (MFI) and optical signal-to-noise ratio (OSNR) monitoring is proposed and experimentally demonstrated in digital coherent receivers. The proposed scheme introduces convolutional neural network (CNN) to automatically extract and monitor modulation format and OSNR dependent features (the empirical distribution of intensity and differential-phase) which can be obtained after constant modulus algorithm (CMA) equalization. The experiment results show that 100% identification accuracies for all modulation formats (e.g. 28-GBaud PDM-QPSK/−8PSK/ −8QAM/−16QAM/−32QAM/−64QAM) are achieved at OSNR values are lower than the corresponding theoretical 20% FEC limit (BER = 2.4×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−2</sup> ). Furthermore, under the chromatic dispersion (CD) variation from 0-ps/nm to 1200-ps/nm, the root-mean- square error (RMSE) and mean absolute error (MAE) of OSNR monitoring for all modulation formats are less than 0.0896-dB and 0.0657-dB, respectively. Subsequently, the influence of frequency offset and fiber nonlinearity effect on the intelligent optical performance monitoring scheme is also analyzed. We believe that our proposed multi-parameter monitoring scheme has the potential to be applied in the next-generation intelligent elastic optical networks.

Multi-agent cooperative structural vibration control of three coupled flexible beams based on value decomposition network

Multi-coupled flexible body (MCFB) structure has the characteristics of small damping, close modes and coupled vibration, and the structural vibration is difficult to freely attenuate, which will lead to rapid fatigue failure of the structure. In order to suppress the vibration of the MCFB system quickly, a system identification scheme and a multi-agent reinforcement learning (MARL) scheme are proposed to obtain the cooperative controller. The mathematical model of the three-coupled flexible beam (TCFB) system is identified by wavelet analysis method, particle swarm optimization (PSO) and sinusoidal excitation response method. Based on value decomposition network (VDN) and deterministic policy gradient (DPG), a cooperative MARL framework is constructed to obtain the controller (VDN-DPG controller). The cooperative VDN-DPG controller is applied to the vibration control simulation and experiments of the TCFB system, and compared with proportional–derivative (PD) control without cooperation. The results show that the performance of the VDN-DPG controller is better than that of the PD controller, which verifies the effectiveness of the multi-agent cooperative control scheme based on VDN-DPG.

B-Spline Neural Network Assisted Space-Time Equalization for Single-Carrier Multiuser Nonlinear Frequency-Selective MIMO Uplink

This paper designs a nonlinear space-time equalizer based on B-spline neural network (BSNN) for the singlecarrier high-throughput multiuser frequency-selective multipleinput multiple-output (MIMO) nonlinear uplink. Specifically, based on a BSNN parametrization of the nonlinear high power amplifiers (NHPAs) at mobile terminals’ transmitters, a novel nonlinear identification scheme is developed to estimate the nonlinear dispersive MIMO uplink channel, which includes the BSNN models for the NHPAs at transmitters as well as the frequency-selective MIMO channel impulse response (CIR) matrix. Furthermore, the BSNN inverse models of the NHPAs are also estimated in closed-form. This allows the base station to implement nonlinear multiuser detection effectively using the space-time equalization (STE) based on the estimated frequencyselective MIMO CIR matrix and followed by compensating for the nonlinear distortion of the transmitters’ NHPAs based on the estimated BSNN inverse models. Simulation results are utilized to demonstrate the superior bit error rate performance of our nonlinear STE approach for single-carrier highthroughput multiuser nonlinear frequency-selective MIMO uplink.

Guided waves-based damage identification in plates through an inverse Bayesian process

The use of guided waves to identify damage has become a popular method due to its robustness and fast execution, as well as the advantage of being able to inspect large areas and detect minor structural defects. When a travelling wave on a plate interacts with a defect, it generates a scattered field that will depend on the defects geometry. By analysing the scattered field, one can thus characterize the type and size of the plate damage. A Bayesian framework based on a guided waves interaction model for damage identification of infinite plate for the first time is presented here. A semi-analytical approach based on the lowest order plate theories is adopted to obtain the scattering features for damage geometries with circular symmetry, resulting in an efficient inversion procedure. Subsequently, ultrasound experiments are performed on a large aluminium plate with a circular indentation to generate wave reflection and transmission coefficients. With the aid of signal processing techniques, the effectiveness and efficiency of the proposed approach are verified. A full finite element model is used to test the damage identification scheme. Finally, the scattering coefficients are reconstructed, reliably matching the experimental results. The framework supports digital twin technology of structural health monitoring.

Gravity-Law Based Critical Bots Identification in Large-Scale Heterogeneous Bot Infection Network

The explosive growth of botnets has posed an unprecedented potent threat to the internet. It calls for more efficient ways to screen influential bots, and thus precisely bring the whole botnet down beforehand. In this paper, we propose a gravity-based critical bots identification scheme to assess the influence of bots in a large-scale botnet infection. Specifically, we first model the propagation of the botnet as a Heterogeneous Bot Infection Network (HBIN). An improved SEIR model is embedded into HBIN to extract both heterogeneous spatial and temporal dependencies. Within built-up HBIN, we elaborate a gravity-based influential bots identification algorithm where intrinsic influence and infection diffusion influence are specifically designed to disclose significant bots traits. Experimental results based on large-scale sample collections from the implemented prototype system demonstrate the promising performance of our scheme, comparing it with other state-of-the-art baselines.

Fast Low Frequency Fault Location and Section Identification Scheme for VSC-Based Multi-Terminal HVDC Systems

Penetration of DC networks is rapidly increasing in modern power systems. As transient behavior of DC grids is different from that of AC ones, AC grid protection schemes might not be applicable to protect DC networks. Exact fault location is vital for protection of DC networks to reduce repair cost and achieve fast power recovery. This paper proposes a novel topology independent multi-terminal DC scheme to identify fault section and location for DC transmission systems. Voltage and current signals measured at the terminals are analyzed by the least squares error (LSE) algorithm. Then, the proposed scheme uses low frequency components of the signals to locate DC faults offline. Unlike some other methods, it does not require sophisticated sensors and hardware to capture very high frequency content of the signals. Hence, the proposed scheme can be implemented in practice without additional measuring infrastructure. The performance of the proposed scheme is evaluated under various fault conditions for different topologies of DC networks in both overhead lines and cables. Numerous simulations carried out demonstrate that the proposed scheme is quite accurate and provides excellent performance under different fault resistances, sections, and locations.

Analysis of the effects of fiscal policy shocks in the Baltic region

The study aims to compare the effects of fiscal policy shocks in three Baltic countries – Estonia, Latvia, and Lithuania - within SVAR framework, using the identification scheme proposed by Blanchard and Perotti (2002). The time sample covers quarterly data over the period of 2002q1-2019q4. The main idea of the study is to identify the effects of fiscal policy shocks in three euro area member states under a single monetary policy of the European Central Bank, but with country-specific fiscal policy shaped by the European fiscal framework. The results show that, generally, in the short term (up to four quarters), output reacts consistently with the Keynesian view, emphasizing the importance of using discretionary fiscal policy tools in stimulating economic activity in the Baltic region. However, in Estonia and Latvia, the calculated impact multipliers for net taxes are larger than spending multipliers. Although each country reacts differently to its country-specific fiscal shock, the response to the euro area money market interest rate innovation is quite similar with respect to the direction of the effect, which may indicate the robustness of the Baltic region in terms of the euro area shocks. Thus, the results emphasize the importance of conducting domestic fiscal policy adapted to the conditions of each of the analysed economies. Based on the assumptions and the methodology used in this study, the obtained findings show the limited effects of spending on Baltic economies in comparison with the effects caused by the shocks in net taxes. Moreover, due to the lack of large-scale analysis regarding the effectiveness of fiscal policy in Baltic states, the obtained results are a valuable contribution to the debate about the ‘appropriate’ size of the fiscal multipliers for the Baltic region.

Threat of Adversarial Attacks on DL-Based IoT Device Identification

With the rapid development of the information technology, the number of devices in the Internet of Things (IoT) is increasing explosively, which makes device identification a great challenge. Deep neural networks (DNNs) have been used for device identification in IoT due to their superior learning ability. However, DNNs are susceptible to adversarial attacks, which can greatly degrade the accuracy of deep learning (DL) models for device identification. The adversarial attack is one of the fundamental security concerns for DNNs, and it is of great importance to study the generation of adversarial examples and to examine the attack effects for the design of robust DNN-based device identification schemes. In this article, we examine the effects of nontargeted and targeted adversarial attacks on convolutional neural network (CNN)-based device identification and propose combined evaluation indicators of logits to enrich the evaluation criteria. Our experimental results demonstrate that the identification accuracy degrades with the increase of the perturbation level and iteration step size, and the proposed combined evaluation indicators are effective to show the individual device signal differences. The insights from this study will be useful for the design of robust DL-based IoT systems.

Robust Optimal Power Flow under Renewable Uncertainty with Pairwise Convex Hull and Non-Affine AGC Redispatch Strategy

To accommodate the intermittent and uncertain renewable energy resources (RESs) in the power system, a novel robust optimal power flow (ROPF) method under RES uncertainty is proposed in this paper. A novel convex set, the pairwise convex hull, is applied to characterize the RES uncertainty. Then, an adjustable ROPF model is built to integrate RESs, where non-affine re-dispatch constraints are designed to cope with the situation when the automatic generation control (AGC) units’ power outputs hit their lower or upper bound during the re-dispatch process. The resulting ROPF problem is then solved with an adversarial approach (constraint generation) in which the potential binding constraints are identified to speed up the calculation. By solving the proposed ROPF model, the base point can be obtained to not only serve the forecasted load, but also ensure a feasible solution for all realizations of RES outputs within the pre-defined uncertainty set. Numerical studies on the 39-bus and 500-bus systems show that the proposed pairwise convex hull can capture the complicated distribution of RES outputs and is computationally very efficient. The binding constraint identification scheme can further dramatically speed up the computation. In addition, the non-affine AGC power re-dispatch scheme can achieve a lower objective value, for example, the proposed non-affine AGC re-dispatch-based ROPF method saves 0.389% and 0.1665% of the total costs for the 39-bus and 500-bus systems.

An integrated condition monitoring scheme for health state identification of a multi-stage gearbox through Hurst exponent estimates

The vibration and acoustic signals collected from rotating machinery are often non-stationary and aperiodic, and it is a challenge to post-process and extract the defect sensitive health indicators. In this paper, we demonstrate how the estimated Hurst exponent of such measured data can be advantageous for analyzing non-stationary and aperiodic data due to its self-similarity and scale-invariance properties. To illustrate this, the paper demonstrates detection of fault diagnostics of a multi-stage gearbox operating under fluctuating speeds through estimated Hurst exponent of the raw vibration and acoustic signals as a health indicator. Thirteen health states of the gearbox are considered, and the raw vibration and acoustic signals are collected. The Hurst exponents are calculated using three different approaches: generalized Hurst exponent (q = 1, 2, 3, and 4), rescale range statistical (R/S) analysis, and dispersion analysis from the vibration and acoustic signals. Three different health indicator datasets are formulated and subjected to feature learning through conventional machine-learning (decision tree and support vector machine) and advanced machine-learning (deep-learning) classifiers. The effectiveness of these datasets while discriminating between the health states of the gearbox is investigated, yielding classification accuracies of 96.4% when compared with the individual health indicator datasets. The ability of the fault diagnosis and defect severity analysis with reduced reliance on the signal post-processing algorithms is demonstrated.

Threshold-free localized scheme for DC fault identification in multiterminal HVDC systems

In the future grid scenario, the continuous operation of large-capacity remote power transmission over an augmented DC network is imperative for implementing a reliable multi-terminal high voltage direct current (MT-HVDC) grid or, alternatively, an MTDC grid. A fast and selective DC fault identification method with improved reliability eventually enhances the operational continuity and flexibility of the MTDC grid. Based on the V/I ratio of a current limiting reactor, this paper proposes a new non-unit protection scheme for DC fault identification without a threshold value setting. The DC fault is precisely identified in a span of three sampling intervals by the V/I ratios of four sampling instants. The selectivity of the proposed scheme is verified in a four-terminal MTDC grid. Simulation results demonstrate that the effective detection, discrimination, and location of a DC fault strictly satisfies the speed requirement (<1ms) with a location error of less than 1%. Moreover, the relevant sensitivity analyses reveal that the proposed scheme remains invariant for a wide range of fault locations and resistances and perform efficiently, even with a lower sampling frequency. In addition, transient events apart from DC faults fail to trigger the protection, indicating the high robustness of the proposed scheme.

Defect Identification of Concrete Piles Based on Numerical Simulation and Convolutional Neural Network

Defects in pile foundations, such as neck defects, bulge imperfections, weak concretes, cracks, and broken piles, can cause a decrease in the bearing capacity and the structural stability of the foundation. Identification of the type of defect is vital in formulating a reasonable repair plan for the pile foundation. In this study, the authors proposed a scheme to identify the types of defects in concrete piles based on a convolution neural network and a low-strain pile integrity test (LSPIT). A batch modeling method of defective pile foundations using Python script was also proffered. The different degrees of signals of five types of defective pile foundations were simulated by this method. The original data were decomposed and reconstructed by wavelet packet decomposition (WPT). To prevent the data from losing too much information after WPT, the data of 400 × 1 after decomposition and reconstruction were processed by dimension-raising to obtain the data of 20 × 20 × 1. Then, the multidimensional feature index of 20 × 20 × 2 was generated by index fusion with the original data. Finally, the data were input onto convolutional neural network (CNN) as a training parameter. Following an improvement of the dataset, the recognition accuracy of the type of defect in the pile foundation by the proposed identification scheme reached 94.4%.

Self‐tuning regulator adaptive controller design for DC‐DC boost converter with a novel robust improved identification method

The design of a self-tuning regulator adaptive controller is presented for Boost converter using Pulse Width Modulation, which has been improved in dynamic with a novel Robust Improved Exponential Regressive Least Square identification scheme. Regarding the negative influences of harmful disturbances on the converters, the Minimum Degree Pole Placement technique is designed using an adaptive mechanism with an online identification technique, which is simple in structure and can provide more accurate parametric estimation and better efficiency in challenging situations, particularly against noise. Based on the right half-plane zero structure of the Boost converter, the open-loop system is called a non-minimum phase system which creates some challenging constraints for the controller design. The primary objective of designing a feedback loop controller is to ensure the stability of the system and appropriate regulation within a pre-determined range of operating conditions. This controller considers the system as a black-box structure; thus, the mathematical model of the system is not needed. This benefit can decrease the computational burden, and provides faster dynamics along with ease of implementation. Finally, the strength of this control strategy is tested by experimental and simulation results in different conditions.

OpenCBD: A Network-Encrypted Unknown Traffic Identification Scheme Based on Open-Set Recognition

The encryption of network traffic promotes the development of encrypted traffic classification and identification research. However, many existing studies are only effective for closed-set experimental data, that is to say, only for traffic of known classes, while there are often lots of unknown classes traffic in the real environment of open sets, and many studies have difficulty identifying the traffic of unknown classes and can only misclassify them as known classes. How to identify unknown traffic and classify known traffic in an open-collection environment is one of the focuses of traffic analysis research. Considering these problems, this paper proposes a novel solution, which applies the open-set recognition method to the unknown traffic identification, and constructs a model based on deep learning and ensemble learning. The method constructs a model based on a convolutional neural network and a transformer encoder and then uses a three-stage training and testing process, combined with a novel loss function, to generalize to the open space to form OpenCBD. Experiments on public datasets show that the proposed method is significantly better than other open-set identification methods. It can not only distinguish known traffic from unknown traffic but also identify specific classes of known traffic.

Wielerella bovis gen. nov., sp. nov. a member of the family Neisseriaceae associated with bovine endocarditis.

Seven bacterial strains isolated from bovine endocarditis in six animals from different geographic regions were investigated in a polyphasic taxonomic approach. Phylogenetic analysis based on 16S rRNA gene sequences placed all seven isolates on a distinct, monophyletic cluster in the family Neisseriaceae with closest similarity to type strains of Alysiella filiformis (97.06 %) and Kingella kingae (96.34 %). Whole genome sequence analysis of isolates confirmed their species status, with an average nucleotide identity >96 % between isolates and <80 % to other type species of genera of Neisseriaceae while digital DNA-DNA hybridization values were >80 % and<18 %, respectively. The DNA G+C content was 42.5-43.0 mol%. Whole genome sequence based phylogeny showed the isolates being monophyletic and separated from established genera, thereby forming a new genus within the family Neisseriaceae. Similarly, analysis of MALDI-TOF MS reference spectra clustered the isolates close together and clearly separated from other genera, making this the method of choice for identification. Biochemical markers based on classical as well as commercial identification schemes allowed separation from closely related Neisseriaceae genera, even though the new taxon is biochemically not very active. Major fatty acids are C12 : 0, C14 : 0 and C16 : 0. The major quinone is ubiquinone Q-8. In the polar lipid profile, diphosphatidylglycerol, phosphatidylglycerol, phosphatidylethanolamine and phospholipid were predominant. We propose the novel genus Wielerella with the type species Wielerella bovis gen. nov., sp. nov. The type strain is CCUG 44465T (=DSM 113289T=JF 2483T) isolated post mortem from a cow with endocarditis in Switzerland.

Intrusion identification using GMM-HMM for perimeter monitoring based on ultra-weak FBG arrays.

Intrusion identification has been an intractable task for perimeter security. One of the primary challenges is to possess high identification rate over a long-distance range monitoring. This paper proposes an intrusion identification scheme based on ultra-weak fiber Bragg grating (UWFBG) arrays. The scheme is acquired by the combination of a Gaussian mixture model (GMM) and a hidden Markov model (HMM). The time dependencies are obtained by the analysis of relevant sensors in UWFBG arrays from the procedure of intrusions. The features extracted from vibration signals with time dependencies are used as the input of GMM-HMM. The GMM-HMM simultaneously analyzes features and time dependencies to identify intrusion. Experimental demonstration verifies that the proposed scheme can identify three intrusions (walking, knocking and climbing) and two non-intrusions (heavy truck passing and wind blowing) with the average identification rate of 98.2%. By the comparison tests with other six classifiers, the proposed GMM-HMM scheme shows a solid performance in the integrated evaluation for intrusion identification.

Reliable control strategy based on sliding mode observer against FDI attacks in smart grid

AbstractThis paper is concerned with the reliable operation of cyber‐physical systems under false data injection attacks. First of all, a robust adaptive sliding mode observer is designed to estimate the state of the power system; different from the traditional sliding mode observer, the observer we designed is not only robust to state errors but also can automatically adjust the parameter of attack identification. Secondly, a method of attack reconstruction has been given to estimate the actual attack signal. Finally, a reliable sliding mode control strategy is proposed to eliminate the impact of false data injection attacks; compared with the existing results, the designed defense strategy utilizes the reconstructed attack signal in the attack identification scheme and state error signal at the same time. Moreover, a power system with 3 generator buses and 6 load buses is taken as an simulation example to verify the availability of the proposed control strategy.

A Distributionally Robust Scheme for Critical Component Identification to Bolster Cyber-Physical Resilience of Power Systems

With the increasing risks of malicious cyber-physical attacks and natural disasters, it is urged for power grids to improve the resilience performance against such high-impact, low-frequency events. The critical component identification is an important problem for the effective planning, operation and asset management of power systems. Thus, it is highly necessary and beneficial to develop a resilience oriented critical component identification method for defending power systems against extreme events. In this paper, a tri-level optimization model is developed to identify the critical components while the coordinated cyber-physical attacks on power systems are formulated considering the resources of attackers, the optimal attack strategy, and the actions of the system operator to enhance the system resilience against potential attacks. Meanwhile, a distributionally robust optimization (DRO) based model is proposed to consider the impacts of distribution uncertainty of the resource or ability of the malicious attackers in the criticality identification framework. A constraint-generation based algorithm is developed to solve the overall multi-level DRO model with a master and sub-problem scheme. Further, a criticality index is proposed to quantify the importance of key components to the system resilience against malicious cyber-physical attacks. In order to validate the proposed method, case studies were conducted on the IEEE reliability test system (RTS-79). The obtained results show that the proposed critical component identification method can provide effective and robust importance evaluation of system components to bolster the grid resilience against potential cyber-physical threats.

An Artificial Radio Frequency Fingerprint Embedding Scheme for Device Identification

Radio frequency fingerprint (RFF) is an intrinsic physical characteristic of the device caused by hardware imperfection. It can be extracted from wireless signals and has been widely applied for device identification. However, the improving precision of electronic components reduces the distinguishability of RFF, which makes it difficult to identify large amount of devices that are of the same model, especially in a low signal-to-noise ratio (SNR) scenario. In this letter, we propose an artificial radio frequency fingerprint (ARFF) embedding scheme for device identification, which greatly increases the distinguishability of fingerprints and minimally affects the performance of communication. The scheme includes an adaptive filter based RFF extraction method, a principal component analysis (PCA) based ARFF generation algorithm and a proposed ARFF embedding algorithm that eliminates the influence of the device’s original RFF to form a preset ARFF pattern. Experimental results on ZigBee devices demonstrate that our ARFF based scheme achieves 99.91% identification accuracy and simultaneously has little impact on bit error rate.