Data-based Scheme Research Articles

Assessing Electrode Characteristics in Continuous Resistance Spot Welding of BH 340 Steel Based on Dynamic Resistance

The aim of this investigation is to offer a data-based scheme for predicting electrode wear in resistance spot welding. One of the major factors affecting the mechanical properties of spot welds and the variation in weld quality is electrode wear and alloying. In this study, Rogowski coils and twisted pairs attached to the top and bottom electrodes were used to obtain the welding current and the voltage between the electrodes in the welding process, thereby calculating the dynamic resistance value during the welding process. The electrode tip diameter was obtained from the pressure exerted by the upper and lower electrodes on the carbon paper when the current was cut off and was regarded as an indicator of electrode wear. By continuously welding 0.5 mm thick BH 340 steel plates until the electrode failed, the dynamic resistance signal was recorded in real time. Simultaneously, the electrode diameter after every several welds was also recorded. On this basis, the correlation between electrode tip diameter and dynamic resistance is studied. In order to quantitatively study the mapping relationship between dynamic resistance and electrode wear, 10 characteristic values were extracted from the dynamic resistance, and the stepwise regression method was used to obtain the regression formula between the characteristic values and the electrode tip diameter. Using new data to verify the effectiveness of the regression model, the acquired results display that the maximum error between the predicted value of the electrode tip diameter and the measured value obtained by the regression equation with the interactive quadratic term is 0.3 mm, and the corresponding relative error is 7.69%. When welding with a new pair of electrodes, the maximum absolute error was 0.72 mm, and the relative error of the model prediction is within 20% according to the linear regression model with interaction terms. This indicates that this regression model is barely satisfactory for monitoring electrode condition.

A data-based fault detection scheme for the stratospheric airship control system

This brief proposed an innovative fault detection method based on analytical data for the stratospheric airship control system. The control system considered is subject to both space disturbance and nonlinear characteristics; the faults of sensors and actuators are all taken into account. The proposed method is developed in two phases. In the first phase, the moving window kernel principal component analysis is employed to construct the fault detection model with the training data under normal operating conditions and update the fault detection model online until abnormal data are detected. Second, a fault detection model updating mechanism is designed to reduce computational complexity and cost with a clustering algorithm, which compounds the mean shift clustering with weighted Euclidean distance to reflect the data density distribution feature to make the updating to be adaptive. Finally, the proposed method is applied to detect fault for an illustrative simulation stratospheric airship control model. The fault detection results validate the effectiveness of proposed fault detection method for different sensor and actuator fault cases. Comparing to some extended moving window kernel principal component analysis method, the proposed method reduces the computational cost significantly.

Hybrid Reinforcement Learning for Optimal Control of Non-Linear Switching System.

Based on the reinforcement learning mechanism, a data-based scheme is proposed to address the optimal control problem of discrete-time non-linear switching systems. In contrast to conventional systems, in the switching systems, the control signal consists of the active mode (discrete) and the control inputs (continuous). First, the Hamilton-Jacobi-Bellman equation of the hybrid action space is derived, and a two-stage value iteration method is proposed to learn the optimal solution. In addition, a neural network structure is designed by decomposing the Q-function into the value function and the normalized advantage value function, which is quadratic with respect to the continuous control of subsystems. In this way, the Q-function and the continuous policy can be simultaneously updated at each iteration step so that the training of hybrid policies is simplified to a one-step manner. Moreover, the convergence analysis of the proposed algorithm with consideration of approximation error is provided. Finally, the algorithm is applied evaluated on three different simulation examples. Compared to the related work, the results demonstrate the potential of our method.

Nonequilibrium Self-Assembly Time Forecasting by the Stochastic Landscape Method.

Many biological systems rely on the ability to self-assemble target structures from different molecular building blocks using nonequilibrium drives, stemming, for example, from chemical potential gradients. The complex interactions between the different components give rise to a rugged energy landscape with a plethora of local minima on the dynamic pathway to the target assembly. Exploring a toy physical model of multicomponents nonequilibrium self-assembly, we demonstrate that a segmented description of the system dynamics can be used to provide predictions of the first assembly times. We show that for a wide range of values of the nonequilibrium drive, a log-normal distribution emerges for the first assembly time statistics. Based on data segmentation by a Bayesian estimator of abrupt changes (BEAST), we further present a general data-based algorithmic scheme, namely, the stochastic landscape method (SLM), for assembly time predictions. We demonstrate that this scheme can be implemented for the first assembly time forecast during a nonequilibrium self-assembly process, with improved prediction power compared to a naïve guess based on the mean remaining time to the first assembly. Our results can be used to establish a general quantitative framework for nonequilibrium systems and to improve control protocols of nonequilibrium self-assembly processes.

Research on key technologies for connected vehicle autonomous driving based on 5G big data

Abstract In recent years, with the improvement of computers, automation, and communication technologies, autonomous driving has developed rapidly and has become a research hotspot in transportation. In order to optimize the existing autonomous driving scheme, this paper investigates the key technologies in 5G-based Telematics autonomous driving, mainly including the millimeter wave communication method and automatic obstacle avoidance strategy design, and tests and analyzes them through simulation experiments. In the simulation experiment, the synchronization rate of rear vehicle 1 of lane X 1 is 97.56%, that of rear vehicle X 2 is 98.43%, and that of rear vehicle X 3 is 97.82%, with an average synchronization rate of 97.94%. The synchronization rates of rear vehicle Y 1, Y 2 and Y 3 of lane 2 are 98.27%, 97.84%, and 96.89%, respectively, with an average synchronization rate of 97.67%. For the local observation latency in Telematics, the 5G Big Data-based scheme reduces 10.22% on average compared to the F-DDQL scheme and 9.76% on average compared to the IF-DDQL scheme. Regarding system latency, the 5G Big Data-based scheme reduces 8.67% and 9.21% on average compared to the other two schemes, respectively. The 5G Big Data-based Telematics autopilot can significantly improve the synchronization rate of vehicles and effectively reduce network latency. The research on the key technologies of 5G big data-based connected vehicle autonomous driving in this paper can overcome the shortcomings of traditional autonomous driving technology with unstable networking and help reduce the reliance on high-precision sensors, thus further improving autonomous driving performance.

A Lightweight, Secure Big Data-Based Authentication and Key-Agreement Scheme for IoT with Revocability

With the rapid development of Internet of Things (IoT), designing a secure two-factor authentication scheme for IoT is becoming increasingly demanding. Two-factor protocols are deployed to achieve a higher security level than single-factor protocols. Given the resource constraints of IoT devices, other factors such as biometrics are ruled out as additional authentication factors due to their large overhead. Smart cards are also prone to side-channel attacks. Therefore, historical big data have gained interest recently as a novel authentication factor in IoT. In this paper, we show that existing big data-based schemes fail to achieve their claimed security properties such as perfect forward secrecy (PFS), key compromise impersonation (KCI) resilience, and server compromise impersonation (SCI) resilience. Assuming a real strong attacker rather than a weak one, we show that previous schemes not only fail to provide KCI and SCI but also do not provide real two-factor security and revocability and suffer inside attack. Then, we propose our novel scheme which can indeed provide real two-factor security, PFS, KCI, and inside attack resilience and revocability of the client. Furthermore, our performance analysis shows that our scheme has reduced modular exponentiation operation and multiplication for both the client and the server compared to Liu et al.’s scheme which reduces the execution time by one third for security levels of λ = 128 . Moreover, in order to cope with the potential threat of quantum computers, we suggest using lightweight XMSS signature schemes which provide the desired security properties with λ = 128 bit postquantum security. Finally, we prove the security of our proposed scheme formally using both the real-or-random model and the ProVerif analysis tool.

An integrated CRN-SVR approach for the quality consistency improvement in a diesel engine assembly process

ABSTRACT As the last production link, the diesel engine assembly process (DEAP) significantly impacts the quality consistency of diesel engine products. Therefore, the quality consistency improvement of DEAP has become an urgent problem for academia and industry. The challenge is how to mine the causal relationship in DEAP and establish a reliable quality prediction model. This paper attempts to describe DEAP using a causal relationship network (CRN) and to provide an effective data-based scheme for improving quality consistency by integrating CRN with support vector regression (SVR). First, a two-step CRN learning method is proposed for describing the DEAP. In the first step, the association relationship network is developed by a hybrid direct association detection method of the maximal information coefficient and network deconvolution, which can accurately measure the data relations. In the second step, the information geometric causal inference is employed to determine the direction of the edges in the association relationship network, thus forming the CRN of DEAP. Then, an integrated CRN-SVR approach is proposed to realize the predictive modeling of the critical quality indicators in DEAP, which integrated SVR into CRN. At the same time, it also provides a feasible idea for the interpretability of existing machine learning techniques. Finally, the proposed approach is tested and verified in a real-world DEAP and the obtained RMSE is only 0.033. The results of this study provide theoretical support and technical guarantee for quality consistency improvement in DEAP.

Data-based [formula omitted]gain optimal control for discrete-time system with unknown dynamics

This paper considers the L2gain optimal problem for a class of discrete-time linear time-invariant with state-disturbance feedback controller and unknown system dynamic. Firstly, for a given stabilizing control policy, we establish the relation between the L2gain and a sequence of lower triangle Toeplitz matrices. Meanwhile, we show that the upper bound of optimal L2gain is proportional to the linear correlation degree between the input and disturbance matrices. Secondly, to overcome the obstacle arising from the unknown system dynamics, a data-based reinforcement learning scheme is developed for the optimal control policy by using linear matrix inequality technique and Q-learning with policy iteration. Under certain conditions, we prove that either the reinforcement learning process ends in a finite number of iterations, or the L2gain sequence is strictly monotonically convergent along the iteration axis provided that the disturbance data set can fully activate the closed-loop system. Finally, simulations are given to illustrate the effectiveness of our findings.

Design and Implementation of Protocol Conversion of Intelligent Power Distribution Equipment for New Power System

A protocol conversion method of intelligent distribution equipment for a new power system is proposed to aim at the problems of short data reading distance and high data packet loss rate in the current protocol conversion process of intelligent distribution equipment. The protocol conversion process of the equipment is divided into two parts, the uplink channel, and the downlink channel. The multi-protocol conversion process of the intelligent distribution equipment is designed. A data-based protocol conversion scheme is set up to realize the bidirectional conversion of the protocol. The original protocol conversion gateway is replaced by the CAN-PROFINET protocol conversion gateway to control the network message throughput and realize the protocol conversion of the intelligent power distribution equipment. The experimental results show that the method can effectively extend the data reading distance and reduce the data packet loss rate to a certain extent, which provides a new development direction for the new power system network control technology.

Optical scheme of developing Hamming code-based error detection and correction using Toffoli gates with frequency encoded data

Bit-error detection and correction is a very important part of a data communication network. In this article, we propose an optical approach to designing an error detection and correction circuit using Hamming code-based frequency encoded binary data and Toffoli gates. Here, the Toffoli gates are made of semiconductor optical amplifiers (SOAs) that work based on the nonlinear polarization rotation property. The characteristics of SOA, including very fast switching action (about 0.01 ns), low power consumption, frequency independent cross-polarization gain in the C-band, cascading property, etc., make the scheme attractive. The frequency encoded data-based proposed scheme will be effective for WDM communication networks. MATLAB simulation results testify to the feasibility of the proposed scheme.

Online recorded data-based finite-time composite neural trajectory tracking control for underactuated MSVs.

This paper presents an online recorded data-based composite neural finite-time control scheme for underactuated marine surface vessels (MSVs) subject to uncertain dynamics and time-varying external disturbances. The underactuation problem of the MSVs was solved by introducing the line-of-sight (LOS) method. The uncertain dynamics of MSVs are approximated by the composite neural networks (NNs). A modified prediction error signal is designed by virtue of online recorded data. The weight updating law of NN is driven by both tracking error and prediction error, introducing additional correction information to the weights of NN, thus improving the learning ability of the NN. Furthermore, disturbance observers can be devised to estimate the compound disturbances consisting of the approximation errors of NNs and external disturbances. Moreover, the smooth function is inserted into the design of the control scheme, and the finite-time composite neural trajectory tracking control of MSVs is achieved. The stability of the MSVs trajectory tracking closed-loop control system is guaranteed rigorously by the Lyapunov approach, and the tracking error will converge to the set of residuals around zero within a finite time. The simulation tests on an MSV verify the effectiveness of the proposed control scheme.

Intrusion Detection System After Data Augmentation Schemes Based on the VAE and CVAE

Industrial Internet of Things (IoT) is the most rapidly developing industry in the current IoT industry, and the intrusion detection system (IDS) remains one of the key technologies for industrial IoT security protection. Researchers have considered applying algorithms such as machine learning and deep learning to network IDSs to cope with complex and changing network environments and to automatically extract key features from high-dimensional feature data. However, in the real industrial IoT environment, data imbalance is the main factor that affects the performance of the deep-learning-based IDS. In this article, we study the network intrusion detection model based on data level. Three data-based research schemes are constructed step by step in this article, which are a data augmentation scheme based on the variational autoencoder (VAE), a data-balancing scheme based on the conditional VAE, and a data-balancing scheme based on random undersampling and conditional VAE. The three data-level-based schemes are combined with the deep-learning-based IDS. In this article, we build experiments based on the CSE-CIC-IDS2018 dataset to verify the effectiveness of three data processing schemes. After data enhancement through the third scheme, the Macro-F1-score of the convolutional-neural-network-based IDS model improved by 3.75% and the Macro-F1-score of the gated-recurrent-unit-based IDS model improved by 5.32%.

Iterative Learning Control for Discrete-Time Systems With Full Learnability.

This article considers iterative learning control (ILC) for a class of discrete-time systems with full learnability and unknown system dynamics. First, we give a framework to analyze the learnability of the control system and build the relationship between the learnability of the control system and the input-output coupling matrix (IOCM). The control system has full learnability if and only if the IOCM is full-row rank and the control system has no learnability almost everywhere if and only if the rank of the IOCM is less than the dimension of system output. Second, by using the repetitiveness of the control system, some data-based learning schemes are developed. It is shown that we can obtain all the needed information on system dynamics through the developed learning schemes if the control system is controllable. Third, by the dynamic characteristics of system outputs of the ILC system along the iteration direction, we show how to use the available information of system dynamics to design the iterative learning gain matrix and the current state feedback gain matrix. And we strictly prove that the iterative learning scheme with the current state feedback mechanism can guarantee the monotone convergence of the ILC process if the IOCM is full-row rank. Finally, a numerical example is provided to validate the effectiveness of the proposed iterative learning scheme with the current state feedback mechanism.

Benchmarking prediction skill in binary El Ni\xf1o forecasts

Reliable El Niño Southern Oscillation (ENSO) prediction at seasonal-to-interannual lead times would be critical for different stakeholders to conduct suitable management. In recent years, new methods combining climate network analysis with El Niño prediction claim that they can predict El Niño up to 1 year in advance by overcoming the spring barrier problem (SPB). Usually this kind of method develops an index representing the relationship between different nodes in El Niño related basins, and the index crossing a certain threshold is taken as the warning of an El Niño event in the next few months. How well the prediction performs should be measured in order to estimate any improvements. However, the amount of El Niño recordings in the available data is limited, therefore it is difficult to validate whether these methods are truly predictive or their success is merely a result of chance. We propose a benchmarking method by surrogate data for a quantitative forecast validation for small data sets. We apply this method to a naïve prediction of El Niño events based on the Oscillation Niño Index (ONI) time series, where we build a data-based prediction scheme using the index series itself as input. In order to assess the network-based El Niño prediction method, we reproduce two different climate network-based forecasts and apply our method to compare the prediction skill of all these. Our benchmark shows that using the ONI itself as input to the forecast does not work for moderate lead times, while at least one of the two climate network-based methods has predictive skill well above chance at lead times of about one year.

The Cosmolian program for simulating aeolian dynamics and its application to central Australia

AbstractThe wide spatial coverage of sand dunes in continental interiors makes the understanding of their activity and accumulation history valuable for palaeoenvironmental reconstructions and the interpretation of landscape evolution. Nevertheless, the study of aeolian landscape development at the million‐year timescale is hampered by the complex interaction of factors determining dune migration and the inherently self‐destructive nature of their chronostratigraphy, thus limiting the applicability of traditional dating methods. This study presents a standalone program that simulates aeolian transport based on luminescence‐derived chronologies coupled with numerical modelling of the accumulation of cosmogenic nuclides. This integrative approach to modelling the history of aeolian landforms reveals phases of emergence of aeolian sand into the landscape, and provides a data‐based scheme that facilitates the morphodynamical study of aeolian processes over multiple timescales and up to several millions of years. The application of the program for reanalysing previously reported data from the Australian Simpson Desert reveals multiple pulses of sand dispersion into central Australia at 3.8–3.4, 2.9–2.5 and 1.5–1 Ma, corresponding to pronounced changes in climatic conditions and landscape deformation events. The synchronicity of the results with the established environmental framework that would promote the production and aeolian distribution of sand exemplifies the applicability of process‐based modelling in constructing a timeframe of key landscape evolution events in arid environments by studying aeolian deposits. The dependence of the parameters used to determine environmental settings on sand transportation patterns additionally makes the program a powerful tool to further investigate the triggers and mechanisms of aeolian processes.

An effective Two-Stage Electricity Price forecasting scheme

With the development of the global power market reform, the monopoly of the power sector and government control pattern has gradually broken. Due to the unique properties of electricity, electricity prices show high volatility and uncertainty, bringing significant challenges to the accurate prediction of electricity prices. The sudden occurrence of a few spike prices in the electricity spot market has significantly affected electricity price forecasting accuracy. We propose a novel two-stage electricity price forecasting scheme (TSEP). A multi-source data-based spike occurrence prediction scheme is presented in the first stage, which adopts a deep neural network (DNN) to predict whether the price to be forecasted is a spike or not. Specifically, to alleviate the impact of low spike price samples, the oversampling method is used to synthesize some spikes at the data level. A loss function with a misclassification penalty to increase the cost of missing price spikes is designed at the algorithm level. Based on the outputs of the first stage, in the second stage, TSEP exploits the variance stabilizing transformations respectively suitable for pre-processing spike and normal prices and combines an artificial neural network (ANN) based spike calibration model to improve the accuracy of electricity price forecasting further. The experimental results on the European Power Exchange for France (EPEX-FR) demonstrate that TSEP increases spike occurrence prediction accuracy compared with the conventional models and significantly improves the accuracy of spike electricity price forecasting without affecting the accuracy of forecasting normal electricity price.

Virtual Guidance-Based Coordinated Tracking Control of Multi-Autonomous Underwater Vehicles Using Composite Neural Learning.

This article proposes a virtual leader-based coordinated controller for the nonlinear multiple autonomous underwater vehicles (multi-AUVs) with the system uncertainties. To achieve the coordinated formation, a virtual AUV is set as the leader, while the desired command is designed using the relative position between each AUV and the virtual leader. The controller is designed based on the back-stepping scheme, and the online data-based learning scheme is used for uncertainty approximation. The highlight is that compared with previous learning methods which mostly focus on stability, the learning performance index is constructed using the collected online data in this article. The index is further used in the composite update law of the neural weights. The closed-loop system stability is analyzed via the Lyapunov approach. The simulation test on the five AUVs under fixed formation shows that the proposed method can achieve higher tracking performance with improved approximation accuracy.

Data-Driven Predictive Control for Linear Parameter-Varying Systems

Based on the extension of the behavioral theory and the Fundamental Lemma for Linear Parameter-Varying (LPV) systems, this paper introduces a Data-driven Predictive Control (DPC) scheme capable to ensure reference tracking and satisfaction of Input-Output (IO) constraints for an unknown system under the conditions that (i) the system can be represented in an LPV form and (ii) an informative data-set containing measured IO and scheduling trajectories of the system is available. It is shown that if the data set satisfies a persistence of excitation condition, then a data-driven LPV predictor of future trajectories of the system can be constructed from the IO data set and online measured data. The approach represents the first step towards a DPC solution for nonlinear and time-varying systems due to the potential of the LPV framework to represent them. Two illustrative examples, including reference tracking control of a nonlinear system, are provided to demonstrate that the data-based LPV-DPC scheme, achieves similar performance as LPV model-based predictive control.

English

Facing up with the effects of climate change, increasing human population, reduction of natural resources, and degradation of soils the agricultural sector has the challenge of meeting the world's demand for food. In this scenario, the interest of scientific communities for the use of Unmanned Aerial Vehicles (UAV) in the agricultural sector has increased in recent years. The aim of this article is to provide a global view on how scientific communities interact and identify gaps and opportunities in research of UAV in the agricultural sector. The study reviewed the scientific publications of the Web of Science from 2000 to 2018 using a data-driven approach. According to specific search terms, the most relevant publications have been downloaded from specialized database and they have been analyzed from the point of view of bibliographic data through the VOSviewer software. Examining the network graphic of citations to describe the interaction and processing the terms of the titles and abstracts with the data mining techniques, in order to identify current trends research and gaps in the literature were identified. Scientific community is working to design technological platforms to support agriculture actors for making data-based decision schemes, where computational algorithms and visualization techniques are applied. Key words: Agricultural innovation, technology applications, unmanned aerial vehicles (UAV), drones.

Data-based optimal tracking of autonomous nonlinear switching systems

In this paper, a data-based scheme is proposed to solve the optimal tracking problem of autonomous nonlinear switching systems. The system state is forced to track the reference signal by minimizing the performance function. First, the problem is transformed to solve the corresponding Bellman optimality equation in terms of the Q-function (also named as action value function). Then, an iterative algorithm based on adaptive dynamic programming (ADP) is developed to find the optimal solution which is totally based on sampled data. The linear-in-parameter (LIP) neural network is taken as the value function approximator. Considering the presence of approximation error at each iteration step, the generated approximated value function sequence is proved to be boundedness around the exact optimal solution under some verifiable assumptions. Moreover, the effect that the learning process will be terminated after a finite number of iterations is investigated in this paper. A sufficient condition for asymptotically stability of the tracking error is derived. Finally, the effectiveness of the algorithm is demonstrated with three simulation examples.